summary refs log tree commit diff stats
diff options
context:
space:
mode:
-rw-r--r--Makefile10
-rw-r--r--bsd-user/main.c10
-rw-r--r--bsd-user/x86_64/target_arch_thread.h2
-rwxr-xr-xconfigure18
-rw-r--r--contrib/plugins/Makefile87
-rw-r--r--contrib/plugins/cflow.c6
-rw-r--r--contrib/plugins/meson.build28
-rw-r--r--crypto/hash-gcrypt.c9
-rw-r--r--crypto/hash-nettle.c14
-rw-r--r--crypto/hash.c3
-rw-r--r--crypto/hmac-gcrypt.c5
-rw-r--r--crypto/hmac-nettle.c11
-rw-r--r--crypto/pbkdf-gcrypt.c6
-rw-r--r--crypto/pbkdf-nettle.c13
-rw-r--r--crypto/secret_common.c12
-rw-r--r--crypto/tlscredsanon.c35
-rw-r--r--crypto/tlscredspsk.c34
-rw-r--r--crypto/tlscredsx509.c30
-rw-r--r--docs/about/removed-features.rst6
-rw-r--r--docs/interop/vhost-user.rst24
-rw-r--r--docs/system/arm/emulation.rst1
-rw-r--r--fpu/softfloat-specialize.c.inc156
-rw-r--r--hw/acpi/acpi_generic_initiator.c148
-rw-r--r--hw/acpi/aml-build.c83
-rw-r--r--hw/acpi/cpu.c53
-rw-r--r--hw/acpi/generic_event_device.c19
-rw-r--r--hw/acpi/meson.build1
-rw-r--r--hw/acpi/pci.c242
-rw-r--r--hw/arm/virt-acpi-build.c3
-rw-r--r--hw/block/vhost-user-blk.c27
-rw-r--r--hw/core/machine.c4
-rw-r--r--hw/cxl/cxl-mailbox-utils.c111
-rw-r--r--hw/i386/acpi-build.c15
-rw-r--r--hw/i386/amd_iommu.c98
-rw-r--r--hw/i386/amd_iommu.h5
-rw-r--r--hw/i386/intel_iommu.c96
-rw-r--r--hw/i386/intel_iommu_internal.h16
-rw-r--r--hw/i386/pc.c1
-rw-r--r--hw/mem/cxl_type3.c21
-rw-r--r--hw/net/npcm_gmac.c5
-rw-r--r--hw/net/trace-events1
-rw-r--r--hw/pci-bridge/cxl_downstream.c23
-rw-r--r--hw/pci-bridge/cxl_root_port.c5
-rw-r--r--hw/pci-bridge/cxl_upstream.c6
-rw-r--r--hw/pci-bridge/pci_expander_bridge.c27
-rw-r--r--hw/pci-host/gpex-acpi.c5
-rw-r--r--hw/pci/pci.c16
-rw-r--r--hw/pci/pci_bridge.c5
-rw-r--r--hw/pci/pcie.c113
-rw-r--r--hw/rtc/ds1338.c6
-rw-r--r--hw/rtc/trace-events4
-rw-r--r--hw/sensor/tmp105.c7
-rw-r--r--hw/sensor/trace-events6
-rw-r--r--hw/sensor/trace.h1
-rw-r--r--hw/timer/imx_gpt.c18
-rw-r--r--hw/timer/trace-events6
-rw-r--r--hw/vfio/migration.c17
-rw-r--r--hw/vfio/trace-events3
-rw-r--r--hw/virtio/vhost-user.c59
-rw-r--r--hw/virtio/virtio-pci.c19
-rw-r--r--hw/watchdog/wdt_imx2.c1
-rw-r--r--include/crypto/hash.h1
-rw-r--r--include/disas/capstone.h1
-rw-r--r--include/exec/memory.h9
-rw-r--r--include/fpu/softfloat-helpers.h11
-rw-r--r--include/fpu/softfloat-types.h38
-rw-r--r--include/hw/acpi/acpi_generic_initiator.h47
-rw-r--r--include/hw/acpi/aml-build.h7
-rw-r--r--include/hw/acpi/pci.h3
-rw-r--r--include/hw/core/cpu.h2
-rw-r--r--include/hw/cxl/cxl_device.h40
-rw-r--r--include/hw/i386/intel_iommu.h3
-rw-r--r--include/hw/pci-bridge/cxl_upstream_port.h4
-rw-r--r--include/hw/pci/pci.h4
-rw-r--r--include/hw/pci/pci_bridge.h3
-rw-r--r--include/hw/pci/pci_device.h6
-rw-r--r--include/hw/pci/pcie.h2
-rw-r--r--include/hw/qdev-core.h6
-rw-r--r--include/hw/vfio/vfio-common.h3
-rw-r--r--include/hw/virtio/vhost-user.h1
-rw-r--r--include/hw/virtio/virtio-pci.h3
-rw-r--r--linux-user/arm/nwfpe/fpa11.c18
-rw-r--r--linux-user/gen-vdso-elfn.c.inc98
-rw-r--r--linux-user/gen-vdso.c40
-rw-r--r--linux-user/main.c12
-rw-r--r--linux-user/signal-common.h2
-rw-r--r--linux-user/signal.c108
-rw-r--r--meson.build47
-rw-r--r--meson_options.txt2
-rw-r--r--qapi/crypto.json54
-rw-r--r--qapi/qdev.json24
-rw-r--r--qapi/qom.json41
-rw-r--r--scripts/meson-buildoptions.sh2
-rw-r--r--system/qdev-monitor.c53
-rw-r--r--target/alpha/cpu.c11
-rw-r--r--target/arm/cpu-features.h5
-rw-r--r--target/arm/cpu.c25
-rw-r--r--target/arm/cpu.h49
-rw-r--r--target/arm/helper.c73
-rw-r--r--target/arm/internals.h41
-rw-r--r--target/arm/ptw.c10
-rw-r--r--target/arm/tcg/cpu64.c1
-rw-r--r--target/arm/tcg/hflags.c4
-rw-r--r--target/arm/tcg/op_helper.c14
-rw-r--r--target/arm/tcg/translate-a64.c2
-rw-r--r--target/arm/tcg/translate.c12
-rw-r--r--target/arm/tcg/translate.h2
-rw-r--r--target/arm/tcg/vec_helper.c9
-rw-r--r--target/hppa/fpu_helper.c6
-rw-r--r--target/i386/cpu.c4
-rw-r--r--target/i386/cpu.h3
-rw-r--r--target/i386/tcg/fpu_helper.c40
-rw-r--r--target/loongarch/tcg/fpu_helper.c1
-rw-r--r--target/m68k/cpu.c16
-rw-r--r--target/m68k/fpu_helper.c1
-rw-r--r--target/m68k/helper.c4
-rw-r--r--target/microblaze/cpu.c10
-rw-r--r--target/mips/cpu.c2
-rw-r--r--target/mips/fpu_helper.h22
-rw-r--r--target/mips/msa.c17
-rw-r--r--target/openrisc/cpu.c6
-rw-r--r--target/ppc/cpu_init.c8
-rw-r--r--target/rx/cpu.c7
-rw-r--r--target/s390x/cpu.c1
-rw-r--r--target/sparc/cpu.c10
-rw-r--r--target/sparc/fop_helper.c10
-rw-r--r--target/xtensa/cpu.c2
-rw-r--r--target/xtensa/cpu.h6
-rw-r--r--target/xtensa/fpu_helper.c35
-rwxr-xr-xtests/data/acpi/disassemle-aml.sh2
-rw-r--r--tests/data/acpi/x86/pc/DSDTbin8527 -> 8560 bytes
-rw-r--r--tests/data/acpi/x86/pc/DSDT.acpierstbin8438 -> 8471 bytes
-rw-r--r--tests/data/acpi/x86/pc/DSDT.acpihmatbin9852 -> 9885 bytes
-rw-r--r--tests/data/acpi/x86/pc/DSDT.bridgebin15398 -> 15431 bytes
-rw-r--r--tests/data/acpi/x86/pc/DSDT.cphpbin8991 -> 9024 bytes
-rw-r--r--tests/data/acpi/x86/pc/DSDT.dimmpxmbin10181 -> 10214 bytes
-rw-r--r--tests/data/acpi/x86/pc/DSDT.hpbridgebin8478 -> 8511 bytes
-rw-r--r--tests/data/acpi/x86/pc/DSDT.hpbrrootbin5034 -> 5067 bytes
-rw-r--r--tests/data/acpi/x86/pc/DSDT.ipmikcsbin8599 -> 8632 bytes
-rw-r--r--tests/data/acpi/x86/pc/DSDT.memhpbin9886 -> 9919 bytes
-rw-r--r--tests/data/acpi/x86/pc/DSDT.nohpetbin8385 -> 8418 bytes
-rw-r--r--tests/data/acpi/x86/pc/DSDT.numamembin8533 -> 8566 bytes
-rw-r--r--tests/data/acpi/x86/pc/DSDT.roothpbin12320 -> 12353 bytes
-rw-r--r--tests/data/acpi/x86/q35/DSDTbin8355 -> 8389 bytes
-rw-r--r--tests/data/acpi/x86/q35/DSDT.acpierstbin8372 -> 8406 bytes
-rw-r--r--tests/data/acpi/x86/q35/DSDT.acpihmatbin9680 -> 9714 bytes
-rw-r--r--tests/data/acpi/x86/q35/DSDT.acpihmat-noinitiatorbin8634 -> 8668 bytes
-rw-r--r--tests/data/acpi/x86/q35/DSDT.applesmcbin8401 -> 8435 bytes
-rw-r--r--tests/data/acpi/x86/q35/DSDT.bridgebin11968 -> 12002 bytes
-rw-r--r--tests/data/acpi/x86/q35/DSDT.core-countbin12913 -> 12947 bytes
-rw-r--r--tests/data/acpi/x86/q35/DSDT.core-count2bin33770 -> 33804 bytes
-rw-r--r--tests/data/acpi/x86/q35/DSDT.cphpbin8819 -> 8853 bytes
-rw-r--r--tests/data/acpi/x86/q35/DSDT.cxlbin13148 -> 13180 bytes
-rw-r--r--tests/data/acpi/x86/q35/DSDT.dimmpxmbin10009 -> 10043 bytes
-rw-r--r--tests/data/acpi/x86/q35/DSDT.ipmibtbin8430 -> 8464 bytes
-rw-r--r--tests/data/acpi/x86/q35/DSDT.ipmismbusbin8443 -> 8477 bytes
-rw-r--r--tests/data/acpi/x86/q35/DSDT.ivrsbin8372 -> 8406 bytes
-rw-r--r--tests/data/acpi/x86/q35/DSDT.memhpbin9714 -> 9748 bytes
-rw-r--r--tests/data/acpi/x86/q35/DSDT.mmio64bin9485 -> 9519 bytes
-rw-r--r--tests/data/acpi/x86/q35/DSDT.multi-bridgebin13208 -> 13242 bytes
-rw-r--r--tests/data/acpi/x86/q35/DSDT.noacpihpbin8235 -> 8269 bytes
-rw-r--r--tests/data/acpi/x86/q35/DSDT.nohpetbin8213 -> 8247 bytes
-rw-r--r--tests/data/acpi/x86/q35/DSDT.numamembin8361 -> 8395 bytes
-rw-r--r--tests/data/acpi/x86/q35/DSDT.pvpanic-isabin8456 -> 8490 bytes
-rw-r--r--tests/data/acpi/x86/q35/DSDT.thread-countbin12913 -> 12947 bytes
-rw-r--r--tests/data/acpi/x86/q35/DSDT.thread-count2bin33770 -> 33804 bytes
-rw-r--r--tests/data/acpi/x86/q35/DSDT.tis.tpm12bin8961 -> 8995 bytes
-rw-r--r--tests/data/acpi/x86/q35/DSDT.tis.tpm2bin8987 -> 9021 bytes
-rw-r--r--tests/data/acpi/x86/q35/DSDT.type4-countbin18589 -> 18623 bytes
-rw-r--r--tests/data/acpi/x86/q35/DSDT.viotbin14615 -> 14646 bytes
-rw-r--r--tests/data/acpi/x86/q35/DSDT.xapicbin35718 -> 35752 bytes
-rw-r--r--tests/fp/fp-bench.c2
-rw-r--r--tests/fp/fp-test-log2.c1
-rw-r--r--tests/fp/fp-test.c2
-rw-r--r--tests/qtest/fuzz-virtio-balloon-test.c37
-rw-r--r--tests/qtest/meson.build1
-rw-r--r--tests/tcg/Makefile.target4
-rw-r--r--tests/tcg/multiarch/linux/linux-sigrtminmax.c74
-rw-r--r--tests/unit/test-crypto-hash.c16
-rw-r--r--tests/unit/test-crypto-hmac.c8
-rw-r--r--tests/unit/test-crypto-pbkdf.c16
181 files changed, 2117 insertions, 1026 deletions
diff --git a/Makefile b/Makefile
index 917c9a34d1..b65b0bd41a 100644
--- a/Makefile
+++ b/Makefile
@@ -187,11 +187,6 @@ SUBDIR_RULES=$(foreach t, all clean distclean, $(addsuffix /$(t), $(SUBDIRS)))
 $(SUBDIR_RULES):
 	$(call quiet-command,$(MAKE) $(SUBDIR_MAKEFLAGS) -C $(dir $@) V="$(V)" TARGET_DIR="$(dir $@)" $(notdir $@),)
 
-ifneq ($(filter contrib/plugins, $(SUBDIRS)),)
-.PHONY: plugins
-plugins: contrib/plugins/all
-endif
-
 .PHONY: recurse-all recurse-clean
 recurse-all: $(addsuffix /all, $(SUBDIRS))
 recurse-clean: $(addsuffix /clean, $(SUBDIRS))
@@ -307,11 +302,6 @@ help:
 	$(call print-help,cscope,Generate cscope index)
 	$(call print-help,sparse,Run sparse on the QEMU source)
 	@echo  ''
-ifneq ($(filter contrib/plugins, $(SUBDIRS)),)
-	@echo  'Plugin targets:'
-	$(call print-help,plugins,Build the example TCG plugins)
-	@echo  ''
-endif
 	@echo  'Cleaning targets:'
 	$(call print-help,clean,Remove most generated files but keep the config)
 	$(call print-help,distclean,Remove all generated files)
diff --git a/bsd-user/main.c b/bsd-user/main.c
index cc980e6f40..61ca73c478 100644
--- a/bsd-user/main.c
+++ b/bsd-user/main.c
@@ -60,6 +60,7 @@ uintptr_t qemu_host_page_size;
 intptr_t qemu_host_page_mask;
 
 static bool opt_one_insn_per_tb;
+static unsigned long opt_tb_size;
 uintptr_t guest_base;
 bool have_guest_base;
 /*
@@ -169,6 +170,7 @@ static void usage(void)
            "                  (use '-d help' for a list of log items)\n"
            "-D logfile        write logs to 'logfile' (default stderr)\n"
            "-one-insn-per-tb  run with one guest instruction per emulated TB\n"
+           "-tb-size size     TCG translation block cache size\n"
            "-strace           log system calls\n"
            "-trace            [[enable=]<pattern>][,events=<file>][,file=<file>]\n"
            "                  specify tracing options\n"
@@ -387,6 +389,11 @@ int main(int argc, char **argv)
             seed_optarg = optarg;
         } else if (!strcmp(r, "one-insn-per-tb")) {
             opt_one_insn_per_tb = true;
+        } else if (!strcmp(r, "tb-size")) {
+            r = argv[optind++];
+            if (qemu_strtoul(r, NULL, 0, &opt_tb_size)) {
+                usage();
+            }
         } else if (!strcmp(r, "strace")) {
             do_strace = 1;
         } else if (!strcmp(r, "trace")) {
@@ -452,6 +459,8 @@ int main(int argc, char **argv)
         accel_init_interfaces(ac);
         object_property_set_bool(OBJECT(accel), "one-insn-per-tb",
                                  opt_one_insn_per_tb, &error_abort);
+        object_property_set_int(OBJECT(accel), "tb-size",
+                                opt_tb_size, &error_abort);
         ac->init_machine(NULL);
     }
 
@@ -601,6 +610,7 @@ int main(int argc, char **argv)
     init_task_state(ts);
     ts->info = info;
     ts->bprm = &bprm;
+    ts->ts_tid = qemu_get_thread_id();
     cpu->opaque = ts;
 
     target_set_brk(info->brk);
diff --git a/bsd-user/x86_64/target_arch_thread.h b/bsd-user/x86_64/target_arch_thread.h
index 52c28906d6..7739bb2154 100644
--- a/bsd-user/x86_64/target_arch_thread.h
+++ b/bsd-user/x86_64/target_arch_thread.h
@@ -31,7 +31,7 @@ static inline void target_thread_init(struct target_pt_regs *regs,
     struct image_info *infop)
 {
     regs->rax = 0;
-    regs->rsp = infop->start_stack;
+    regs->rsp = ((infop->start_stack - 8) & ~0xfUL) + 8;
     regs->rip = infop->entry;
     regs->rdi = infop->start_stack;
 }
diff --git a/configure b/configure
index f24940ca77..096b1fddb7 100755
--- a/configure
+++ b/configure
@@ -1077,7 +1077,6 @@ if test "$plugins" != "no" && test $host_bits -eq 64; then
         plugins="no"
     else
         plugins=yes
-        subdirs="$subdirs contrib/plugins"
     fi
 fi
 
@@ -1708,7 +1707,6 @@ LINKS="$LINKS .gdbinit scripts" # scripts needed by relative path in .gdbinit
 LINKS="$LINKS tests/avocado tests/data"
 LINKS="$LINKS tests/qemu-iotests/check tests/qemu-iotests/Makefile"
 LINKS="$LINKS python"
-LINKS="$LINKS contrib/plugins/Makefile "
 for f in $LINKS ; do
     if [ -e "$source_path/$f" ]; then
         symlink "$source_path/$f" "$f"
@@ -1794,22 +1792,6 @@ if test "$default_targets" = "yes"; then
   echo "CONFIG_DEFAULT_TARGETS=y" >> $config_host_mak
 fi
 
-# contrib/plugins configuration
-echo "# Automatically generated by configure - do not modify" > contrib/plugins/$config_host_mak
-echo "SRC_PATH=$source_path/contrib/plugins" >> contrib/plugins/$config_host_mak
-echo "PKG_CONFIG=${pkg_config}" >> contrib/plugins/$config_host_mak
-echo "CC=$cc $CPU_CFLAGS" >> contrib/plugins/$config_host_mak
-echo "CFLAGS=${CFLAGS-$default_cflags} $EXTRA_CFLAGS" >> contrib/plugins/$config_host_mak
-if test "$host_os" = windows; then
-  echo "DLLTOOL=$dlltool" >> contrib/plugins/$config_host_mak
-fi
-if test "$host_os" = darwin; then
-  echo "CONFIG_DARWIN=y" >> contrib/plugins/$config_host_mak
-fi
-if test "$host_os" = windows; then
-  echo "CONFIG_WIN32=y" >> contrib/plugins/$config_host_mak
-fi
-
 # tests/tcg configuration
 mkdir -p tests/tcg
 echo "# Automatically generated by configure - do not modify" > tests/tcg/$config_host_mak
diff --git a/contrib/plugins/Makefile b/contrib/plugins/Makefile
deleted file mode 100644
index bbddd4800f..0000000000
--- a/contrib/plugins/Makefile
+++ /dev/null
@@ -1,87 +0,0 @@
-# -*- Mode: makefile -*-
-#
-# This Makefile example is fairly independent from the main makefile
-# so users can take and adapt it for their build. We only really
-# include config-host.mak so we don't have to repeat probing for
-# programs that the main configure has already done for us.
-#
-
-include config-host.mak
-
-TOP_SRC_PATH = $(SRC_PATH)/../..
-
-VPATH += $(SRC_PATH)
-
-NAMES :=
-NAMES += bbv
-NAMES += execlog
-NAMES += hotblocks
-NAMES += hotpages
-NAMES += howvec
-
-# The lockstep example communicates using unix sockets,
-# and can't be easily made to work on windows.
-ifneq ($(CONFIG_WIN32),y)
-NAMES += lockstep
-endif
-
-NAMES += hwprofile
-NAMES += cache
-NAMES += drcov
-NAMES += ips
-NAMES += stoptrigger
-NAMES += cflow
-
-ifeq ($(CONFIG_WIN32),y)
-SO_SUFFIX := .dll
-LDLIBS += $(shell $(PKG_CONFIG) --libs glib-2.0)
-else
-SO_SUFFIX := .so
-endif
-
-SONAMES := $(addsuffix $(SO_SUFFIX),$(addprefix lib,$(NAMES)))
-
-# The main QEMU uses Glib extensively so it is perfectly fine to use it
-# in plugins (which many example do).
-PLUGIN_CFLAGS := $(shell $(PKG_CONFIG) --cflags glib-2.0)
-PLUGIN_CFLAGS += -fPIC -Wall
-PLUGIN_CFLAGS += -I$(TOP_SRC_PATH)/include/qemu
-
-# Helper that honours V=1 so we get some output when compiling
-quiet-@ = $(if $(V),,@$(if $1,printf "  %-7s %s\n" "$(strip $1)" "$(strip $2)" && ))
-quiet-command = $(call quiet-@,$2,$3)$1
-
-# for including , in command strings
-COMMA := ,
-
-all: $(SONAMES)
-
-%.o: %.c
-	$(call quiet-command, \
-		$(CC) $(CFLAGS) $(PLUGIN_CFLAGS) -c -o $@ $<, \
-	        BUILD, plugin $@)
-
-ifeq ($(CONFIG_WIN32),y)
-lib%$(SO_SUFFIX): %.o win32_linker.o ../../plugins/libqemu_plugin_api.a
-	$(call quiet-command, \
-		$(CC) -shared -o $@ $^ $(LDLIBS), \
-		LINK, plugin $@)
-else ifeq ($(CONFIG_DARWIN),y)
-lib%$(SO_SUFFIX): %.o
-	$(call quiet-command, \
-		$(CC) -bundle -Wl$(COMMA)-undefined$(COMMA)dynamic_lookup -o $@ $^ $(LDLIBS), \
-		LINK, plugin $@)
-else
-lib%$(SO_SUFFIX): %.o
-	$(call quiet-command, \
-		$(CC) -shared -o $@ $^ $(LDLIBS), \
-		LINK, plugin $@)
-endif
-
-
-clean distclean:
-	rm -f *.o *$(SO_SUFFIX) *.d
-	rm -Rf .libs
-
-.PHONY: all clean
-.SECONDARY:
diff --git a/contrib/plugins/cflow.c b/contrib/plugins/cflow.c
index 6faa55d10d..b39974d1cf 100644
--- a/contrib/plugins/cflow.c
+++ b/contrib/plugins/cflow.c
@@ -136,7 +136,7 @@ static void plugin_exit(qemu_plugin_id_t id, void *p)
     g_autoptr(GString) result = g_string_new("collected ");
     GList *data;
     GCompareFunc sort = &hottest;
-    int n = 0;
+    int i = 0;
 
     g_mutex_lock(&node_lock);
     g_string_append_printf(result, "%d control flow nodes in the hash table\n",
@@ -162,8 +162,8 @@ static void plugin_exit(qemu_plugin_id_t id, void *p)
     data = g_list_sort(data, sort);
 
     for (GList *l = data;
-         l != NULL && n < topn;
-         l = l->next, n++) {
+         l != NULL && i < topn;
+         l = l->next, i++) {
         NodeData *n = l->data;
         const char *type = n->mid_count ? "sync fault" : "branch";
         g_string_append_printf(result, "  addr: 0x%"PRIx64 " %s: %s (%s)\n",
diff --git a/contrib/plugins/meson.build b/contrib/plugins/meson.build
new file mode 100644
index 0000000000..63a32c2b4f
--- /dev/null
+++ b/contrib/plugins/meson.build
@@ -0,0 +1,28 @@
+contrib_plugins = ['bbv', 'cache', 'cflow', 'drcov', 'execlog', 'hotblocks',
+                   'hotpages', 'howvec', 'hwprofile', 'ips', 'stoptrigger']
+if host_os != 'windows'
+  # lockstep uses socket.h
+  contrib_plugins += 'lockstep'
+endif
+
+t = []
+if get_option('plugins')
+  foreach i : contrib_plugins
+    if host_os == 'windows'
+      t += shared_module(i, files(i + '.c') + 'win32_linker.c',
+                        include_directories: '../../include/qemu',
+                        link_depends: [win32_qemu_plugin_api_lib],
+                        link_args: ['-Lplugins', '-lqemu_plugin_api'],
+                        dependencies: glib)
+    else
+      t += shared_module(i, files(i + '.c'),
+                        include_directories: '../../include/qemu',
+                        dependencies: glib)
+    endif
+  endforeach
+endif
+if t.length() > 0
+  alias_target('contrib-plugins', t)
+else
+  run_target('contrib-plugins', command: find_program('true'))
+endif
diff --git a/crypto/hash-gcrypt.c b/crypto/hash-gcrypt.c
index 73533a4949..af61c4e75d 100644
--- a/crypto/hash-gcrypt.c
+++ b/crypto/hash-gcrypt.c
@@ -34,13 +34,16 @@ static int qcrypto_hash_alg_map[QCRYPTO_HASH_ALGO__MAX] = {
     [QCRYPTO_HASH_ALGO_SHA384] = GCRY_MD_SHA384,
     [QCRYPTO_HASH_ALGO_SHA512] = GCRY_MD_SHA512,
     [QCRYPTO_HASH_ALGO_RIPEMD160] = GCRY_MD_RMD160,
+#ifdef CONFIG_CRYPTO_SM3
+    [QCRYPTO_HASH_ALGO_SM3] = GCRY_MD_SM3,
+#endif
 };
 
 gboolean qcrypto_hash_supports(QCryptoHashAlgo alg)
 {
     if (alg < G_N_ELEMENTS(qcrypto_hash_alg_map) &&
         qcrypto_hash_alg_map[alg] != GCRY_MD_NONE) {
-        return true;
+        return gcry_md_test_algo(qcrypto_hash_alg_map[alg]) == 0;
     }
     return false;
 }
@@ -49,7 +52,7 @@ static
 QCryptoHash *qcrypto_gcrypt_hash_new(QCryptoHashAlgo alg, Error **errp)
 {
     QCryptoHash *hash;
-    int ret;
+    gcry_error_t ret;
 
     hash = g_new(QCryptoHash, 1);
     hash->alg = alg;
@@ -57,7 +60,7 @@ QCryptoHash *qcrypto_gcrypt_hash_new(QCryptoHashAlgo alg, Error **errp)
 
     ret = gcry_md_open((gcry_md_hd_t *) hash->opaque,
                        qcrypto_hash_alg_map[alg], 0);
-    if (ret < 0) {
+    if (ret != 0) {
         error_setg(errp,
                    "Unable to initialize hash algorithm: %s",
                    gcry_strerror(ret));
diff --git a/crypto/hash-nettle.c b/crypto/hash-nettle.c
index c78624b347..53f68301ef 100644
--- a/crypto/hash-nettle.c
+++ b/crypto/hash-nettle.c
@@ -26,6 +26,9 @@
 #include <nettle/md5.h>
 #include <nettle/sha.h>
 #include <nettle/ripemd160.h>
+#ifdef CONFIG_CRYPTO_SM3
+#include <nettle/sm3.h>
+#endif
 
 typedef void (*qcrypto_nettle_init)(void *ctx);
 typedef void (*qcrypto_nettle_write)(void *ctx,
@@ -43,6 +46,9 @@ union qcrypto_hash_ctx {
     struct sha384_ctx sha384;
     struct sha512_ctx sha512;
     struct ripemd160_ctx ripemd160;
+#ifdef CONFIG_CRYPTO_SM3
+    struct sm3_ctx sm3;
+#endif
 };
 
 struct qcrypto_hash_alg {
@@ -93,6 +99,14 @@ struct qcrypto_hash_alg {
         .result = (qcrypto_nettle_result)ripemd160_digest,
         .len = RIPEMD160_DIGEST_SIZE,
     },
+#ifdef CONFIG_CRYPTO_SM3
+    [QCRYPTO_HASH_ALGO_SM3] = {
+        .init = (qcrypto_nettle_init)sm3_init,
+        .write = (qcrypto_nettle_write)sm3_update,
+        .result = (qcrypto_nettle_result)sm3_digest,
+        .len = SM3_DIGEST_SIZE,
+    },
+#endif
 };
 
 gboolean qcrypto_hash_supports(QCryptoHashAlgo alg)
diff --git a/crypto/hash.c b/crypto/hash.c
index 0c8548c568..7513769e42 100644
--- a/crypto/hash.c
+++ b/crypto/hash.c
@@ -33,6 +33,9 @@ static size_t qcrypto_hash_alg_size[QCRYPTO_HASH_ALGO__MAX] = {
     [QCRYPTO_HASH_ALGO_SHA384]    = QCRYPTO_HASH_DIGEST_LEN_SHA384,
     [QCRYPTO_HASH_ALGO_SHA512]    = QCRYPTO_HASH_DIGEST_LEN_SHA512,
     [QCRYPTO_HASH_ALGO_RIPEMD160] = QCRYPTO_HASH_DIGEST_LEN_RIPEMD160,
+#ifdef CONFIG_CRYPTO_SM3
+    [QCRYPTO_HASH_ALGO_SM3] = QCRYPTO_HASH_DIGEST_LEN_SM3,
+#endif
 };
 
 size_t qcrypto_hash_digest_len(QCryptoHashAlgo alg)
diff --git a/crypto/hmac-gcrypt.c b/crypto/hmac-gcrypt.c
index 19990cb6ed..5273086eb9 100644
--- a/crypto/hmac-gcrypt.c
+++ b/crypto/hmac-gcrypt.c
@@ -26,6 +26,9 @@ static int qcrypto_hmac_alg_map[QCRYPTO_HASH_ALGO__MAX] = {
     [QCRYPTO_HASH_ALGO_SHA384] = GCRY_MAC_HMAC_SHA384,
     [QCRYPTO_HASH_ALGO_SHA512] = GCRY_MAC_HMAC_SHA512,
     [QCRYPTO_HASH_ALGO_RIPEMD160] = GCRY_MAC_HMAC_RMD160,
+#ifdef CONFIG_CRYPTO_SM3
+    [QCRYPTO_HASH_ALGO_SM3] = GCRY_MAC_HMAC_SM3,
+#endif
 };
 
 typedef struct QCryptoHmacGcrypt QCryptoHmacGcrypt;
@@ -37,7 +40,7 @@ bool qcrypto_hmac_supports(QCryptoHashAlgo alg)
 {
     if (alg < G_N_ELEMENTS(qcrypto_hmac_alg_map) &&
         qcrypto_hmac_alg_map[alg] != GCRY_MAC_NONE) {
-        return true;
+        return gcry_mac_test_algo(qcrypto_hmac_alg_map[alg]) == 0;
     }
 
     return false;
diff --git a/crypto/hmac-nettle.c b/crypto/hmac-nettle.c
index 54dd75d5ff..dd5b2ab7a1 100644
--- a/crypto/hmac-nettle.c
+++ b/crypto/hmac-nettle.c
@@ -38,6 +38,9 @@ struct QCryptoHmacNettle {
         struct hmac_sha256_ctx sha256_ctx; /* equals hmac_sha224_ctx */
         struct hmac_sha512_ctx sha512_ctx; /* equals hmac_sha384_ctx */
         struct hmac_ripemd160_ctx ripemd160_ctx;
+#ifdef CONFIG_CRYPTO_SM3
+ struct hmac_sm3_ctx ctx;
+#endif
     } u;
 };
 
@@ -89,6 +92,14 @@ struct qcrypto_nettle_hmac_alg {
         .digest = (qcrypto_nettle_hmac_digest)hmac_ripemd160_digest,
         .len = RIPEMD160_DIGEST_SIZE,
     },
+#ifdef CONFIG_CRYPTO_SM3
+    [QCRYPTO_HASH_ALGO_SM3] = {
+        .setkey = (qcrypto_nettle_hmac_setkey)hmac_sm3_set_key,
+        .update = (qcrypto_nettle_hmac_update)hmac_sm3_update,
+        .digest = (qcrypto_nettle_hmac_digest)hmac_sm3_digest,
+        .len = SM3_DIGEST_SIZE,
+    },
+#endif
 };
 
 bool qcrypto_hmac_supports(QCryptoHashAlgo alg)
diff --git a/crypto/pbkdf-gcrypt.c b/crypto/pbkdf-gcrypt.c
index 76bbb55f7a..e89b8b1c76 100644
--- a/crypto/pbkdf-gcrypt.c
+++ b/crypto/pbkdf-gcrypt.c
@@ -33,6 +33,9 @@ bool qcrypto_pbkdf2_supports(QCryptoHashAlgo hash)
     case QCRYPTO_HASH_ALGO_SHA384:
     case QCRYPTO_HASH_ALGO_SHA512:
     case QCRYPTO_HASH_ALGO_RIPEMD160:
+#ifdef CONFIG_CRYPTO_SM3
+    case QCRYPTO_HASH_ALGO_SM3:
+#endif
         return qcrypto_hash_supports(hash);
     default:
         return false;
@@ -54,6 +57,9 @@ int qcrypto_pbkdf2(QCryptoHashAlgo hash,
         [QCRYPTO_HASH_ALGO_SHA384] = GCRY_MD_SHA384,
         [QCRYPTO_HASH_ALGO_SHA512] = GCRY_MD_SHA512,
         [QCRYPTO_HASH_ALGO_RIPEMD160] = GCRY_MD_RMD160,
+#ifdef CONFIG_CRYPTO_SM3
+        [QCRYPTO_HASH_ALGO_SM3] = GCRY_MD_SM3,
+#endif
     };
     int ret;
 
diff --git a/crypto/pbkdf-nettle.c b/crypto/pbkdf-nettle.c
index 93e686c2c6..3ef9c1b52c 100644
--- a/crypto/pbkdf-nettle.c
+++ b/crypto/pbkdf-nettle.c
@@ -34,6 +34,9 @@ bool qcrypto_pbkdf2_supports(QCryptoHashAlgo hash)
     case QCRYPTO_HASH_ALGO_SHA384:
     case QCRYPTO_HASH_ALGO_SHA512:
     case QCRYPTO_HASH_ALGO_RIPEMD160:
+#ifdef CONFIG_CRYPTO_SM3
+    case QCRYPTO_HASH_ALGO_SM3:
+#endif
         return true;
     default:
         return false;
@@ -55,6 +58,9 @@ int qcrypto_pbkdf2(QCryptoHashAlgo hash,
         struct hmac_sha384_ctx sha384;
         struct hmac_sha512_ctx sha512;
         struct hmac_ripemd160_ctx ripemd160;
+#ifdef CONFIG_CRYPTO_SM3
+        struct hmac_sm3_ctx sm3;
+#endif
     } ctx;
 
     if (iterations > UINT_MAX) {
@@ -106,6 +112,13 @@ int qcrypto_pbkdf2(QCryptoHashAlgo hash,
         PBKDF2(&ctx.ripemd160, hmac_ripemd160_update, hmac_ripemd160_digest,
                RIPEMD160_DIGEST_SIZE, iterations, nsalt, salt, nout, out);
         break;
+#ifdef CONFIG_CRYPTO_SM3
+    case QCRYPTO_HASH_ALGO_SM3:
+        hmac_sm3_set_key(&ctx.sm3, nkey, key);
+        PBKDF2(&ctx.sm3, hmac_sm3_update, hmac_sm3_digest,
+               SM3_DIGEST_SIZE, iterations, nsalt, salt, nout, out);
+        break;
+#endif
 
     default:
         error_setg_errno(errp, ENOSYS,
diff --git a/crypto/secret_common.c b/crypto/secret_common.c
index 2c141107a5..dbda998940 100644
--- a/crypto/secret_common.c
+++ b/crypto/secret_common.c
@@ -191,15 +191,6 @@ qcrypto_secret_complete(UserCreatable *uc, Error **errp)
 }
 
 
-static bool
-qcrypto_secret_prop_get_loaded(Object *obj,
-                               Error **errp G_GNUC_UNUSED)
-{
-    QCryptoSecretCommon *secret = QCRYPTO_SECRET_COMMON(obj);
-    return secret->rawdata != NULL;
-}
-
-
 static void
 qcrypto_secret_prop_set_format(Object *obj,
                                int value,
@@ -278,9 +269,6 @@ qcrypto_secret_class_init(ObjectClass *oc, void *data)
 
     ucc->complete = qcrypto_secret_complete;
 
-    object_class_property_add_bool(oc, "loaded",
-                                   qcrypto_secret_prop_get_loaded,
-                                   NULL);
     object_class_property_add_enum(oc, "format",
                                    "QCryptoSecretFormat",
                                    &QCryptoSecretFormat_lookup,
diff --git a/crypto/tlscredsanon.c b/crypto/tlscredsanon.c
index c0d23a0ef3..476cf89c96 100644
--- a/crypto/tlscredsanon.c
+++ b/crypto/tlscredsanon.c
@@ -127,37 +127,6 @@ qcrypto_tls_creds_anon_complete(UserCreatable *uc, Error **errp)
 }
 
 
-#ifdef CONFIG_GNUTLS
-
-
-static bool
-qcrypto_tls_creds_anon_prop_get_loaded(Object *obj,
-                                       Error **errp G_GNUC_UNUSED)
-{
-    QCryptoTLSCredsAnon *creds = QCRYPTO_TLS_CREDS_ANON(obj);
-
-    if (creds->parent_obj.endpoint == QCRYPTO_TLS_CREDS_ENDPOINT_SERVER) {
-        return creds->data.server != NULL;
-    } else {
-        return creds->data.client != NULL;
-    }
-}
-
-
-#else /* ! CONFIG_GNUTLS */
-
-
-static bool
-qcrypto_tls_creds_anon_prop_get_loaded(Object *obj G_GNUC_UNUSED,
-                                       Error **errp G_GNUC_UNUSED)
-{
-    return false;
-}
-
-
-#endif /* ! CONFIG_GNUTLS */
-
-
 static void
 qcrypto_tls_creds_anon_finalize(Object *obj)
 {
@@ -173,10 +142,6 @@ qcrypto_tls_creds_anon_class_init(ObjectClass *oc, void *data)
     UserCreatableClass *ucc = USER_CREATABLE_CLASS(oc);
 
     ucc->complete = qcrypto_tls_creds_anon_complete;
-
-    object_class_property_add_bool(oc, "loaded",
-                                   qcrypto_tls_creds_anon_prop_get_loaded,
-                                   NULL);
 }
 
 
diff --git a/crypto/tlscredspsk.c b/crypto/tlscredspsk.c
index 0d6b71a37c..aa270d7988 100644
--- a/crypto/tlscredspsk.c
+++ b/crypto/tlscredspsk.c
@@ -206,37 +206,6 @@ qcrypto_tls_creds_psk_complete(UserCreatable *uc, Error **errp)
 }
 
 
-#ifdef CONFIG_GNUTLS
-
-
-static bool
-qcrypto_tls_creds_psk_prop_get_loaded(Object *obj,
-                                      Error **errp G_GNUC_UNUSED)
-{
-    QCryptoTLSCredsPSK *creds = QCRYPTO_TLS_CREDS_PSK(obj);
-
-    if (creds->parent_obj.endpoint == QCRYPTO_TLS_CREDS_ENDPOINT_SERVER) {
-        return creds->data.server != NULL;
-    } else {
-        return creds->data.client != NULL;
-    }
-}
-
-
-#else /* ! CONFIG_GNUTLS */
-
-
-static bool
-qcrypto_tls_creds_psk_prop_get_loaded(Object *obj G_GNUC_UNUSED,
-                                      Error **errp G_GNUC_UNUSED)
-{
-    return false;
-}
-
-
-#endif /* ! CONFIG_GNUTLS */
-
-
 static void
 qcrypto_tls_creds_psk_finalize(Object *obj)
 {
@@ -273,9 +242,6 @@ qcrypto_tls_creds_psk_class_init(ObjectClass *oc, void *data)
 
     ucc->complete = qcrypto_tls_creds_psk_complete;
 
-    object_class_property_add_bool(oc, "loaded",
-                                   qcrypto_tls_creds_psk_prop_get_loaded,
-                                   NULL);
     object_class_property_add_str(oc, "username",
                                   qcrypto_tls_creds_psk_prop_get_username,
                                   qcrypto_tls_creds_psk_prop_set_username);
diff --git a/crypto/tlscredsx509.c b/crypto/tlscredsx509.c
index d14313925d..24ec584922 100644
--- a/crypto/tlscredsx509.c
+++ b/crypto/tlscredsx509.c
@@ -695,33 +695,6 @@ qcrypto_tls_creds_x509_complete(UserCreatable *uc, Error **errp)
 }
 
 
-#ifdef CONFIG_GNUTLS
-
-
-static bool
-qcrypto_tls_creds_x509_prop_get_loaded(Object *obj,
-                                       Error **errp G_GNUC_UNUSED)
-{
-    QCryptoTLSCredsX509 *creds = QCRYPTO_TLS_CREDS_X509(obj);
-
-    return creds->data != NULL;
-}
-
-
-#else /* ! CONFIG_GNUTLS */
-
-
-static bool
-qcrypto_tls_creds_x509_prop_get_loaded(Object *obj G_GNUC_UNUSED,
-                                       Error **errp G_GNUC_UNUSED)
-{
-    return false;
-}
-
-
-#endif /* ! CONFIG_GNUTLS */
-
-
 static void
 qcrypto_tls_creds_x509_prop_set_sanity(Object *obj,
                                        bool value,
@@ -838,9 +811,6 @@ qcrypto_tls_creds_x509_class_init(ObjectClass *oc, void *data)
 
     ucc->complete = qcrypto_tls_creds_x509_complete;
 
-    object_class_property_add_bool(oc, "loaded",
-                                   qcrypto_tls_creds_x509_prop_get_loaded,
-                                   NULL);
     object_class_property_add_bool(oc, "sanity-check",
                                    qcrypto_tls_creds_x509_prop_get_sanity,
                                    qcrypto_tls_creds_x509_prop_set_sanity);
diff --git a/docs/about/removed-features.rst b/docs/about/removed-features.rst
index 912e0a1fcf..ee6455aeee 100644
--- a/docs/about/removed-features.rst
+++ b/docs/about/removed-features.rst
@@ -355,13 +355,13 @@ The ``-writeconfig`` option was not able to serialize the entire contents
 of the QEMU command line.  It is thus considered a failed experiment
 and removed without a replacement.
 
-``loaded`` property of ``secret`` and ``secret_keyring`` objects (removed in 7.1)
-'''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''
+``loaded`` property of secret and TLS credential objects (removed in 9.2)
+'''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''
 
 The ``loaded=on`` option in the command line or QMP ``object-add`` either had
 no effect (if ``loaded`` was the last option) or caused options to be
 effectively ignored as if they were not given.  The property is therefore
-useless and should simply be removed.
+useless and has been removed.
 
 ``opened`` property of ``rng-*`` objects (removed in 7.1)
 '''''''''''''''''''''''''''''''''''''''''''''''''''''''''
diff --git a/docs/interop/vhost-user.rst b/docs/interop/vhost-user.rst
index d8419fd2f1..2e50f2ddfa 100644
--- a/docs/interop/vhost-user.rst
+++ b/docs/interop/vhost-user.rst
@@ -167,6 +167,8 @@ A vring address description
 Note that a ring address is an IOVA if ``VIRTIO_F_IOMMU_PLATFORM`` has
 been negotiated. Otherwise it is a user address.
 
+.. _memory_region_description:
+
 Memory region description
 ^^^^^^^^^^^^^^^^^^^^^^^^^
 
@@ -180,7 +182,7 @@ Memory region description
 
 :user address: a 64-bit user address
 
-:mmap offset: 64-bit offset where region starts in the mapped memory
+:mmap offset: a 64-bit offset where region starts in the mapped memory
 
 When the ``VHOST_USER_PROTOCOL_F_XEN_MMAP`` protocol feature has been
 successfully negotiated, the memory region description contains two extra
@@ -190,7 +192,7 @@ fields at the end.
 | guest address | size | user address | mmap offset | xen mmap flags | domid |
 +---------------+------+--------------+-------------+----------------+-------+
 
-:xen mmap flags: 32-bit bit field
+:xen mmap flags: a 32-bit bit field
 
 - Bit 0 is set for Xen foreign memory mapping.
 - Bit 1 is set for Xen grant memory mapping.
@@ -211,7 +213,7 @@ Single memory region description
 
 :padding: 64-bit
 
-A region is represented by Memory region description.
+:region: region is represented by :ref:`Memory region description <memory_region_description>`.
 
 Multiple Memory regions description
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
@@ -224,7 +226,7 @@ Multiple Memory regions description
 
 :padding: 32-bit
 
-A region is represented by Memory region description.
+:regions: regions field contains 8 regions of type :ref:`Memory region description <memory_region_description>`.
 
 Log description
 ^^^^^^^^^^^^^^^
@@ -233,9 +235,9 @@ Log description
 | log size | log offset |
 +----------+------------+
 
-:log size: size of area used for logging
+:log size: a 64-bit size of area used for logging
 
-:log offset: offset from start of supplied file descriptor where
+:log offset: a 64-bit offset from start of supplied file descriptor where
              logging starts (i.e. where guest address 0 would be
              logged)
 
@@ -382,7 +384,7 @@ the kernel implementation.
 
 The communication consists of the *front-end* sending message requests and
 the *back-end* sending message replies. Most of the requests don't require
-replies. Here is a list of the ones that do:
+replies, except for the following requests:
 
 * ``VHOST_USER_GET_FEATURES``
 * ``VHOST_USER_GET_PROTOCOL_FEATURES``
@@ -1239,11 +1241,11 @@ Front-end message types
   (*a vring descriptor index for split virtqueues* vs. *vring descriptor
   indices for packed virtqueues*).
 
-  When and as long as all of a device’s vrings are stopped, it is
+  When and as long as all of a device's vrings are stopped, it is
   *suspended*, see :ref:`Suspended device state
   <suspended_device_state>`.
 
-  The request payload’s *num* field is currently reserved and must be
+  The request payload's *num* field is currently reserved and must be
   set to 0.
 
 ``VHOST_USER_SET_VRING_KICK``
@@ -1662,7 +1664,7 @@ Front-end message types
   :reply payload: ``u64``
 
   Front-end and back-end negotiate a channel over which to transfer the
-  back-end’s internal state during migration.  Either side (front-end or
+  back-end's internal state during migration.  Either side (front-end or
   back-end) may create the channel.  The nature of this channel is not
   restricted or defined in this document, but whichever side creates it
   must create a file descriptor that is provided to the respectively
@@ -1714,7 +1716,7 @@ Front-end message types
   :request payload: N/A
   :reply payload: ``u64``
 
-  After transferring the back-end’s internal state during migration (see
+  After transferring the back-end's internal state during migration (see
   the :ref:`Migrating back-end state <migrating_backend_state>`
   section), check whether the back-end was able to successfully fully
   process the state.
diff --git a/docs/system/arm/emulation.rst b/docs/system/arm/emulation.rst
index 35f52a54b1..a2a388f091 100644
--- a/docs/system/arm/emulation.rst
+++ b/docs/system/arm/emulation.rst
@@ -26,6 +26,7 @@ the following architecture extensions:
 - FEAT_BF16 (AArch64 BFloat16 instructions)
 - FEAT_BTI (Branch Target Identification)
 - FEAT_CCIDX (Extended cache index)
+- FEAT_CMOW (Control for cache maintenance permission)
 - FEAT_CRC32 (CRC32 instructions)
 - FEAT_Crypto (Cryptographic Extension)
 - FEAT_CSV2 (Cache speculation variant 2)
diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc
index 4e279b9bc4..b5a3208050 100644
--- a/fpu/softfloat-specialize.c.inc
+++ b/fpu/softfloat-specialize.c.inc
@@ -390,118 +390,80 @@ bool float32_is_signaling_nan(float32 a_, float_status *status)
 static int pickNaN(FloatClass a_cls, FloatClass b_cls,
                    bool aIsLargerSignificand, float_status *status)
 {
-#if defined(TARGET_ARM) || defined(TARGET_MIPS) || defined(TARGET_HPPA) || \
-    defined(TARGET_LOONGARCH64) || defined(TARGET_S390X)
-    /* ARM mandated NaN propagation rules (see FPProcessNaNs()), take
-     * the first of:
-     *  1. A if it is signaling
-     *  2. B if it is signaling
-     *  3. A (quiet)
-     *  4. B (quiet)
-     * A signaling NaN is always quietened before returning it.
-     */
-    /* According to MIPS specifications, if one of the two operands is
-     * a sNaN, a new qNaN has to be generated. This is done in
-     * floatXX_silence_nan(). For qNaN inputs the specifications
-     * says: "When possible, this QNaN result is one of the operand QNaN
-     * values." In practice it seems that most implementations choose
-     * the first operand if both operands are qNaN. In short this gives
-     * the following rules:
-     *  1. A if it is signaling
-     *  2. B if it is signaling
-     *  3. A (quiet)
-     *  4. B (quiet)
-     * A signaling NaN is always silenced before returning it.
-     */
-    if (is_snan(a_cls)) {
-        return 0;
-    } else if (is_snan(b_cls)) {
-        return 1;
-    } else if (is_qnan(a_cls)) {
-        return 0;
-    } else {
-        return 1;
-    }
-#elif defined(TARGET_PPC) || defined(TARGET_M68K)
-    /* PowerPC propagation rules:
-     *  1. A if it sNaN or qNaN
-     *  2. B if it sNaN or qNaN
-     * A signaling NaN is always silenced before returning it.
-     */
-    /* M68000 FAMILY PROGRAMMER'S REFERENCE MANUAL
-     * 3.4 FLOATING-POINT INSTRUCTION DETAILS
-     * If either operand, but not both operands, of an operation is a
-     * nonsignaling NaN, then that NaN is returned as the result. If both
-     * operands are nonsignaling NaNs, then the destination operand
-     * nonsignaling NaN is returned as the result.
-     * If either operand to an operation is a signaling NaN (SNaN), then the
-     * SNaN bit is set in the FPSR EXC byte. If the SNaN exception enable bit
-     * is set in the FPCR ENABLE byte, then the exception is taken and the
-     * destination is not modified. If the SNaN exception enable bit is not
-     * set, setting the SNaN bit in the operand to a one converts the SNaN to
-     * a nonsignaling NaN. The operation then continues as described in the
-     * preceding paragraph for nonsignaling NaNs.
-     */
-    if (is_nan(a_cls)) {
-        return 0;
-    } else {
-        return 1;
-    }
-#elif defined(TARGET_SPARC)
-    /* Prefer SNaN over QNaN, order B then A. */
-    if (is_snan(b_cls)) {
-        return 1;
-    } else if (is_snan(a_cls)) {
-        return 0;
-    } else if (is_qnan(b_cls)) {
-        return 1;
-    } else {
-        return 0;
-    }
-#elif defined(TARGET_XTENSA)
     /*
-     * Xtensa has two NaN propagation modes.
-     * Which one is active is controlled by float_status::use_first_nan.
+     * We guarantee not to require the target to tell us how to
+     * pick a NaN if we're always returning the default NaN.
+     * But if we're not in default-NaN mode then the target must
+     * specify via set_float_2nan_prop_rule().
      */
-    if (status->use_first_nan) {
-        if (is_nan(a_cls)) {
+    assert(!status->default_nan_mode);
+
+    switch (status->float_2nan_prop_rule) {
+    case float_2nan_prop_s_ab:
+        if (is_snan(a_cls)) {
+            return 0;
+        } else if (is_snan(b_cls)) {
+            return 1;
+        } else if (is_qnan(a_cls)) {
             return 0;
         } else {
             return 1;
         }
-    } else {
-        if (is_nan(b_cls)) {
+        break;
+    case float_2nan_prop_s_ba:
+        if (is_snan(b_cls)) {
+            return 1;
+        } else if (is_snan(a_cls)) {
+            return 0;
+        } else if (is_qnan(b_cls)) {
             return 1;
         } else {
             return 0;
         }
-    }
-#else
-    /* This implements x87 NaN propagation rules:
-     * SNaN + QNaN => return the QNaN
-     * two SNaNs => return the one with the larger significand, silenced
-     * two QNaNs => return the one with the larger significand
-     * SNaN and a non-NaN => return the SNaN, silenced
-     * QNaN and a non-NaN => return the QNaN
-     *
-     * If we get down to comparing significands and they are the same,
-     * return the NaN with the positive sign bit (if any).
-     */
-    if (is_snan(a_cls)) {
-        if (is_snan(b_cls)) {
-            return aIsLargerSignificand ? 0 : 1;
+        break;
+    case float_2nan_prop_ab:
+        if (is_nan(a_cls)) {
+            return 0;
+        } else {
+            return 1;
         }
-        return is_qnan(b_cls) ? 1 : 0;
-    } else if (is_qnan(a_cls)) {
-        if (is_snan(b_cls) || !is_qnan(b_cls)) {
+        break;
+    case float_2nan_prop_ba:
+        if (is_nan(b_cls)) {
+            return 1;
+        } else {
             return 0;
+        }
+        break;
+    case float_2nan_prop_x87:
+        /*
+         * This implements x87 NaN propagation rules:
+         * SNaN + QNaN => return the QNaN
+         * two SNaNs => return the one with the larger significand, silenced
+         * two QNaNs => return the one with the larger significand
+         * SNaN and a non-NaN => return the SNaN, silenced
+         * QNaN and a non-NaN => return the QNaN
+         *
+         * If we get down to comparing significands and they are the same,
+         * return the NaN with the positive sign bit (if any).
+         */
+        if (is_snan(a_cls)) {
+            if (is_snan(b_cls)) {
+                return aIsLargerSignificand ? 0 : 1;
+            }
+            return is_qnan(b_cls) ? 1 : 0;
+        } else if (is_qnan(a_cls)) {
+            if (is_snan(b_cls) || !is_qnan(b_cls)) {
+                return 0;
+            } else {
+                return aIsLargerSignificand ? 0 : 1;
+            }
         } else {
-            return aIsLargerSignificand ? 0 : 1;
+            return 1;
         }
-    } else {
-        return 1;
+    default:
+        g_assert_not_reached();
     }
-#endif
 }
 
 /*----------------------------------------------------------------------------
diff --git a/hw/acpi/acpi_generic_initiator.c b/hw/acpi/acpi_generic_initiator.c
deleted file mode 100644
index 17b9a052f5..0000000000
--- a/hw/acpi/acpi_generic_initiator.c
+++ /dev/null
@@ -1,148 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Copyright (c) 2024, NVIDIA CORPORATION & AFFILIATES. All rights reserved
- */
-
-#include "qemu/osdep.h"
-#include "hw/acpi/acpi_generic_initiator.h"
-#include "hw/acpi/aml-build.h"
-#include "hw/boards.h"
-#include "hw/pci/pci_device.h"
-#include "qemu/error-report.h"
-
-typedef struct AcpiGenericInitiatorClass {
-    ObjectClass parent_class;
-} AcpiGenericInitiatorClass;
-
-OBJECT_DEFINE_TYPE_WITH_INTERFACES(AcpiGenericInitiator, acpi_generic_initiator,
-                   ACPI_GENERIC_INITIATOR, OBJECT,
-                   { TYPE_USER_CREATABLE },
-                   { NULL })
-
-OBJECT_DECLARE_SIMPLE_TYPE(AcpiGenericInitiator, ACPI_GENERIC_INITIATOR)
-
-static void acpi_generic_initiator_init(Object *obj)
-{
-    AcpiGenericInitiator *gi = ACPI_GENERIC_INITIATOR(obj);
-
-    gi->node = MAX_NODES;
-    gi->pci_dev = NULL;
-}
-
-static void acpi_generic_initiator_finalize(Object *obj)
-{
-    AcpiGenericInitiator *gi = ACPI_GENERIC_INITIATOR(obj);
-
-    g_free(gi->pci_dev);
-}
-
-static void acpi_generic_initiator_set_pci_device(Object *obj, const char *val,
-                                                  Error **errp)
-{
-    AcpiGenericInitiator *gi = ACPI_GENERIC_INITIATOR(obj);
-
-    gi->pci_dev = g_strdup(val);
-}
-
-static void acpi_generic_initiator_set_node(Object *obj, Visitor *v,
-                                            const char *name, void *opaque,
-                                            Error **errp)
-{
-    AcpiGenericInitiator *gi = ACPI_GENERIC_INITIATOR(obj);
-    MachineState *ms = MACHINE(qdev_get_machine());
-    uint32_t value;
-
-    if (!visit_type_uint32(v, name, &value, errp)) {
-        return;
-    }
-
-    if (value >= MAX_NODES) {
-        error_printf("%s: Invalid NUMA node specified\n",
-                     TYPE_ACPI_GENERIC_INITIATOR);
-        exit(1);
-    }
-
-    gi->node = value;
-    ms->numa_state->nodes[gi->node].has_gi = true;
-}
-
-static void acpi_generic_initiator_class_init(ObjectClass *oc, void *data)
-{
-    object_class_property_add_str(oc, "pci-dev", NULL,
-        acpi_generic_initiator_set_pci_device);
-    object_class_property_add(oc, "node", "int", NULL,
-        acpi_generic_initiator_set_node, NULL, NULL);
-}
-
-/*
- * ACPI 6.3:
- * Table 5-78 Generic Initiator Affinity Structure
- */
-static void
-build_srat_generic_pci_initiator_affinity(GArray *table_data, int node,
-                                          PCIDeviceHandle *handle)
-{
-    uint8_t index;
-
-    build_append_int_noprefix(table_data, 5, 1);  /* Type */
-    build_append_int_noprefix(table_data, 32, 1); /* Length */
-    build_append_int_noprefix(table_data, 0, 1);  /* Reserved */
-    build_append_int_noprefix(table_data, 1, 1);  /* Device Handle Type: PCI */
-    build_append_int_noprefix(table_data, node, 4);  /* Proximity Domain */
-
-    /* Device Handle - PCI */
-    build_append_int_noprefix(table_data, handle->segment, 2);
-    build_append_int_noprefix(table_data, handle->bdf, 2);
-    for (index = 0; index < 12; index++) {
-        build_append_int_noprefix(table_data, 0, 1);
-    }
-
-    build_append_int_noprefix(table_data, GEN_AFFINITY_ENABLED, 4); /* Flags */
-    build_append_int_noprefix(table_data, 0, 4);     /* Reserved */
-}
-
-static int build_all_acpi_generic_initiators(Object *obj, void *opaque)
-{
-    MachineState *ms = MACHINE(qdev_get_machine());
-    AcpiGenericInitiator *gi;
-    GArray *table_data = opaque;
-    PCIDeviceHandle dev_handle;
-    PCIDevice *pci_dev;
-    Object *o;
-
-    if (!object_dynamic_cast(obj, TYPE_ACPI_GENERIC_INITIATOR)) {
-        return 0;
-    }
-
-    gi = ACPI_GENERIC_INITIATOR(obj);
-    if (gi->node >= ms->numa_state->num_nodes) {
-        error_printf("%s: Specified node %d is invalid.\n",
-                     TYPE_ACPI_GENERIC_INITIATOR, gi->node);
-        exit(1);
-    }
-
-    o = object_resolve_path_type(gi->pci_dev, TYPE_PCI_DEVICE, NULL);
-    if (!o) {
-        error_printf("%s: Specified device must be a PCI device.\n",
-                     TYPE_ACPI_GENERIC_INITIATOR);
-        exit(1);
-    }
-
-    pci_dev = PCI_DEVICE(o);
-
-    dev_handle.segment = 0;
-    dev_handle.bdf = PCI_BUILD_BDF(pci_bus_num(pci_get_bus(pci_dev)),
-                                               pci_dev->devfn);
-
-    build_srat_generic_pci_initiator_affinity(table_data,
-                                              gi->node, &dev_handle);
-
-    return 0;
-}
-
-void build_srat_generic_pci_initiator(GArray *table_data)
-{
-    object_child_foreach_recursive(object_get_root(),
-                                   build_all_acpi_generic_initiators,
-                                   table_data);
-}
diff --git a/hw/acpi/aml-build.c b/hw/acpi/aml-build.c
index 34e0ddbde8..6a76626177 100644
--- a/hw/acpi/aml-build.c
+++ b/hw/acpi/aml-build.c
@@ -1938,6 +1938,89 @@ void build_srat_memory(GArray *table_data, uint64_t base,
 }
 
 /*
+ * ACPI Spec Revision 6.3
+ * Table 5-80 Device Handle - PCI
+ */
+static void build_append_srat_pci_device_handle(GArray *table_data,
+                                                uint16_t segment,
+                                                uint8_t bus, uint8_t devfn)
+{
+    /* PCI segment number */
+    build_append_int_noprefix(table_data, segment, 2);
+    /* PCI Bus Device Function */
+    build_append_int_noprefix(table_data, bus, 1);
+    build_append_int_noprefix(table_data, devfn, 1);
+    /* Reserved */
+    build_append_int_noprefix(table_data, 0, 12);
+}
+
+static void build_append_srat_acpi_device_handle(GArray *table_data,
+                                                 const char *hid,
+                                                 uint32_t uid)
+{
+    assert(strlen(hid) == 8);
+    /* Device Handle - ACPI */
+    for (int i = 0; i < sizeof(hid); i++) {
+        build_append_int_noprefix(table_data, hid[i], 1);
+    }
+    build_append_int_noprefix(table_data, uid, 4);
+    build_append_int_noprefix(table_data, 0, 4);
+}
+
+/*
+ * ACPI spec, Revision 6.3
+ * 5.2.16.6 Generic Initiator Affinity Structure
+ *    With PCI Device Handle.
+ */
+void build_srat_pci_generic_initiator(GArray *table_data, uint32_t node,
+                                      uint16_t segment, uint8_t bus,
+                                      uint8_t devfn)
+{
+    /* Type */
+    build_append_int_noprefix(table_data, 5, 1);
+    /* Length */
+    build_append_int_noprefix(table_data, 32, 1);
+    /* Reserved */
+    build_append_int_noprefix(table_data, 0, 1);
+    /* Device Handle Type: PCI */
+    build_append_int_noprefix(table_data, 1, 1);
+    /* Proximity Domain */
+    build_append_int_noprefix(table_data, node, 4);
+    /* Device Handle */
+    build_append_srat_pci_device_handle(table_data, segment, bus, devfn);
+    /* Flags - GI Enabled */
+    build_append_int_noprefix(table_data, 1, 4);
+    /* Reserved */
+    build_append_int_noprefix(table_data, 0, 4);
+}
+
+/*
+ * ACPI spec, Revision 6.5
+ * 5.2.16.7 Generic Port Affinity Structure
+ *   With ACPI Device Handle.
+ */
+void build_srat_acpi_generic_port(GArray *table_data, uint32_t node,
+                                  const char *hid, uint32_t uid)
+{
+    /* Type */
+    build_append_int_noprefix(table_data, 6, 1);
+    /* Length */
+    build_append_int_noprefix(table_data, 32, 1);
+    /* Reserved */
+    build_append_int_noprefix(table_data, 0, 1);
+    /* Device Handle Type: ACPI */
+    build_append_int_noprefix(table_data, 0, 1);
+    /* Proximity Domain */
+    build_append_int_noprefix(table_data, node, 4);
+    /* Device Handle */
+    build_append_srat_acpi_device_handle(table_data, hid, uid);
+    /* Flags - GP Enabled */
+    build_append_int_noprefix(table_data, 1, 4);
+    /* Reserved */
+    build_append_int_noprefix(table_data, 0, 4);
+}
+
+/*
  * ACPI spec 5.2.17 System Locality Distance Information Table
  * (Revision 2.0 or later)
  */
diff --git a/hw/acpi/cpu.c b/hw/acpi/cpu.c
index 5cb60ca8bc..23443f09a5 100644
--- a/hw/acpi/cpu.c
+++ b/hw/acpi/cpu.c
@@ -50,6 +50,18 @@ void acpi_cpu_ospm_status(CPUHotplugState *cpu_st, ACPIOSTInfoList ***list)
     }
 }
 
+static bool check_cpu_enabled_status(DeviceState *dev)
+{
+    CPUClass *k = dev ? CPU_GET_CLASS(dev) : NULL;
+    CPUState *cpu = CPU(dev);
+
+    if (cpu && (!k->cpu_enabled_status || k->cpu_enabled_status(cpu))) {
+        return true;
+    }
+
+    return false;
+}
+
 static uint64_t cpu_hotplug_rd(void *opaque, hwaddr addr, unsigned size)
 {
     uint64_t val = 0;
@@ -63,10 +75,11 @@ static uint64_t cpu_hotplug_rd(void *opaque, hwaddr addr, unsigned size)
     cdev = &cpu_st->devs[cpu_st->selector];
     switch (addr) {
     case ACPI_CPU_FLAGS_OFFSET_RW: /* pack and return is_* fields */
-        val |= cdev->cpu ? 1 : 0;
+        val |= check_cpu_enabled_status(DEVICE(cdev->cpu)) ? 1 : 0;
         val |= cdev->is_inserting ? 2 : 0;
         val |= cdev->is_removing  ? 4 : 0;
         val |= cdev->fw_remove  ? 16 : 0;
+        val |= cdev->cpu ? 32 : 0;
         trace_cpuhp_acpi_read_flags(cpu_st->selector, val);
         break;
     case ACPI_CPU_CMD_DATA_OFFSET_RW:
@@ -233,6 +246,17 @@ void cpu_hotplug_hw_init(MemoryRegion *as, Object *owner,
     memory_region_add_subregion(as, base_addr, &state->ctrl_reg);
 }
 
+static bool should_remain_acpi_present(DeviceState *dev)
+{
+    CPUClass *k = CPU_GET_CLASS(dev);
+    /*
+     * A system may contain CPUs that are always present on one die, NUMA node,
+     * or socket, yet may be non-present on another simultaneously. Check from
+     * architecture specific code.
+     */
+    return k->cpu_persistent_status && k->cpu_persistent_status(CPU(dev));
+}
+
 static AcpiCpuStatus *get_cpu_status(CPUHotplugState *cpu_st, DeviceState *dev)
 {
     CPUClass *k = CPU_GET_CLASS(dev);
@@ -289,7 +313,9 @@ void acpi_cpu_unplug_cb(CPUHotplugState *cpu_st,
         return;
     }
 
-    cdev->cpu = NULL;
+    if (!should_remain_acpi_present(dev)) {
+        cdev->cpu = NULL;
+    }
 }
 
 static const VMStateDescription vmstate_cpuhp_sts = {
@@ -336,6 +362,7 @@ const VMStateDescription vmstate_cpu_hotplug = {
 #define CPU_REMOVE_EVENT  "CRMV"
 #define CPU_EJECT_EVENT   "CEJ0"
 #define CPU_FW_EJECT_EVENT "CEJF"
+#define CPU_PRESENT       "CPRS"
 
 void build_cpus_aml(Aml *table, MachineState *machine, CPUHotplugFeatures opts,
                     build_madt_cpu_fn build_madt_cpu, hwaddr base_addr,
@@ -396,7 +423,9 @@ void build_cpus_aml(Aml *table, MachineState *machine, CPUHotplugFeatures opts,
         aml_append(field, aml_named_field(CPU_EJECT_EVENT, 1));
         /* tell firmware to do device eject, write only */
         aml_append(field, aml_named_field(CPU_FW_EJECT_EVENT, 1));
-        aml_append(field, aml_reserved_field(3));
+        /* 1 if present, read only */
+        aml_append(field, aml_named_field(CPU_PRESENT, 1));
+        aml_append(field, aml_reserved_field(2));
         aml_append(field, aml_named_field(CPU_COMMAND, 8));
         aml_append(cpu_ctrl_dev, field);
 
@@ -426,6 +455,7 @@ void build_cpus_aml(Aml *table, MachineState *machine, CPUHotplugFeatures opts,
         Aml *ctrl_lock = aml_name("%s.%s", cphp_res_path, CPU_LOCK);
         Aml *cpu_selector = aml_name("%s.%s", cphp_res_path, CPU_SELECTOR);
         Aml *is_enabled = aml_name("%s.%s", cphp_res_path, CPU_ENABLED);
+        Aml *is_present = aml_name("%s.%s", cphp_res_path, CPU_PRESENT);
         Aml *cpu_cmd = aml_name("%s.%s", cphp_res_path, CPU_COMMAND);
         Aml *cpu_data = aml_name("%s.%s", cphp_res_path, CPU_DATA);
         Aml *ins_evt = aml_name("%s.%s", cphp_res_path, CPU_INSERT_EVENT);
@@ -454,13 +484,26 @@ void build_cpus_aml(Aml *table, MachineState *machine, CPUHotplugFeatures opts,
         {
             Aml *idx = aml_arg(0);
             Aml *sta = aml_local(0);
+            Aml *ifctx2;
+            Aml *else_ctx;
 
             aml_append(method, aml_acquire(ctrl_lock, 0xFFFF));
             aml_append(method, aml_store(idx, cpu_selector));
             aml_append(method, aml_store(zero, sta));
-            ifctx = aml_if(aml_equal(is_enabled, one));
+            ifctx = aml_if(aml_equal(is_present, one));
             {
-                aml_append(ifctx, aml_store(aml_int(0xF), sta));
+                ifctx2 = aml_if(aml_equal(is_enabled, one));
+                {
+                    /* cpu is present and enabled */
+                    aml_append(ifctx2, aml_store(aml_int(0xF), sta));
+                }
+                aml_append(ifctx, ifctx2);
+                else_ctx = aml_else();
+                {
+                    /* cpu is present but disabled */
+                    aml_append(else_ctx, aml_store(aml_int(0xD), sta));
+                }
+                aml_append(ifctx, else_ctx);
             }
             aml_append(method, ifctx);
             aml_append(method, aml_release(ctrl_lock));
diff --git a/hw/acpi/generic_event_device.c b/hw/acpi/generic_event_device.c
index d00f5a6c1c..663d9cb093 100644
--- a/hw/acpi/generic_event_device.c
+++ b/hw/acpi/generic_event_device.c
@@ -331,6 +331,24 @@ static const VMStateDescription vmstate_memhp_state = {
     }
 };
 
+static bool cpuhp_needed(void *opaque)
+{
+    MachineClass *mc = MACHINE_GET_CLASS(qdev_get_machine());
+
+    return mc->has_hotpluggable_cpus;
+}
+
+static const VMStateDescription vmstate_cpuhp_state = {
+    .name = "acpi-ged/cpuhp",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .needed = cpuhp_needed,
+    .fields      = (VMStateField[]) {
+        VMSTATE_CPU_HOTPLUG(cpuhp_state, AcpiGedState),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
 static const VMStateDescription vmstate_ged_state = {
     .name = "acpi-ged-state",
     .version_id = 1,
@@ -379,6 +397,7 @@ static const VMStateDescription vmstate_acpi_ged = {
     },
     .subsections = (const VMStateDescription * const []) {
         &vmstate_memhp_state,
+        &vmstate_cpuhp_state,
         &vmstate_ghes_state,
         NULL
     }
diff --git a/hw/acpi/meson.build b/hw/acpi/meson.build
index 7f8ccc9b7a..c8854f4d48 100644
--- a/hw/acpi/meson.build
+++ b/hw/acpi/meson.build
@@ -1,6 +1,5 @@
 acpi_ss = ss.source_set()
 acpi_ss.add(files(
-  'acpi_generic_initiator.c',
   'acpi_interface.c',
   'aml-build.c',
   'bios-linker-loader.c',
diff --git a/hw/acpi/pci.c b/hw/acpi/pci.c
index 20b70dcd81..f88f450af3 100644
--- a/hw/acpi/pci.c
+++ b/hw/acpi/pci.c
@@ -24,8 +24,14 @@
  */
 
 #include "qemu/osdep.h"
+#include "qemu/error-report.h"
+#include "qom/object_interfaces.h"
+#include "qapi/error.h"
+#include "hw/boards.h"
 #include "hw/acpi/aml-build.h"
 #include "hw/acpi/pci.h"
+#include "hw/pci/pci_bridge.h"
+#include "hw/pci/pci_device.h"
 #include "hw/pci/pcie_host.h"
 
 /*
@@ -59,3 +65,239 @@ void build_mcfg(GArray *table_data, BIOSLinker *linker, AcpiMcfgInfo *info,
 
     acpi_table_end(linker, &table);
 }
+
+typedef struct AcpiGenericInitiator {
+    /* private */
+    Object parent;
+
+    /* public */
+    char *pci_dev;
+    uint32_t node;
+} AcpiGenericInitiator;
+
+typedef struct AcpiGenericInitiatorClass {
+    ObjectClass parent_class;
+} AcpiGenericInitiatorClass;
+
+#define TYPE_ACPI_GENERIC_INITIATOR "acpi-generic-initiator"
+
+OBJECT_DEFINE_TYPE_WITH_INTERFACES(AcpiGenericInitiator, acpi_generic_initiator,
+                   ACPI_GENERIC_INITIATOR, OBJECT,
+                   { TYPE_USER_CREATABLE },
+                   { NULL })
+
+OBJECT_DECLARE_SIMPLE_TYPE(AcpiGenericInitiator, ACPI_GENERIC_INITIATOR)
+
+static void acpi_generic_initiator_init(Object *obj)
+{
+    AcpiGenericInitiator *gi = ACPI_GENERIC_INITIATOR(obj);
+
+    gi->node = MAX_NODES;
+    gi->pci_dev = NULL;
+}
+
+static void acpi_generic_initiator_finalize(Object *obj)
+{
+    AcpiGenericInitiator *gi = ACPI_GENERIC_INITIATOR(obj);
+
+    g_free(gi->pci_dev);
+}
+
+static void acpi_generic_initiator_set_pci_device(Object *obj, const char *val,
+                                                  Error **errp)
+{
+    AcpiGenericInitiator *gi = ACPI_GENERIC_INITIATOR(obj);
+
+    gi->pci_dev = g_strdup(val);
+}
+
+static void acpi_generic_initiator_set_node(Object *obj, Visitor *v,
+                                            const char *name, void *opaque,
+                                            Error **errp)
+{
+    AcpiGenericInitiator *gi = ACPI_GENERIC_INITIATOR(obj);
+    MachineState *ms = MACHINE(qdev_get_machine());
+    uint32_t value;
+
+    if (!visit_type_uint32(v, name, &value, errp)) {
+        return;
+    }
+
+    if (value >= MAX_NODES) {
+        error_printf("%s: Invalid NUMA node specified\n",
+                     TYPE_ACPI_GENERIC_INITIATOR);
+        exit(1);
+    }
+
+    gi->node = value;
+    ms->numa_state->nodes[gi->node].has_gi = true;
+}
+
+static void acpi_generic_initiator_class_init(ObjectClass *oc, void *data)
+{
+    object_class_property_add_str(oc, "pci-dev", NULL,
+        acpi_generic_initiator_set_pci_device);
+    object_class_property_set_description(oc, "pci-dev",
+        "PCI device to associate with the node");
+    object_class_property_add(oc, "node", "int", NULL,
+        acpi_generic_initiator_set_node, NULL, NULL);
+    object_class_property_set_description(oc, "node",
+        "NUMA node associated with the PCI device");
+}
+
+static int build_acpi_generic_initiator(Object *obj, void *opaque)
+{
+    MachineState *ms = MACHINE(qdev_get_machine());
+    AcpiGenericInitiator *gi;
+    GArray *table_data = opaque;
+    int32_t devfn;
+    uint8_t bus;
+    Object *o;
+
+    if (!object_dynamic_cast(obj, TYPE_ACPI_GENERIC_INITIATOR)) {
+        return 0;
+    }
+
+    gi = ACPI_GENERIC_INITIATOR(obj);
+    if (gi->node >= ms->numa_state->num_nodes) {
+        error_printf("%s: Specified node %d is invalid.\n",
+                     TYPE_ACPI_GENERIC_INITIATOR, gi->node);
+        exit(1);
+    }
+
+    o = object_resolve_path_type(gi->pci_dev, TYPE_PCI_DEVICE, NULL);
+    if (!o) {
+        error_printf("%s: Specified device must be a PCI device.\n",
+                     TYPE_ACPI_GENERIC_INITIATOR);
+        exit(1);
+    }
+
+    bus = object_property_get_uint(o, "busnr", &error_fatal);
+    devfn = object_property_get_uint(o, "addr", &error_fatal);
+    /* devfn is constrained in PCI to be 8 bit but storage is an int32_t */
+    assert(devfn >= 0 && devfn < PCI_DEVFN_MAX);
+
+    build_srat_pci_generic_initiator(table_data, gi->node, 0, bus, devfn);
+
+    return 0;
+}
+
+typedef struct AcpiGenericPort {
+    /* private */
+    Object parent;
+
+    /* public */
+    char *pci_bus;
+    uint32_t node;
+} AcpiGenericPort;
+
+typedef struct AcpiGenericPortClass {
+    ObjectClass parent_class;
+} AcpiGenericPortClass;
+
+#define TYPE_ACPI_GENERIC_PORT "acpi-generic-port"
+
+OBJECT_DEFINE_TYPE_WITH_INTERFACES(AcpiGenericPort, acpi_generic_port,
+                   ACPI_GENERIC_PORT, OBJECT,
+                   { TYPE_USER_CREATABLE },
+                   { NULL })
+
+OBJECT_DECLARE_SIMPLE_TYPE(AcpiGenericPort, ACPI_GENERIC_PORT)
+
+static void acpi_generic_port_init(Object *obj)
+{
+    AcpiGenericPort *gp = ACPI_GENERIC_PORT(obj);
+
+    gp->node = MAX_NODES;
+    gp->pci_bus = NULL;
+}
+
+static void acpi_generic_port_finalize(Object *obj)
+{
+    AcpiGenericPort *gp = ACPI_GENERIC_PORT(obj);
+
+    g_free(gp->pci_bus);
+}
+
+static void acpi_generic_port_set_pci_bus(Object *obj, const char *val,
+                                          Error **errp)
+{
+    AcpiGenericPort *gp = ACPI_GENERIC_PORT(obj);
+
+    gp->pci_bus = g_strdup(val);
+}
+
+static void acpi_generic_port_set_node(Object *obj, Visitor *v,
+                                       const char *name, void *opaque,
+                                       Error **errp)
+{
+    AcpiGenericPort *gp = ACPI_GENERIC_PORT(obj);
+    uint32_t value;
+
+    if (!visit_type_uint32(v, name, &value, errp)) {
+        return;
+    }
+
+    if (value >= MAX_NODES) {
+        error_printf("%s: Invalid NUMA node specified\n",
+                     TYPE_ACPI_GENERIC_INITIATOR);
+        exit(1);
+    }
+
+    gp->node = value;
+}
+
+static void acpi_generic_port_class_init(ObjectClass *oc, void *data)
+{
+    object_class_property_add_str(oc, "pci-bus", NULL,
+        acpi_generic_port_set_pci_bus);
+    object_class_property_set_description(oc, "pci-bus",
+       "PCI Bus of the host bridge associated with this GP affinity structure");
+    object_class_property_add(oc, "node", "int", NULL,
+        acpi_generic_port_set_node, NULL, NULL);
+    object_class_property_set_description(oc, "node",
+       "The NUMA node like ID to index HMAT/SLIT NUMA properties involving GP");
+}
+
+static int build_acpi_generic_port(Object *obj, void *opaque)
+{
+    MachineState *ms = MACHINE(qdev_get_machine());
+    const char *hid = "ACPI0016";
+    GArray *table_data = opaque;
+    AcpiGenericPort *gp;
+    uint32_t uid;
+    Object *o;
+
+    if (!object_dynamic_cast(obj, TYPE_ACPI_GENERIC_PORT)) {
+        return 0;
+    }
+
+    gp = ACPI_GENERIC_PORT(obj);
+
+    if (gp->node >= ms->numa_state->num_nodes) {
+        error_printf("%s: node %d is invalid.\n",
+                     TYPE_ACPI_GENERIC_PORT, gp->node);
+        exit(1);
+    }
+
+    o = object_resolve_path_type(gp->pci_bus, TYPE_PXB_CXL_BUS, NULL);
+    if (!o) {
+        error_printf("%s: device must be a CXL host bridge.\n",
+                     TYPE_ACPI_GENERIC_PORT);
+       exit(1);
+    }
+
+    uid = object_property_get_uint(o, "acpi_uid", &error_fatal);
+    build_srat_acpi_generic_port(table_data, gp->node, hid, uid);
+
+    return 0;
+}
+
+void build_srat_generic_affinity_structures(GArray *table_data)
+{
+    object_child_foreach_recursive(object_get_root(),
+                                   build_acpi_generic_initiator,
+                                   table_data);
+    object_child_foreach_recursive(object_get_root(), build_acpi_generic_port,
+                                   table_data);
+}
diff --git a/hw/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c
index f76fb117ad..620992c92c 100644
--- a/hw/arm/virt-acpi-build.c
+++ b/hw/arm/virt-acpi-build.c
@@ -57,7 +57,6 @@
 #include "migration/vmstate.h"
 #include "hw/acpi/ghes.h"
 #include "hw/acpi/viot.h"
-#include "hw/acpi/acpi_generic_initiator.h"
 #include "hw/virtio/virtio-acpi.h"
 #include "target/arm/multiprocessing.h"
 
@@ -511,7 +510,7 @@ build_srat(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms)
         }
     }
 
-    build_srat_generic_pci_initiator(table_data);
+    build_srat_generic_affinity_structures(table_data);
 
     if (ms->nvdimms_state->is_enabled) {
         nvdimm_build_srat(table_data);
diff --git a/hw/block/vhost-user-blk.c b/hw/block/vhost-user-blk.c
index 5b7f46bbb0..7996e49821 100644
--- a/hw/block/vhost-user-blk.c
+++ b/hw/block/vhost-user-blk.c
@@ -90,27 +90,39 @@ static void vhost_user_blk_set_config(VirtIODevice *vdev, const uint8_t *config)
     s->blkcfg.wce = blkcfg->wce;
 }
 
+static int vhost_user_blk_sync_config(DeviceState *dev, Error **errp)
+{
+    int ret;
+    VirtIODevice *vdev = VIRTIO_DEVICE(dev);
+    VHostUserBlk *s = VHOST_USER_BLK(vdev);
+
+    ret = vhost_dev_get_config(&s->dev, (uint8_t *)&s->blkcfg,
+                               vdev->config_len, errp);
+    if (ret < 0) {
+        return ret;
+    }
+
+    memcpy(vdev->config, &s->blkcfg, vdev->config_len);
+    virtio_notify_config(vdev);
+
+    return 0;
+}
+
 static int vhost_user_blk_handle_config_change(struct vhost_dev *dev)
 {
     int ret;
-    VirtIODevice *vdev = dev->vdev;
-    VHostUserBlk *s = VHOST_USER_BLK(dev->vdev);
     Error *local_err = NULL;
 
     if (!dev->started) {
         return 0;
     }
 
-    ret = vhost_dev_get_config(dev, (uint8_t *)&s->blkcfg,
-                               vdev->config_len, &local_err);
+    ret = vhost_user_blk_sync_config(DEVICE(dev->vdev), &local_err);
     if (ret < 0) {
         error_report_err(local_err);
         return ret;
     }
 
-    memcpy(dev->vdev->config, &s->blkcfg, vdev->config_len);
-    virtio_notify_config(dev->vdev);
-
     return 0;
 }
 
@@ -579,6 +591,7 @@ static void vhost_user_blk_class_init(ObjectClass *klass, void *data)
 
     device_class_set_props(dc, vhost_user_blk_properties);
     dc->vmsd = &vmstate_vhost_user_blk;
+    dc->sync_config = vhost_user_blk_sync_config;
     set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
     vdc->realize = vhost_user_blk_device_realize;
     vdc->unrealize = vhost_user_blk_device_unrealize;
diff --git a/hw/core/machine.c b/hw/core/machine.c
index e6c92faf73..a35c4a8fae 100644
--- a/hw/core/machine.c
+++ b/hw/core/machine.c
@@ -36,7 +36,9 @@
 #include "hw/virtio/virtio-iommu.h"
 #include "audio/audio.h"
 
-GlobalProperty hw_compat_9_1[] = {};
+GlobalProperty hw_compat_9_1[] = {
+    { TYPE_PCI_DEVICE, "x-pcie-ext-tag", "false" },
+};
 const size_t hw_compat_9_1_len = G_N_ELEMENTS(hw_compat_9_1);
 
 GlobalProperty hw_compat_9_0[] = {
diff --git a/hw/cxl/cxl-mailbox-utils.c b/hw/cxl/cxl-mailbox-utils.c
index 9258e48f95..2d4d62c454 100644
--- a/hw/cxl/cxl-mailbox-utils.c
+++ b/hw/cxl/cxl-mailbox-utils.c
@@ -151,6 +151,9 @@ static CXLRetCode cmd_tunnel_management_cmd(const struct cxl_cmd *cmd,
     in = (void *)payload_in;
     out = (void *)payload_out;
 
+    if (len_in < sizeof(*in)) {
+        return CXL_MBOX_INVALID_PAYLOAD_LENGTH;
+    }
     /* Enough room for minimum sized message - no payload */
     if (in->size < sizeof(in->ccimessage)) {
         return CXL_MBOX_INVALID_PAYLOAD_LENGTH;
@@ -266,6 +269,12 @@ static CXLRetCode cmd_events_clear_records(const struct cxl_cmd *cmd,
     CXLClearEventPayload *pl;
 
     pl = (CXLClearEventPayload *)payload_in;
+
+    if (len_in < sizeof(*pl) ||
+        len_in < sizeof(*pl) + sizeof(*pl->handle) * pl->nr_recs) {
+        return CXL_MBOX_INVALID_PAYLOAD_LENGTH;
+    }
+
     *len_out = 0;
     return cxl_event_clear_records(cxlds, pl);
 }
@@ -374,7 +383,7 @@ static CXLRetCode cmd_infostat_identify(const struct cxl_cmd *cmd,
         uint16_t pcie_subsys_vid;
         uint16_t pcie_subsys_id;
         uint64_t sn;
-    uint8_t max_message_size;
+        uint8_t max_message_size;
         uint8_t component_type;
     } QEMU_PACKED *is_identify;
     QEMU_BUILD_BUG_ON(sizeof(*is_identify) != 18);
@@ -521,6 +530,9 @@ static CXLRetCode cmd_get_physical_port_state(const struct cxl_cmd *cmd,
     in = (struct cxl_fmapi_get_phys_port_state_req_pl *)payload_in;
     out = (struct cxl_fmapi_get_phys_port_state_resp_pl *)payload_out;
 
+    if (len_in < sizeof(*in)) {
+        return CXL_MBOX_INVALID_PAYLOAD_LENGTH;
+    }
     /* Check if what was requested can fit */
     if (sizeof(*out) + sizeof(*out->ports) * in->num_ports > cci->payload_max) {
         return CXL_MBOX_INVALID_INPUT;
@@ -649,9 +661,9 @@ static CXLRetCode cmd_firmware_update_get_info(const struct cxl_cmd *cmd,
     } QEMU_PACKED *fw_info;
     QEMU_BUILD_BUG_ON(sizeof(*fw_info) != 0x50);
 
-    if ((cxl_dstate->vmem_size < CXL_CAPACITY_MULTIPLIER) ||
-        (cxl_dstate->pmem_size < CXL_CAPACITY_MULTIPLIER) ||
-        (ct3d->dc.total_capacity < CXL_CAPACITY_MULTIPLIER)) {
+    if (!QEMU_IS_ALIGNED(cxl_dstate->vmem_size, CXL_CAPACITY_MULTIPLIER) ||
+        !QEMU_IS_ALIGNED(cxl_dstate->pmem_size, CXL_CAPACITY_MULTIPLIER) ||
+        !QEMU_IS_ALIGNED(ct3d->dc.total_capacity, CXL_CAPACITY_MULTIPLIER)) {
         return CXL_MBOX_INTERNAL_ERROR;
     }
 
@@ -699,6 +711,10 @@ static CXLRetCode cmd_firmware_update_transfer(const struct cxl_cmd *cmd,
     } QEMU_PACKED *fw_transfer = (void *)payload_in;
     size_t offset, length;
 
+    if (len < sizeof(*fw_transfer)) {
+        return CXL_MBOX_INVALID_PAYLOAD_LENGTH;
+    }
+
     if (fw_transfer->action == CXL_FW_XFER_ACTION_ABORT) {
         /*
          * At this point there aren't any on-going transfers
@@ -927,24 +943,28 @@ static CXLRetCode cmd_logs_get_log(const struct cxl_cmd *cmd,
 
     get_log = (void *)payload_in;
 
+    if (get_log->length > cci->payload_max) {
+        return CXL_MBOX_INVALID_INPUT;
+    }
+
+    if (!qemu_uuid_is_equal(&get_log->uuid, &cel_uuid)) {
+        return CXL_MBOX_INVALID_LOG;
+    }
+
     /*
      * CXL r3.1 Section 8.2.9.5.2: Get Log (Opcode 0401h)
      *   The device shall return Invalid Input if the Offset or Length
      *   fields attempt to access beyond the size of the log as reported by Get
-     *   Supported Logs.
+     *   Supported Log.
      *
-     * The CEL buffer is large enough to fit all commands in the emulation, so
-     * the only possible failure would be if the mailbox itself isn't big
-     * enough.
+     * Only valid for there to be one entry per opcode, but the length + offset
+     * may still be greater than that if the inputs are not valid and so access
+     * beyond the end of cci->cel_log.
      */
-    if (get_log->offset + get_log->length > cci->payload_max) {
+    if ((uint64_t)get_log->offset + get_log->length >= sizeof(cci->cel_log)) {
         return CXL_MBOX_INVALID_INPUT;
     }
 
-    if (!qemu_uuid_is_equal(&get_log->uuid, &cel_uuid)) {
-        return CXL_MBOX_INVALID_LOG;
-    }
-
     /* Store off everything to local variables so we can wipe out the payload */
     *len_out = get_log->length;
 
@@ -1133,10 +1153,8 @@ static CXLRetCode cmd_features_get_supported(const struct cxl_cmd *cmd,
                          (struct CXLSupportedFeatureEntry) {
                 .uuid = ecs_uuid,
                 .feat_index = index,
-                .get_feat_size = CXL_ECS_NUM_MEDIA_FRUS *
-                                    sizeof(CXLMemECSReadAttrs),
-                .set_feat_size = CXL_ECS_NUM_MEDIA_FRUS *
-                                    sizeof(CXLMemECSWriteAttrs),
+                .get_feat_size = sizeof(CXLMemECSReadAttrs),
+                .set_feat_size = sizeof(CXLMemECSWriteAttrs),
                 .attr_flags = CXL_FEAT_ENTRY_ATTR_FLAG_CHANGABLE,
                 .get_feat_version = CXL_ECS_GET_FEATURE_VERSION,
                 .set_feat_version = CXL_ECS_SET_FEATURE_VERSION,
@@ -1204,13 +1222,10 @@ static CXLRetCode cmd_features_get_feature(const struct cxl_cmd *cmd,
                (uint8_t *)&ct3d->patrol_scrub_attrs + get_feature->offset,
                bytes_to_copy);
     } else if (qemu_uuid_is_equal(&get_feature->uuid, &ecs_uuid)) {
-        if (get_feature->offset >=  CXL_ECS_NUM_MEDIA_FRUS *
-                                sizeof(CXLMemECSReadAttrs)) {
+        if (get_feature->offset >= sizeof(CXLMemECSReadAttrs)) {
             return CXL_MBOX_INVALID_INPUT;
         }
-        bytes_to_copy = CXL_ECS_NUM_MEDIA_FRUS *
-                        sizeof(CXLMemECSReadAttrs) -
-                            get_feature->offset;
+        bytes_to_copy = sizeof(CXLMemECSReadAttrs) - get_feature->offset;
         bytes_to_copy = MIN(bytes_to_copy, get_feature->count);
         memcpy(payload_out,
                (uint8_t *)&ct3d->ecs_attrs + get_feature->offset,
@@ -1243,6 +1258,9 @@ static CXLRetCode cmd_features_set_feature(const struct cxl_cmd *cmd,
     CXLType3Dev *ct3d;
     uint16_t count;
 
+    if (len_in < sizeof(*hdr)) {
+        return CXL_MBOX_INVALID_PAYLOAD_LENGTH;
+    }
 
     if (!object_dynamic_cast(OBJECT(cci->d), TYPE_CXL_TYPE3)) {
         return CXL_MBOX_UNSUPPORTED;
@@ -1277,6 +1295,11 @@ static CXLRetCode cmd_features_set_feature(const struct cxl_cmd *cmd,
 
         ps_set_feature = (void *)payload_in;
         ps_write_attrs = &ps_set_feature->feat_data;
+
+        if ((uint32_t)hdr->offset + bytes_to_copy >
+            sizeof(ct3d->patrol_scrub_wr_attrs)) {
+            return CXL_MBOX_INVALID_PAYLOAD_LENGTH;
+        }
         memcpy((uint8_t *)&ct3d->patrol_scrub_wr_attrs + hdr->offset,
                ps_write_attrs,
                bytes_to_copy);
@@ -1299,18 +1322,22 @@ static CXLRetCode cmd_features_set_feature(const struct cxl_cmd *cmd,
 
         ecs_set_feature = (void *)payload_in;
         ecs_write_attrs = ecs_set_feature->feat_data;
-        memcpy((uint8_t *)ct3d->ecs_wr_attrs + hdr->offset,
+
+        if ((uint32_t)hdr->offset + bytes_to_copy >
+            sizeof(ct3d->ecs_wr_attrs)) {
+            return CXL_MBOX_INVALID_PAYLOAD_LENGTH;
+        }
+        memcpy((uint8_t *)&ct3d->ecs_wr_attrs + hdr->offset,
                ecs_write_attrs,
                bytes_to_copy);
         set_feat_info->data_size += bytes_to_copy;
 
         if (data_transfer_flag == CXL_SET_FEATURE_FLAG_FULL_DATA_TRANSFER ||
             data_transfer_flag ==  CXL_SET_FEATURE_FLAG_FINISH_DATA_TRANSFER) {
+            ct3d->ecs_attrs.ecs_log_cap = ct3d->ecs_wr_attrs.ecs_log_cap;
             for (count = 0; count < CXL_ECS_NUM_MEDIA_FRUS; count++) {
-                ct3d->ecs_attrs[count].ecs_log_cap =
-                                  ct3d->ecs_wr_attrs[count].ecs_log_cap;
-                ct3d->ecs_attrs[count].ecs_config =
-                                  ct3d->ecs_wr_attrs[count].ecs_config & 0x1F;
+                ct3d->ecs_attrs.fru_attrs[count].ecs_config =
+                        ct3d->ecs_wr_attrs.fru_attrs[count].ecs_config & 0x1F;
             }
         }
     } else {
@@ -1324,7 +1351,7 @@ static CXLRetCode cmd_features_set_feature(const struct cxl_cmd *cmd,
         if (qemu_uuid_is_equal(&hdr->uuid, &patrol_scrub_uuid)) {
             memset(&ct3d->patrol_scrub_wr_attrs, 0, set_feat_info->data_size);
         } else if (qemu_uuid_is_equal(&hdr->uuid, &ecs_uuid)) {
-            memset(ct3d->ecs_wr_attrs, 0, set_feat_info->data_size);
+            memset(&ct3d->ecs_wr_attrs, 0, set_feat_info->data_size);
         }
         set_feat_info->data_transfer_flag = 0;
         set_feat_info->data_saved_across_reset = false;
@@ -1445,7 +1472,7 @@ static CXLRetCode cmd_ccls_get_lsa(const struct cxl_cmd *cmd,
     } QEMU_PACKED *get_lsa;
     CXLType3Dev *ct3d = CXL_TYPE3(cci->d);
     CXLType3Class *cvc = CXL_TYPE3_GET_CLASS(ct3d);
-    uint32_t offset, length;
+    uint64_t offset, length;
 
     get_lsa = (void *)payload_in;
     offset = get_lsa->offset;
@@ -1479,8 +1506,8 @@ static CXLRetCode cmd_ccls_set_lsa(const struct cxl_cmd *cmd,
     const size_t hdr_len = offsetof(struct set_lsa_pl, data);
 
     *len_out = 0;
-    if (!len_in) {
-        return CXL_MBOX_SUCCESS;
+    if (len_in < hdr_len) {
+        return CXL_MBOX_INVALID_PAYLOAD_LENGTH;
     }
 
     if (set_lsa_payload->offset + len_in > cvc->get_lsa_size(ct3d) + hdr_len) {
@@ -2233,6 +2260,7 @@ static CXLRetCode cmd_dcd_get_dyn_cap_ext_list(const struct cxl_cmd *cmd,
             stw_le_p(&out_rec->shared_seq, ent->shared_seq);
 
             record_done++;
+            out_rec++;
             if (record_done == record_count) {
                 break;
             }
@@ -2470,11 +2498,20 @@ static CXLRetCode cmd_dcd_add_dyn_cap_rsp(const struct cxl_cmd *cmd,
     uint64_t dpa, len;
     CXLRetCode ret;
 
+    if (len_in < sizeof(*in)) {
+        return CXL_MBOX_INVALID_PAYLOAD_LENGTH;
+    }
+
     if (in->num_entries_updated == 0) {
         cxl_extent_group_list_delete_front(&ct3d->dc.extents_pending);
         return CXL_MBOX_SUCCESS;
     }
 
+    if (len_in <
+        sizeof(*in) + sizeof(*in->updated_entries) * in->num_entries_updated) {
+        return CXL_MBOX_INVALID_PAYLOAD_LENGTH;
+    }
+
     /* Adding extents causes exceeding device's extent tracking ability. */
     if (in->num_entries_updated + ct3d->dc.total_extent_count >
         CXL_NUM_EXTENTS_SUPPORTED) {
@@ -2629,10 +2666,19 @@ static CXLRetCode cmd_dcd_release_dyn_cap(const struct cxl_cmd *cmd,
     uint32_t updated_list_size;
     CXLRetCode ret;
 
+    if (len_in < sizeof(*in)) {
+        return CXL_MBOX_INVALID_PAYLOAD_LENGTH;
+    }
+
     if (in->num_entries_updated == 0) {
         return CXL_MBOX_INVALID_INPUT;
     }
 
+    if (len_in <
+        sizeof(*in) + sizeof(*in->updated_entries) * in->num_entries_updated) {
+        return CXL_MBOX_INVALID_PAYLOAD_LENGTH;
+    }
+
     ret = cxl_detect_malformed_extent_list(ct3d, in);
     if (ret != CXL_MBOX_SUCCESS) {
         return ret;
@@ -2879,7 +2925,8 @@ static void bg_timercb(void *opaque)
         }
     } else {
         /* estimate only */
-        cci->bg.complete_pct = 100 * now / total_time;
+        cci->bg.complete_pct =
+            100 * (now - cci->bg.starttime) / cci->bg.runtime;
         timer_mod(cci->bg.timer, now + CXL_MBOX_BG_UPDATE_FREQ);
     }
 
diff --git a/hw/i386/acpi-build.c b/hw/i386/acpi-build.c
index 4967aa7459..9fcc2897b8 100644
--- a/hw/i386/acpi-build.c
+++ b/hw/i386/acpi-build.c
@@ -68,7 +68,6 @@
 #include "hw/acpi/utils.h"
 #include "hw/acpi/pci.h"
 #include "hw/acpi/cxl.h"
-#include "hw/acpi/acpi_generic_initiator.h"
 
 #include "qom/qom-qobject.h"
 #include "hw/i386/amd_iommu.h"
@@ -741,7 +740,8 @@ static Aml *build_prt(bool is_pci0_prt)
     int pin;
 
     method = aml_method("_PRT", 0, AML_NOTSERIALIZED);
-    rt_pkg = aml_varpackage(nroutes);
+    assert(nroutes < 256);
+    rt_pkg = aml_package(nroutes);
 
     for (pin = 0; pin < nroutes; pin++) {
         Aml *pkg = aml_package(4);
@@ -1476,6 +1476,7 @@ build_dsdt(GArray *table_data, BIOSLinker *linker,
         QLIST_FOREACH(bus, &bus->child, sibling) {
             uint8_t bus_num = pci_bus_num(bus);
             uint8_t numa_node = pci_bus_numa_node(bus);
+            uint32_t uid;
 
             /* look only for expander root buses */
             if (!pci_bus_is_root(bus)) {
@@ -1486,6 +1487,8 @@ build_dsdt(GArray *table_data, BIOSLinker *linker,
                 root_bus_limit = bus_num - 1;
             }
 
+            uid = object_property_get_uint(OBJECT(bus), "acpi_uid",
+                                           &error_fatal);
             scope = aml_scope("\\_SB");
 
             if (pci_bus_is_cxl(bus)) {
@@ -1493,7 +1496,7 @@ build_dsdt(GArray *table_data, BIOSLinker *linker,
             } else {
                 dev = aml_device("PC%.02X", bus_num);
             }
-            aml_append(dev, aml_name_decl("_UID", aml_int(bus_num)));
+            aml_append(dev, aml_name_decl("_UID", aml_int(uid)));
             aml_append(dev, aml_name_decl("_BBN", aml_int(bus_num)));
             if (pci_bus_is_cxl(bus)) {
                 struct Aml *aml_pkg = aml_package(2);
@@ -1971,7 +1974,7 @@ build_srat(GArray *table_data, BIOSLinker *linker, MachineState *machine)
         build_srat_memory(table_data, 0, 0, 0, MEM_AFFINITY_NOFLAGS);
     }
 
-    build_srat_generic_pci_initiator(table_data);
+    build_srat_generic_affinity_structures(table_data);
 
     /*
      * Entry is required for Windows to enable memory hotplug in OS
@@ -2321,7 +2324,7 @@ build_amd_iommu(GArray *table_data, BIOSLinker *linker, const char *oem_id,
     /* Capability offset */
     build_append_int_noprefix(table_data, s->pci.capab_offset, 2);
     /* IOMMU base address */
-    build_append_int_noprefix(table_data, s->mmio.addr, 8);
+    build_append_int_noprefix(table_data, s->mr_mmio.addr, 8);
     /* PCI Segment Group */
     build_append_int_noprefix(table_data, 0, 2);
     /* IOMMU info */
@@ -2356,7 +2359,7 @@ build_amd_iommu(GArray *table_data, BIOSLinker *linker, const char *oem_id,
     /* Capability offset */
     build_append_int_noprefix(table_data, s->pci.capab_offset, 2);
     /* IOMMU base address */
-    build_append_int_noprefix(table_data, s->mmio.addr, 8);
+    build_append_int_noprefix(table_data, s->mr_mmio.addr, 8);
     /* PCI Segment Group */
     build_append_int_noprefix(table_data, 0, 2);
     /* IOMMU info */
diff --git a/hw/i386/amd_iommu.c b/hw/i386/amd_iommu.c
index 464f0b666e..13af7211e1 100644
--- a/hw/i386/amd_iommu.c
+++ b/hw/i386/amd_iommu.c
@@ -32,6 +32,7 @@
 #include "trace.h"
 #include "hw/i386/apic-msidef.h"
 #include "hw/qdev-properties.h"
+#include "kvm/kvm_i386.h"
 
 /* used AMD-Vi MMIO registers */
 const char *amdvi_mmio_low[] = {
@@ -60,8 +61,9 @@ struct AMDVIAddressSpace {
     uint8_t bus_num;            /* bus number                           */
     uint8_t devfn;              /* device function                      */
     AMDVIState *iommu_state;    /* AMDVI - one per machine              */
-    MemoryRegion root;          /* AMDVI Root memory map region */
+    MemoryRegion root;          /* AMDVI Root memory map region         */
     IOMMUMemoryRegion iommu;    /* Device's address translation region  */
+    MemoryRegion iommu_nodma;   /* Alias of shared nodma memory region  */
     MemoryRegion iommu_ir;      /* Device's interrupt remapping region  */
     AddressSpace as;            /* device's corresponding address space */
 };
@@ -430,6 +432,12 @@ static void amdvi_complete_ppr(AMDVIState *s, uint64_t *cmd)
     trace_amdvi_ppr_exec();
 }
 
+static void amdvi_intremap_inval_notify_all(AMDVIState *s, bool global,
+                               uint32_t index, uint32_t mask)
+{
+    x86_iommu_iec_notify_all(X86_IOMMU_DEVICE(s), global, index, mask);
+}
+
 static void amdvi_inval_all(AMDVIState *s, uint64_t *cmd)
 {
     if (extract64(cmd[0], 0, 60) || cmd[1]) {
@@ -437,6 +445,9 @@ static void amdvi_inval_all(AMDVIState *s, uint64_t *cmd)
                                    s->cmdbuf + s->cmdbuf_head);
     }
 
+    /* Notify global invalidation */
+    amdvi_intremap_inval_notify_all(s, true, 0, 0);
+
     amdvi_iotlb_reset(s);
     trace_amdvi_all_inval();
 }
@@ -485,6 +496,9 @@ static void amdvi_inval_inttable(AMDVIState *s, uint64_t *cmd)
         return;
     }
 
+    /* Notify global invalidation */
+    amdvi_intremap_inval_notify_all(s, true, 0, 0);
+
     trace_amdvi_intr_inval();
 }
 
@@ -1412,6 +1426,7 @@ static AddressSpace *amdvi_host_dma_iommu(PCIBus *bus, void *opaque, int devfn)
     AMDVIState *s = opaque;
     AMDVIAddressSpace **iommu_as, *amdvi_dev_as;
     int bus_num = pci_bus_num(bus);
+    X86IOMMUState *x86_iommu = X86_IOMMU_DEVICE(s);
 
     iommu_as = s->address_spaces[bus_num];
 
@@ -1436,13 +1451,13 @@ static AddressSpace *amdvi_host_dma_iommu(PCIBus *bus, void *opaque, int devfn)
          * Memory region relationships looks like (Address range shows
          * only lower 32 bits to make it short in length...):
          *
-         * |-----------------+-------------------+----------|
-         * | Name            | Address range     | Priority |
-         * |-----------------+-------------------+----------+
-         * | amdvi_root      | 00000000-ffffffff |        0 |
-         * |  amdvi_iommu    | 00000000-ffffffff |        1 |
-         * |  amdvi_iommu_ir | fee00000-feefffff |       64 |
-         * |-----------------+-------------------+----------|
+         * |--------------------+-------------------+----------|
+         * | Name               | Address range     | Priority |
+         * |--------------------+-------------------+----------+
+         * | amdvi-root         | 00000000-ffffffff |        0 |
+         * |  amdvi-iommu_nodma  | 00000000-ffffffff |       0 |
+         * |  amdvi-iommu_ir     | fee00000-feefffff |       1 |
+         * |--------------------+-------------------+----------|
          */
         memory_region_init_iommu(&amdvi_dev_as->iommu,
                                  sizeof(amdvi_dev_as->iommu),
@@ -1452,16 +1467,34 @@ static AddressSpace *amdvi_host_dma_iommu(PCIBus *bus, void *opaque, int devfn)
         memory_region_init(&amdvi_dev_as->root, OBJECT(s),
                            "amdvi_root", UINT64_MAX);
         address_space_init(&amdvi_dev_as->as, &amdvi_dev_as->root, name);
-        memory_region_init_io(&amdvi_dev_as->iommu_ir, OBJECT(s),
-                              &amdvi_ir_ops, s, "amd_iommu_ir",
-                              AMDVI_INT_ADDR_SIZE);
-        memory_region_add_subregion_overlap(&amdvi_dev_as->root,
-                                            AMDVI_INT_ADDR_FIRST,
-                                            &amdvi_dev_as->iommu_ir,
-                                            64);
         memory_region_add_subregion_overlap(&amdvi_dev_as->root, 0,
                                             MEMORY_REGION(&amdvi_dev_as->iommu),
-                                            1);
+                                            0);
+
+        /* Build the DMA Disabled alias to shared memory */
+        memory_region_init_alias(&amdvi_dev_as->iommu_nodma, OBJECT(s),
+                                 "amdvi-sys", &s->mr_sys, 0,
+                                 memory_region_size(&s->mr_sys));
+        memory_region_add_subregion_overlap(&amdvi_dev_as->root, 0,
+                                            &amdvi_dev_as->iommu_nodma,
+                                            0);
+        /* Build the Interrupt Remapping alias to shared memory */
+        memory_region_init_alias(&amdvi_dev_as->iommu_ir, OBJECT(s),
+                                 "amdvi-ir", &s->mr_ir, 0,
+                                 memory_region_size(&s->mr_ir));
+        memory_region_add_subregion_overlap(MEMORY_REGION(&amdvi_dev_as->iommu),
+                                            AMDVI_INT_ADDR_FIRST,
+                                            &amdvi_dev_as->iommu_ir, 1);
+
+        if (!x86_iommu->pt_supported) {
+            memory_region_set_enabled(&amdvi_dev_as->iommu_nodma, false);
+            memory_region_set_enabled(MEMORY_REGION(&amdvi_dev_as->iommu),
+                                      true);
+        } else {
+            memory_region_set_enabled(MEMORY_REGION(&amdvi_dev_as->iommu),
+                                      false);
+            memory_region_set_enabled(&amdvi_dev_as->iommu_nodma, true);
+        }
     }
     return &iommu_as[devfn]->as;
 }
@@ -1598,10 +1631,37 @@ static void amdvi_sysbus_realize(DeviceState *dev, Error **errp)
     x86ms->ioapic_as = amdvi_host_dma_iommu(bus, s, AMDVI_IOAPIC_SB_DEVID);
 
     /* set up MMIO */
-    memory_region_init_io(&s->mmio, OBJECT(s), &mmio_mem_ops, s, "amdvi-mmio",
-                          AMDVI_MMIO_SIZE);
+    memory_region_init_io(&s->mr_mmio, OBJECT(s), &mmio_mem_ops, s,
+                          "amdvi-mmio", AMDVI_MMIO_SIZE);
     memory_region_add_subregion(get_system_memory(), AMDVI_BASE_ADDR,
-                                &s->mmio);
+                                &s->mr_mmio);
+
+    /* Create the share memory regions by all devices */
+    memory_region_init(&s->mr_sys, OBJECT(s), "amdvi-sys", UINT64_MAX);
+
+    /* set up the DMA disabled memory region */
+    memory_region_init_alias(&s->mr_nodma, OBJECT(s),
+                             "amdvi-nodma", get_system_memory(), 0,
+                             memory_region_size(get_system_memory()));
+    memory_region_add_subregion_overlap(&s->mr_sys, 0,
+                                        &s->mr_nodma, 0);
+
+    /* set up the Interrupt Remapping memory region */
+    memory_region_init_io(&s->mr_ir, OBJECT(s), &amdvi_ir_ops,
+                          s, "amdvi-ir", AMDVI_INT_ADDR_SIZE);
+    memory_region_add_subregion_overlap(&s->mr_sys, AMDVI_INT_ADDR_FIRST,
+                                        &s->mr_ir, 1);
+
+    /* AMD IOMMU with x2APIC mode requires xtsup=on */
+    if (x86ms->apic_id_limit > 255 && !s->xtsup) {
+        error_report("AMD IOMMU with x2APIC confguration requires xtsup=on");
+        exit(EXIT_FAILURE);
+    }
+    if (s->xtsup && kvm_irqchip_is_split() && !kvm_enable_x2apic()) {
+        error_report("AMD IOMMU xtsup=on requires support on the KVM side");
+        exit(EXIT_FAILURE);
+    }
+
     pci_setup_iommu(bus, &amdvi_iommu_ops, s);
     amdvi_init(s);
 }
diff --git a/hw/i386/amd_iommu.h b/hw/i386/amd_iommu.h
index 73619fe9ea..e0dac4d9a9 100644
--- a/hw/i386/amd_iommu.h
+++ b/hw/i386/amd_iommu.h
@@ -353,7 +353,10 @@ struct AMDVIState {
     uint32_t pprlog_head;        /* ppr log head */
     uint32_t pprlog_tail;        /* ppr log tail */
 
-    MemoryRegion mmio;                 /* MMIO region                  */
+    MemoryRegion mr_mmio;              /* MMIO region                  */
+    MemoryRegion mr_sys;
+    MemoryRegion mr_nodma;
+    MemoryRegion mr_ir;
     uint8_t mmior[AMDVI_MMIO_SIZE];    /* read/write MMIO              */
     uint8_t w1cmask[AMDVI_MMIO_SIZE];  /* read/write 1 clear mask      */
     uint8_t romask[AMDVI_MMIO_SIZE];   /* MMIO read/only mask          */
diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c
index 08fe218935..4c0d1d7d47 100644
--- a/hw/i386/intel_iommu.c
+++ b/hw/i386/intel_iommu.c
@@ -2532,15 +2532,51 @@ static bool vtd_get_inv_desc(IntelIOMMUState *s,
     return true;
 }
 
+static bool vtd_inv_desc_reserved_check(IntelIOMMUState *s,
+                                        VTDInvDesc *inv_desc,
+                                        uint64_t mask[4], bool dw,
+                                        const char *func_name,
+                                        const char *desc_type)
+{
+    if (s->iq_dw) {
+        if (inv_desc->val[0] & mask[0] || inv_desc->val[1] & mask[1] ||
+            inv_desc->val[2] & mask[2] || inv_desc->val[3] & mask[3]) {
+            error_report("%s: invalid %s desc val[3]: 0x%"PRIx64
+                         " val[2]: 0x%"PRIx64" val[1]=0x%"PRIx64
+                         " val[0]=0x%"PRIx64" (reserved nonzero)",
+                         func_name, desc_type, inv_desc->val[3],
+                         inv_desc->val[2], inv_desc->val[1],
+                         inv_desc->val[0]);
+            return false;
+        }
+    } else {
+        if (dw) {
+            error_report("%s: 256-bit %s desc in 128-bit invalidation queue",
+                         func_name, desc_type);
+            return false;
+        }
+
+        if (inv_desc->lo & mask[0] || inv_desc->hi & mask[1]) {
+            error_report("%s: invalid %s desc: hi=%"PRIx64", lo=%"PRIx64
+                         " (reserved nonzero)", func_name, desc_type,
+                         inv_desc->hi, inv_desc->lo);
+            return false;
+        }
+    }
+
+    return true;
+}
+
 static bool vtd_process_wait_desc(IntelIOMMUState *s, VTDInvDesc *inv_desc)
 {
-    if ((inv_desc->hi & VTD_INV_DESC_WAIT_RSVD_HI) ||
-        (inv_desc->lo & VTD_INV_DESC_WAIT_RSVD_LO)) {
-        error_report_once("%s: invalid wait desc: hi=%"PRIx64", lo=%"PRIx64
-                          " (reserved nonzero)", __func__, inv_desc->hi,
-                          inv_desc->lo);
+    uint64_t mask[4] = {VTD_INV_DESC_WAIT_RSVD_LO, VTD_INV_DESC_WAIT_RSVD_HI,
+                        VTD_INV_DESC_ALL_ONE, VTD_INV_DESC_ALL_ONE};
+
+    if (!vtd_inv_desc_reserved_check(s, inv_desc, mask, false,
+                                     __func__, "wait")) {
         return false;
     }
+
     if (inv_desc->lo & VTD_INV_DESC_WAIT_SW) {
         /* Status Write */
         uint32_t status_data = (uint32_t)(inv_desc->lo >>
@@ -2574,13 +2610,14 @@ static bool vtd_process_context_cache_desc(IntelIOMMUState *s,
                                            VTDInvDesc *inv_desc)
 {
     uint16_t sid, fmask;
+    uint64_t mask[4] = {VTD_INV_DESC_CC_RSVD, VTD_INV_DESC_ALL_ONE,
+                        VTD_INV_DESC_ALL_ONE, VTD_INV_DESC_ALL_ONE};
 
-    if ((inv_desc->lo & VTD_INV_DESC_CC_RSVD) || inv_desc->hi) {
-        error_report_once("%s: invalid cc inv desc: hi=%"PRIx64", lo=%"PRIx64
-                          " (reserved nonzero)", __func__, inv_desc->hi,
-                          inv_desc->lo);
+    if (!vtd_inv_desc_reserved_check(s, inv_desc, mask, false,
+                                     __func__, "cc inv")) {
         return false;
     }
+
     switch (inv_desc->lo & VTD_INV_DESC_CC_G) {
     case VTD_INV_DESC_CC_DOMAIN:
         trace_vtd_inv_desc_cc_domain(
@@ -2610,12 +2647,11 @@ static bool vtd_process_iotlb_desc(IntelIOMMUState *s, VTDInvDesc *inv_desc)
     uint16_t domain_id;
     uint8_t am;
     hwaddr addr;
+    uint64_t mask[4] = {VTD_INV_DESC_IOTLB_RSVD_LO, VTD_INV_DESC_IOTLB_RSVD_HI,
+                        VTD_INV_DESC_ALL_ONE, VTD_INV_DESC_ALL_ONE};
 
-    if ((inv_desc->lo & VTD_INV_DESC_IOTLB_RSVD_LO) ||
-        (inv_desc->hi & VTD_INV_DESC_IOTLB_RSVD_HI)) {
-        error_report_once("%s: invalid iotlb inv desc: hi=0x%"PRIx64
-                          ", lo=0x%"PRIx64" (reserved bits unzero)",
-                          __func__, inv_desc->hi, inv_desc->lo);
+    if (!vtd_inv_desc_reserved_check(s, inv_desc, mask, false,
+                                     __func__, "iotlb inv")) {
         return false;
     }
 
@@ -2656,6 +2692,14 @@ static bool vtd_process_iotlb_desc(IntelIOMMUState *s, VTDInvDesc *inv_desc)
 static bool vtd_process_inv_iec_desc(IntelIOMMUState *s,
                                      VTDInvDesc *inv_desc)
 {
+    uint64_t mask[4] = {VTD_INV_DESC_IEC_RSVD, VTD_INV_DESC_ALL_ONE,
+                        VTD_INV_DESC_ALL_ONE, VTD_INV_DESC_ALL_ONE};
+
+    if (!vtd_inv_desc_reserved_check(s, inv_desc, mask, false,
+                                     __func__, "iec inv")) {
+        return false;
+    }
+
     trace_vtd_inv_desc_iec(inv_desc->iec.granularity,
                            inv_desc->iec.index,
                            inv_desc->iec.index_mask);
@@ -2705,19 +2749,19 @@ static bool vtd_process_device_iotlb_desc(IntelIOMMUState *s,
     hwaddr addr;
     uint16_t sid;
     bool size;
+    uint64_t mask[4] = {VTD_INV_DESC_DEVICE_IOTLB_RSVD_LO,
+                        VTD_INV_DESC_DEVICE_IOTLB_RSVD_HI,
+                        VTD_INV_DESC_ALL_ONE, VTD_INV_DESC_ALL_ONE};
+
+    if (!vtd_inv_desc_reserved_check(s, inv_desc, mask, false,
+                                     __func__, "dev-iotlb inv")) {
+        return false;
+    }
 
     addr = VTD_INV_DESC_DEVICE_IOTLB_ADDR(inv_desc->hi);
     sid = VTD_INV_DESC_DEVICE_IOTLB_SID(inv_desc->lo);
     size = VTD_INV_DESC_DEVICE_IOTLB_SIZE(inv_desc->hi);
 
-    if ((inv_desc->lo & VTD_INV_DESC_DEVICE_IOTLB_RSVD_LO) ||
-        (inv_desc->hi & VTD_INV_DESC_DEVICE_IOTLB_RSVD_HI)) {
-        error_report_once("%s: invalid dev-iotlb inv desc: hi=%"PRIx64
-                          ", lo=%"PRIx64" (reserved nonzero)", __func__,
-                          inv_desc->hi, inv_desc->lo);
-        return false;
-    }
-
     /*
      * Using sid is OK since the guest should have finished the
      * initialization of both the bus and device.
@@ -2847,6 +2891,7 @@ static void vtd_handle_iqt_write(IntelIOMMUState *s)
     if (s->iq_dw && (val & VTD_IQT_QT_256_RSV_BIT)) {
         error_report_once("%s: RSV bit is set: val=0x%"PRIx64,
                           __func__, val);
+        vtd_handle_inv_queue_error(s);
         return;
     }
     s->iq_tail = VTD_IQT_QT(s->iq_dw, val);
@@ -3372,6 +3417,7 @@ static Property vtd_properties[] = {
     DEFINE_PROP_BOOL("x-pasid-mode", IntelIOMMUState, pasid, false),
     DEFINE_PROP_BOOL("dma-drain", IntelIOMMUState, dma_drain, true),
     DEFINE_PROP_BOOL("dma-translation", IntelIOMMUState, dma_translation, true),
+    DEFINE_PROP_BOOL("stale-tm", IntelIOMMUState, stale_tm, false),
     DEFINE_PROP_END_OF_LIST(),
 };
 
@@ -4138,15 +4184,15 @@ static void vtd_init(IntelIOMMUState *s)
      */
     vtd_spte_rsvd[0] = ~0ULL;
     vtd_spte_rsvd[1] = VTD_SPTE_PAGE_L1_RSVD_MASK(s->aw_bits,
-                                                  x86_iommu->dt_supported);
+                                        x86_iommu->dt_supported && s->stale_tm);
     vtd_spte_rsvd[2] = VTD_SPTE_PAGE_L2_RSVD_MASK(s->aw_bits);
     vtd_spte_rsvd[3] = VTD_SPTE_PAGE_L3_RSVD_MASK(s->aw_bits);
     vtd_spte_rsvd[4] = VTD_SPTE_PAGE_L4_RSVD_MASK(s->aw_bits);
 
     vtd_spte_rsvd_large[2] = VTD_SPTE_LPAGE_L2_RSVD_MASK(s->aw_bits,
-                                                    x86_iommu->dt_supported);
+                                        x86_iommu->dt_supported && s->stale_tm);
     vtd_spte_rsvd_large[3] = VTD_SPTE_LPAGE_L3_RSVD_MASK(s->aw_bits,
-                                                    x86_iommu->dt_supported);
+                                        x86_iommu->dt_supported && s->stale_tm);
 
     if (s->scalable_mode || s->snoop_control) {
         vtd_spte_rsvd[1] &= ~VTD_SPTE_SNP;
diff --git a/hw/i386/intel_iommu_internal.h b/hw/i386/intel_iommu_internal.h
index 13d5d129ae..4323fc5d6d 100644
--- a/hw/i386/intel_iommu_internal.h
+++ b/hw/i386/intel_iommu_internal.h
@@ -356,6 +356,7 @@ union VTDInvDesc {
 typedef union VTDInvDesc VTDInvDesc;
 
 /* Masks for struct VTDInvDesc */
+#define VTD_INV_DESC_ALL_ONE            -1ULL
 #define VTD_INV_DESC_TYPE(val)          ((((val) >> 5) & 0x70ULL) | \
                                          ((val) & 0xfULL))
 #define VTD_INV_DESC_CC                 0x1 /* Context-cache Invalidate Desc */
@@ -409,11 +410,14 @@ typedef union VTDInvDesc VTDInvDesc;
 #define VTD_INV_DESC_DEVICE_IOTLB_RSVD_HI 0xffeULL
 #define VTD_INV_DESC_DEVICE_IOTLB_RSVD_LO 0xffff0000ffe0f1f0
 
+/* Masks for Interrupt Entry Invalidate Descriptor */
+#define VTD_INV_DESC_IEC_RSVD           0xffff000007fff1e0ULL
+
 /* Rsvd field masks for spte */
 #define VTD_SPTE_SNP 0x800ULL
 
-#define VTD_SPTE_PAGE_L1_RSVD_MASK(aw, dt_supported) \
-        dt_supported ? \
+#define VTD_SPTE_PAGE_L1_RSVD_MASK(aw, stale_tm) \
+        stale_tm ? \
         (0x800ULL | ~(VTD_HAW_MASK(aw) | VTD_SL_IGN_COM | VTD_SL_TM)) : \
         (0x800ULL | ~(VTD_HAW_MASK(aw) | VTD_SL_IGN_COM))
 #define VTD_SPTE_PAGE_L2_RSVD_MASK(aw) \
@@ -423,12 +427,12 @@ typedef union VTDInvDesc VTDInvDesc;
 #define VTD_SPTE_PAGE_L4_RSVD_MASK(aw) \
         (0x880ULL | ~(VTD_HAW_MASK(aw) | VTD_SL_IGN_COM))
 
-#define VTD_SPTE_LPAGE_L2_RSVD_MASK(aw, dt_supported) \
-        dt_supported ? \
+#define VTD_SPTE_LPAGE_L2_RSVD_MASK(aw, stale_tm) \
+        stale_tm ? \
         (0x1ff800ULL | ~(VTD_HAW_MASK(aw) | VTD_SL_IGN_COM | VTD_SL_TM)) : \
         (0x1ff800ULL | ~(VTD_HAW_MASK(aw) | VTD_SL_IGN_COM))
-#define VTD_SPTE_LPAGE_L3_RSVD_MASK(aw, dt_supported) \
-        dt_supported ? \
+#define VTD_SPTE_LPAGE_L3_RSVD_MASK(aw, stale_tm) \
+        stale_tm ? \
         (0x3ffff800ULL | ~(VTD_HAW_MASK(aw) | VTD_SL_IGN_COM | VTD_SL_TM)) : \
         (0x3ffff800ULL | ~(VTD_HAW_MASK(aw) | VTD_SL_IGN_COM))
 
diff --git a/hw/i386/pc.c b/hw/i386/pc.c
index 2047633e4c..830614d930 100644
--- a/hw/i386/pc.c
+++ b/hw/i386/pc.c
@@ -82,6 +82,7 @@
 GlobalProperty pc_compat_9_1[] = {
     { "ICH9-LPC", "x-smi-swsmi-timer", "off" },
     { "ICH9-LPC", "x-smi-periodic-timer", "off" },
+    { TYPE_INTEL_IOMMU_DEVICE, "stale-tm", "on" },
 };
 const size_t pc_compat_9_1_len = G_N_ELEMENTS(pc_compat_9_1);
 
diff --git a/hw/mem/cxl_type3.c b/hw/mem/cxl_type3.c
index 235ac40aeb..5cf754b38f 100644
--- a/hw/mem/cxl_type3.c
+++ b/hw/mem/cxl_type3.c
@@ -17,6 +17,7 @@
 #include "hw/mem/pc-dimm.h"
 #include "hw/pci/pci.h"
 #include "hw/qdev-properties.h"
+#include "hw/qdev-properties-system.h"
 #include "qapi/error.h"
 #include "qemu/log.h"
 #include "qemu/module.h"
@@ -919,16 +920,15 @@ static void ct3_realize(PCIDevice *pci_dev, Error **errp)
     ct3d->patrol_scrub_attrs.scrub_flags = CXL_MEMDEV_PS_ENABLE_DEFAULT;
 
     /* Set default value for DDR5 ECS read attributes */
+    ct3d->ecs_attrs.ecs_log_cap = CXL_ECS_LOG_ENTRY_TYPE_DEFAULT;
     for (count = 0; count < CXL_ECS_NUM_MEDIA_FRUS; count++) {
-        ct3d->ecs_attrs[count].ecs_log_cap =
-                            CXL_ECS_LOG_ENTRY_TYPE_DEFAULT;
-        ct3d->ecs_attrs[count].ecs_cap =
+        ct3d->ecs_attrs.fru_attrs[count].ecs_cap =
                             CXL_ECS_REALTIME_REPORT_CAP_DEFAULT;
-        ct3d->ecs_attrs[count].ecs_config =
+        ct3d->ecs_attrs.fru_attrs[count].ecs_config =
                             CXL_ECS_THRESHOLD_COUNT_DEFAULT |
                             (CXL_ECS_MODE_DEFAULT << 3);
         /* Reserved */
-        ct3d->ecs_attrs[count].ecs_flags = 0;
+        ct3d->ecs_attrs.fru_attrs[count].ecs_flags = 0;
     }
 
     return;
@@ -1200,6 +1200,7 @@ static void ct3d_reset(DeviceState *dev)
     uint32_t *reg_state = ct3d->cxl_cstate.crb.cache_mem_registers;
     uint32_t *write_msk = ct3d->cxl_cstate.crb.cache_mem_regs_write_mask;
 
+    pcie_cap_fill_link_ep_usp(PCI_DEVICE(dev), ct3d->width, ct3d->speed);
     cxl_component_register_init_common(reg_state, write_msk, CXL2_TYPE3_DEVICE);
     cxl_device_register_init_t3(ct3d);
 
@@ -1229,6 +1230,10 @@ static Property ct3_props[] = {
     DEFINE_PROP_UINT8("num-dc-regions", CXLType3Dev, dc.num_regions, 0),
     DEFINE_PROP_LINK("volatile-dc-memdev", CXLType3Dev, dc.host_dc,
                      TYPE_MEMORY_BACKEND, HostMemoryBackend *),
+    DEFINE_PROP_PCIE_LINK_SPEED("x-speed", CXLType3Dev,
+                                speed, PCIE_LINK_SPEED_32),
+    DEFINE_PROP_PCIE_LINK_WIDTH("x-width", CXLType3Dev,
+                                width, PCIE_LINK_WIDTH_16),
     DEFINE_PROP_END_OF_LIST(),
 };
 
@@ -1375,9 +1380,7 @@ void qmp_cxl_inject_poison(const char *path, uint64_t start, uint64_t length,
     ct3d = CXL_TYPE3(obj);
 
     QLIST_FOREACH(p, &ct3d->poison_list, node) {
-        if (((start >= p->start) && (start < p->start + p->length)) ||
-            ((start + length > p->start) &&
-             (start + length <= p->start + p->length))) {
+        if ((start < p->start + p->length) && (start + length > p->start)) {
             error_setg(errp,
                        "Overlap with existing poisoned region not supported");
             return;
@@ -2060,11 +2063,11 @@ static void qmp_cxl_process_dynamic_capacity_prescriptive(const char *path,
     stw_le_p(&dCap.host_id, hid);
     /* only valid for DC_REGION_CONFIG_UPDATED event */
     dCap.updated_region_id = 0;
-    dCap.flags = 0;
     for (i = 0; i < num_extents; i++) {
         memcpy(&dCap.dynamic_capacity_extent, &extents[i],
                sizeof(CXLDCExtentRaw));
 
+        dCap.flags = 0;
         if (i < num_extents - 1) {
             /* Set "More" flag */
             dCap.flags |= BIT(0);
diff --git a/hw/net/npcm_gmac.c b/hw/net/npcm_gmac.c
index 6fa6bece61..685905f9e2 100644
--- a/hw/net/npcm_gmac.c
+++ b/hw/net/npcm_gmac.c
@@ -546,9 +546,8 @@ static void gmac_try_send_next_packet(NPCMGMACState *gmac)
 
         /* 1 = DMA Owned, 0 = Software Owned */
         if (!(tx_desc.tdes0 & TX_DESC_TDES0_OWN)) {
-            qemu_log_mask(LOG_GUEST_ERROR,
-                          "TX Descriptor @ 0x%x is owned by software\n",
-                          desc_addr);
+            trace_npcm_gmac_tx_desc_owner(DEVICE(gmac)->canonical_path,
+                                          desc_addr);
             gmac->regs[R_NPCM_DMA_STATUS] |= NPCM_DMA_STATUS_TU;
             gmac_dma_set_state(gmac, NPCM_DMA_STATUS_TX_PROCESS_STATE_SHIFT,
                 NPCM_DMA_STATUS_TX_SUSPENDED_STATE);
diff --git a/hw/net/trace-events b/hw/net/trace-events
index 91a3d0c054..d0f1d8c0fb 100644
--- a/hw/net/trace-events
+++ b/hw/net/trace-events
@@ -478,6 +478,7 @@ npcm_gmac_packet_received(const char* name, uint32_t len) "%s: Reception finishe
 npcm_gmac_packet_sent(const char* name, uint16_t len) "%s: TX packet sent!, length: 0x%04" PRIX16
 npcm_gmac_debug_desc_data(const char* name, void* addr, uint32_t des0, uint32_t des1, uint32_t des2, uint32_t des3)"%s: Address: %p Descriptor 0: 0x%04" PRIX32 " Descriptor 1: 0x%04" PRIX32 "Descriptor 2: 0x%04" PRIX32 " Descriptor 3: 0x%04" PRIX32
 npcm_gmac_packet_tx_desc_data(const char* name, uint32_t tdes0, uint32_t tdes1) "%s: Tdes0: 0x%04" PRIX32 " Tdes1: 0x%04" PRIX32
+npcm_gmac_tx_desc_owner(const char* name, uint32_t desc_addr) "%s: TX Descriptor @0x%04" PRIX32 " is owned by software"
 
 # npcm_pcs.c
 npcm_pcs_reg_read(const char *name, uint16_t indirect_access_baes, uint64_t offset, uint16_t value) "%s: IND: 0x%02" PRIx16 " offset: 0x%04" PRIx64 " value: 0x%04" PRIx16
diff --git a/hw/pci-bridge/cxl_downstream.c b/hw/pci-bridge/cxl_downstream.c
index 4b42984360..c347ac06f3 100644
--- a/hw/pci-bridge/cxl_downstream.c
+++ b/hw/pci-bridge/cxl_downstream.c
@@ -13,6 +13,8 @@
 #include "hw/pci/msi.h"
 #include "hw/pci/pcie.h"
 #include "hw/pci/pcie_port.h"
+#include "hw/qdev-properties.h"
+#include "hw/qdev-properties-system.h"
 #include "hw/cxl/cxl.h"
 #include "qapi/error.h"
 
@@ -210,24 +212,20 @@ static void cxl_dsp_exitfn(PCIDevice *d)
     pci_bridge_exitfn(d);
 }
 
-static void cxl_dsp_instance_post_init(Object *obj)
-{
-    PCIESlot *s = PCIE_SLOT(obj);
-
-    if (!s->speed) {
-        s->speed = QEMU_PCI_EXP_LNK_2_5GT;
-    }
-
-    if (!s->width) {
-        s->width = QEMU_PCI_EXP_LNK_X1;
-    }
-}
+static Property cxl_dsp_props[] = {
+    DEFINE_PROP_PCIE_LINK_SPEED("x-speed", PCIESlot,
+                                speed, PCIE_LINK_SPEED_64),
+    DEFINE_PROP_PCIE_LINK_WIDTH("x-width", PCIESlot,
+                                width, PCIE_LINK_WIDTH_16),
+    DEFINE_PROP_END_OF_LIST()
+};
 
 static void cxl_dsp_class_init(ObjectClass *oc, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(oc);
     PCIDeviceClass *k = PCI_DEVICE_CLASS(oc);
 
+    device_class_set_props(dc, cxl_dsp_props);
     k->config_write = cxl_dsp_config_write;
     k->realize = cxl_dsp_realize;
     k->exit = cxl_dsp_exitfn;
@@ -243,7 +241,6 @@ static const TypeInfo cxl_dsp_info = {
     .name = TYPE_CXL_DSP,
     .instance_size = sizeof(CXLDownstreamPort),
     .parent = TYPE_PCIE_SLOT,
-    .instance_post_init = cxl_dsp_instance_post_init,
     .class_init = cxl_dsp_class_init,
     .interfaces = (InterfaceInfo[]) {
         { INTERFACE_PCIE_DEVICE },
diff --git a/hw/pci-bridge/cxl_root_port.c b/hw/pci-bridge/cxl_root_port.c
index 2dd10239bd..5e2156d7ba 100644
--- a/hw/pci-bridge/cxl_root_port.c
+++ b/hw/pci-bridge/cxl_root_port.c
@@ -24,6 +24,7 @@
 #include "hw/pci/pcie_port.h"
 #include "hw/pci/msi.h"
 #include "hw/qdev-properties.h"
+#include "hw/qdev-properties-system.h"
 #include "hw/sysbus.h"
 #include "qapi/error.h"
 #include "hw/cxl/cxl.h"
@@ -206,6 +207,10 @@ static Property gen_rp_props[] = {
                      -1),
     DEFINE_PROP_SIZE("pref64-reserve", CXLRootPort, res_reserve.mem_pref_64,
                      -1),
+    DEFINE_PROP_PCIE_LINK_SPEED("x-speed", PCIESlot,
+                                speed, PCIE_LINK_SPEED_64),
+    DEFINE_PROP_PCIE_LINK_WIDTH("x-width", PCIESlot,
+                                width, PCIE_LINK_WIDTH_32),
     DEFINE_PROP_END_OF_LIST()
 };
 
diff --git a/hw/pci-bridge/cxl_upstream.c b/hw/pci-bridge/cxl_upstream.c
index a5a39cc524..55f8b0053f 100644
--- a/hw/pci-bridge/cxl_upstream.c
+++ b/hw/pci-bridge/cxl_upstream.c
@@ -11,6 +11,7 @@
 #include "qemu/osdep.h"
 #include "qemu/log.h"
 #include "hw/qdev-properties.h"
+#include "hw/qdev-properties-system.h"
 #include "hw/pci/msi.h"
 #include "hw/pci/pcie.h"
 #include "hw/pci/pcie_port.h"
@@ -100,6 +101,7 @@ static void cxl_usp_reset(DeviceState *qdev)
 
     pci_bridge_reset(qdev);
     pcie_cap_deverr_reset(d);
+    pcie_cap_fill_link_ep_usp(d, usp->width, usp->speed);
     latch_registers(usp);
 }
 
@@ -363,6 +365,10 @@ static void cxl_usp_exitfn(PCIDevice *d)
 static Property cxl_upstream_props[] = {
     DEFINE_PROP_UINT64("sn", CXLUpstreamPort, sn, UI64_NULL),
     DEFINE_PROP_STRING("cdat", CXLUpstreamPort, cxl_cstate.cdat.filename),
+    DEFINE_PROP_PCIE_LINK_SPEED("x-speed", CXLUpstreamPort,
+                                speed, PCIE_LINK_SPEED_32),
+    DEFINE_PROP_PCIE_LINK_WIDTH("x-width", CXLUpstreamPort,
+                                width, PCIE_LINK_WIDTH_16),
     DEFINE_PROP_END_OF_LIST()
 };
 
diff --git a/hw/pci-bridge/pci_expander_bridge.c b/hw/pci-bridge/pci_expander_bridge.c
index dfaea6cbf4..07d411cff5 100644
--- a/hw/pci-bridge/pci_expander_bridge.c
+++ b/hw/pci-bridge/pci_expander_bridge.c
@@ -38,7 +38,6 @@ DECLARE_INSTANCE_CHECKER(PXBBus, PXB_BUS,
 DECLARE_INSTANCE_CHECKER(PXBBus, PXB_PCIE_BUS,
                          TYPE_PXB_PCIE_BUS)
 
-#define TYPE_PXB_CXL_BUS "pxb-cxl-bus"
 DECLARE_INSTANCE_CHECKER(PXBBus, PXB_CXL_BUS,
                          TYPE_PXB_CXL_BUS)
 
@@ -85,12 +84,25 @@ static uint16_t pxb_bus_numa_node(PCIBus *bus)
     return pxb->numa_node;
 }
 
+static void prop_pxb_uid_get(Object *obj, Visitor *v, const char *name,
+                             void *opaque, Error **errp)
+{
+    uint32_t uid = pci_bus_num(PCI_BUS(obj));
+
+    visit_type_uint32(v, name, &uid, errp);
+}
+
 static void pxb_bus_class_init(ObjectClass *class, void *data)
 {
     PCIBusClass *pbc = PCI_BUS_CLASS(class);
 
     pbc->bus_num = pxb_bus_num;
     pbc->numa_node = pxb_bus_numa_node;
+
+    object_class_property_add(class, "acpi_uid", "uint32",
+                              prop_pxb_uid_get, NULL, NULL, NULL);
+    object_class_property_set_description(class, "acpi_uid",
+        "ACPI Unique ID used to distinguish this PCI Host Bridge / ACPI00016");
 }
 
 static const TypeInfo pxb_bus_info = {
@@ -318,7 +330,7 @@ static gint pxb_compare(gconstpointer a, gconstpointer b)
            0;
 }
 
-static void pxb_dev_realize_common(PCIDevice *dev, enum BusType type,
+static bool pxb_dev_realize_common(PCIDevice *dev, enum BusType type,
                                    Error **errp)
 {
     PXBDev *pxb = PXB_DEV(dev);
@@ -330,13 +342,13 @@ static void pxb_dev_realize_common(PCIDevice *dev, enum BusType type,
 
     if (ms->numa_state == NULL) {
         error_setg(errp, "NUMA is not supported by this machine-type");
-        return;
+        return false;
     }
 
     if (pxb->numa_node != NUMA_NODE_UNASSIGNED &&
         pxb->numa_node >= ms->numa_state->num_nodes) {
         error_setg(errp, "Illegal numa node %d", pxb->numa_node);
-        return;
+        return false;
     }
 
     if (dev->qdev.id && *dev->qdev.id) {
@@ -382,12 +394,13 @@ static void pxb_dev_realize_common(PCIDevice *dev, enum BusType type,
     pci_config_set_class(dev->config, PCI_CLASS_BRIDGE_HOST);
 
     pxb_dev_list = g_list_insert_sorted(pxb_dev_list, pxb, pxb_compare);
-    return;
+    return true;
 
 err_register_bus:
     object_unref(OBJECT(bds));
     object_unparent(OBJECT(bus));
     object_unref(OBJECT(ds));
+    return false;
 }
 
 static void pxb_dev_realize(PCIDevice *dev, Error **errp)
@@ -488,7 +501,9 @@ static void pxb_cxl_dev_realize(PCIDevice *dev, Error **errp)
         return;
     }
 
-    pxb_dev_realize_common(dev, CXL, errp);
+    if (!pxb_dev_realize_common(dev, CXL, errp)) {
+        return;
+    }
     pxb_cxl_dev_reset(DEVICE(dev));
 }
 
diff --git a/hw/pci-host/gpex-acpi.c b/hw/pci-host/gpex-acpi.c
index 391fabb8a8..e8b4c64c5f 100644
--- a/hw/pci-host/gpex-acpi.c
+++ b/hw/pci-host/gpex-acpi.c
@@ -141,6 +141,7 @@ void acpi_dsdt_add_gpex(Aml *scope, struct GPEXConfig *cfg)
         QLIST_FOREACH(bus, &bus->child, sibling) {
             uint8_t bus_num = pci_bus_num(bus);
             uint8_t numa_node = pci_bus_numa_node(bus);
+            uint32_t uid;
             bool is_cxl = pci_bus_is_cxl(bus);
 
             if (!pci_bus_is_root(bus)) {
@@ -156,6 +157,8 @@ void acpi_dsdt_add_gpex(Aml *scope, struct GPEXConfig *cfg)
                 nr_pcie_buses = bus_num;
             }
 
+            uid = object_property_get_uint(OBJECT(bus), "acpi_uid",
+                                           &error_fatal);
             dev = aml_device("PC%.02X", bus_num);
             if (is_cxl) {
                 struct Aml *pkg = aml_package(2);
@@ -168,7 +171,7 @@ void acpi_dsdt_add_gpex(Aml *scope, struct GPEXConfig *cfg)
                 aml_append(dev, aml_name_decl("_CID", aml_string("PNP0A03")));
             }
             aml_append(dev, aml_name_decl("_BBN", aml_int(bus_num)));
-            aml_append(dev, aml_name_decl("_UID", aml_int(bus_num)));
+            aml_append(dev, aml_name_decl("_UID", aml_int(uid)));
             aml_append(dev, aml_name_decl("_STR", aml_unicode("pxb Device")));
             aml_append(dev, aml_name_decl("_CCA", aml_int(1)));
             if (numa_node != NUMA_NODE_UNASSIGNED) {
diff --git a/hw/pci/pci.c b/hw/pci/pci.c
index 87da35ca9b..1416ae202c 100644
--- a/hw/pci/pci.c
+++ b/hw/pci/pci.c
@@ -67,6 +67,19 @@ static char *pcibus_get_fw_dev_path(DeviceState *dev);
 static void pcibus_reset_hold(Object *obj, ResetType type);
 static bool pcie_has_upstream_port(PCIDevice *dev);
 
+static void prop_pci_busnr_get(Object *obj, Visitor *v, const char *name,
+                             void *opaque, Error **errp)
+{
+    uint8_t busnr = pci_dev_bus_num(PCI_DEVICE(obj));
+
+    visit_type_uint8(v, name, &busnr, errp);
+}
+
+static const PropertyInfo prop_pci_busnr = {
+    .name = "busnr",
+    .get = prop_pci_busnr_get,
+};
+
 static Property pci_props[] = {
     DEFINE_PROP_PCI_DEVFN("addr", PCIDevice, devfn, -1),
     DEFINE_PROP_STRING("romfile", PCIDevice, romfile),
@@ -87,6 +100,9 @@ static Property pci_props[] = {
                     QEMU_PCIE_ARI_NEXTFN_1_BITNR, false),
     DEFINE_PROP_SIZE32("x-max-bounce-buffer-size", PCIDevice,
                      max_bounce_buffer_size, DEFAULT_MAX_BOUNCE_BUFFER_SIZE),
+    DEFINE_PROP_BIT("x-pcie-ext-tag", PCIDevice, cap_present,
+                    QEMU_PCIE_EXT_TAG_BITNR, true),
+    { .name = "busnr", .info = &prop_pci_busnr },
     DEFINE_PROP_END_OF_LIST()
 };
 
diff --git a/hw/pci/pci_bridge.c b/hw/pci/pci_bridge.c
index 6a4e38856d..2c7bb1a525 100644
--- a/hw/pci/pci_bridge.c
+++ b/hw/pci/pci_bridge.c
@@ -380,9 +380,12 @@ void pci_bridge_initfn(PCIDevice *dev, const char *typename)
     sec_bus->map_irq = br->map_irq ? br->map_irq : pci_swizzle_map_irq_fn;
     sec_bus->address_space_mem = &br->address_space_mem;
     memory_region_init(&br->address_space_mem, OBJECT(br), "pci_bridge_pci", UINT64_MAX);
+    address_space_init(&br->as_mem, &br->address_space_mem,
+                       "pci_bridge_pci_mem");
     sec_bus->address_space_io = &br->address_space_io;
     memory_region_init(&br->address_space_io, OBJECT(br), "pci_bridge_io",
                        4 * GiB);
+    address_space_init(&br->as_io, &br->address_space_io, "pci_bridge_pci_io");
     pci_bridge_region_init(br);
     QLIST_INIT(&sec_bus->child);
     QLIST_INSERT_HEAD(&parent->child, sec_bus, sibling);
@@ -399,6 +402,8 @@ void pci_bridge_exitfn(PCIDevice *pci_dev)
     PCIBridge *s = PCI_BRIDGE(pci_dev);
     assert(QLIST_EMPTY(&s->sec_bus.child));
     QLIST_REMOVE(&s->sec_bus, sibling);
+    address_space_destroy(&s->as_mem);
+    address_space_destroy(&s->as_io);
     pci_bridge_region_del(s, &s->windows);
     pci_bridge_region_cleanup(s, &s->windows);
     /* object_unparent() is called automatically during device deletion */
diff --git a/hw/pci/pcie.c b/hw/pci/pcie.c
index 4b2f0805c6..0b455c8654 100644
--- a/hw/pci/pcie.c
+++ b/hw/pci/pcie.c
@@ -86,7 +86,13 @@ pcie_cap_v1_fill(PCIDevice *dev, uint8_t port, uint8_t type, uint8_t version)
      * Specification, Revision 1.1., or subsequent PCI Express Base
      * Specification revisions.
      */
-    pci_set_long(exp_cap + PCI_EXP_DEVCAP, PCI_EXP_DEVCAP_RBER);
+    uint32_t devcap = PCI_EXP_DEVCAP_RBER;
+
+    if (dev->cap_present & QEMU_PCIE_EXT_TAG) {
+        devcap = PCI_EXP_DEVCAP_RBER | PCI_EXP_DEVCAP_EXT_TAG;
+    }
+
+    pci_set_long(exp_cap + PCI_EXP_DEVCAP, devcap);
 
     pci_set_long(exp_cap + PCI_EXP_LNKCAP,
                  (port << PCI_EXP_LNKCAP_PN_SHIFT) |
@@ -105,46 +111,18 @@ pcie_cap_v1_fill(PCIDevice *dev, uint8_t port, uint8_t type, uint8_t version)
     pci_set_word(cmask + PCI_EXP_LNKSTA, 0);
 }
 
-static void pcie_cap_fill_slot_lnk(PCIDevice *dev)
+/* Includes setting the target speed default */
+static void pcie_cap_fill_lnk(uint8_t *exp_cap, PCIExpLinkWidth width,
+                              PCIExpLinkSpeed speed)
 {
-    PCIESlot *s = (PCIESlot *)object_dynamic_cast(OBJECT(dev), TYPE_PCIE_SLOT);
-    uint8_t *exp_cap = dev->config + dev->exp.exp_cap;
-
-    /* Skip anything that isn't a PCIESlot */
-    if (!s) {
-        return;
-    }
-
     /* Clear and fill LNKCAP from what was configured above */
     pci_long_test_and_clear_mask(exp_cap + PCI_EXP_LNKCAP,
                                  PCI_EXP_LNKCAP_MLW | PCI_EXP_LNKCAP_SLS);
     pci_long_test_and_set_mask(exp_cap + PCI_EXP_LNKCAP,
-                               QEMU_PCI_EXP_LNKCAP_MLW(s->width) |
-                               QEMU_PCI_EXP_LNKCAP_MLS(s->speed));
-
-    /*
-     * Link bandwidth notification is required for all root ports and
-     * downstream ports supporting links wider than x1 or multiple link
-     * speeds.
-     */
-    if (s->width > QEMU_PCI_EXP_LNK_X1 ||
-        s->speed > QEMU_PCI_EXP_LNK_2_5GT) {
-        pci_long_test_and_set_mask(exp_cap + PCI_EXP_LNKCAP,
-                                   PCI_EXP_LNKCAP_LBNC);
-    }
-
-    if (s->speed > QEMU_PCI_EXP_LNK_2_5GT) {
-        /*
-         * Hot-plug capable downstream ports and downstream ports supporting
-         * link speeds greater than 5GT/s must hardwire PCI_EXP_LNKCAP_DLLLARC
-         * to 1b.  PCI_EXP_LNKCAP_DLLLARC implies PCI_EXP_LNKSTA_DLLLA, which
-         * we also hardwire to 1b here.  2.5GT/s hot-plug slots should also
-         * technically implement this, but it's not done here for compatibility.
-         */
-        pci_long_test_and_set_mask(exp_cap + PCI_EXP_LNKCAP,
-                                   PCI_EXP_LNKCAP_DLLLARC);
-        /* the PCI_EXP_LNKSTA_DLLLA will be set in the hotplug function */
+                               QEMU_PCI_EXP_LNKCAP_MLW(width) |
+                               QEMU_PCI_EXP_LNKCAP_MLS(speed));
 
+    if (speed > QEMU_PCI_EXP_LNK_2_5GT) {
         /*
          * Target Link Speed defaults to the highest link speed supported by
          * the component.  2.5GT/s devices are permitted to hardwire to zero.
@@ -152,7 +130,7 @@ static void pcie_cap_fill_slot_lnk(PCIDevice *dev)
         pci_word_test_and_clear_mask(exp_cap + PCI_EXP_LNKCTL2,
                                      PCI_EXP_LNKCTL2_TLS);
         pci_word_test_and_set_mask(exp_cap + PCI_EXP_LNKCTL2,
-                                   QEMU_PCI_EXP_LNKCAP_MLS(s->speed) &
+                                   QEMU_PCI_EXP_LNKCAP_MLS(speed) &
                                    PCI_EXP_LNKCTL2_TLS);
     }
 
@@ -161,27 +139,82 @@ static void pcie_cap_fill_slot_lnk(PCIDevice *dev)
      * actually a reference to the highest bit supported in this register.
      * We assume the device supports all link speeds.
      */
-    if (s->speed > QEMU_PCI_EXP_LNK_5GT) {
+    if (speed > QEMU_PCI_EXP_LNK_5GT) {
         pci_long_test_and_clear_mask(exp_cap + PCI_EXP_LNKCAP2, ~0U);
         pci_long_test_and_set_mask(exp_cap + PCI_EXP_LNKCAP2,
                                    PCI_EXP_LNKCAP2_SLS_2_5GB |
                                    PCI_EXP_LNKCAP2_SLS_5_0GB |
                                    PCI_EXP_LNKCAP2_SLS_8_0GB);
-        if (s->speed > QEMU_PCI_EXP_LNK_8GT) {
+        if (speed > QEMU_PCI_EXP_LNK_8GT) {
             pci_long_test_and_set_mask(exp_cap + PCI_EXP_LNKCAP2,
                                        PCI_EXP_LNKCAP2_SLS_16_0GB);
         }
-        if (s->speed > QEMU_PCI_EXP_LNK_16GT) {
+        if (speed > QEMU_PCI_EXP_LNK_16GT) {
             pci_long_test_and_set_mask(exp_cap + PCI_EXP_LNKCAP2,
                                        PCI_EXP_LNKCAP2_SLS_32_0GB);
         }
-        if (s->speed > QEMU_PCI_EXP_LNK_32GT) {
+        if (speed > QEMU_PCI_EXP_LNK_32GT) {
             pci_long_test_and_set_mask(exp_cap + PCI_EXP_LNKCAP2,
                                        PCI_EXP_LNKCAP2_SLS_64_0GB);
         }
     }
 }
 
+void pcie_cap_fill_link_ep_usp(PCIDevice *dev, PCIExpLinkWidth width,
+                               PCIExpLinkSpeed speed)
+{
+    uint8_t *exp_cap = dev->config + dev->exp.exp_cap;
+
+    /*
+     * For an end point or USP need to set the current status as well
+     * as the capabilities.
+     */
+    pci_long_test_and_clear_mask(exp_cap + PCI_EXP_LNKSTA,
+                                 PCI_EXP_LNKSTA_CLS | PCI_EXP_LNKSTA_NLW);
+    pci_long_test_and_set_mask(exp_cap + PCI_EXP_LNKSTA,
+                               QEMU_PCI_EXP_LNKSTA_NLW(width) |
+                               QEMU_PCI_EXP_LNKSTA_CLS(speed));
+
+    pcie_cap_fill_lnk(exp_cap, width, speed);
+}
+
+static void pcie_cap_fill_slot_lnk(PCIDevice *dev)
+{
+    PCIESlot *s = (PCIESlot *)object_dynamic_cast(OBJECT(dev), TYPE_PCIE_SLOT);
+    uint8_t *exp_cap = dev->config + dev->exp.exp_cap;
+
+    /* Skip anything that isn't a PCIESlot */
+    if (!s) {
+        return;
+    }
+
+    /*
+     * Link bandwidth notification is required for all root ports and
+     * downstream ports supporting links wider than x1 or multiple link
+     * speeds.
+     */
+    if (s->width > QEMU_PCI_EXP_LNK_X1 ||
+        s->speed > QEMU_PCI_EXP_LNK_2_5GT) {
+        pci_long_test_and_set_mask(exp_cap + PCI_EXP_LNKCAP,
+                                   PCI_EXP_LNKCAP_LBNC);
+    }
+
+    if (s->speed > QEMU_PCI_EXP_LNK_2_5GT) {
+        /*
+         * Hot-plug capable downstream ports and downstream ports supporting
+         * link speeds greater than 5GT/s must hardwire PCI_EXP_LNKCAP_DLLLARC
+         * to 1b.  PCI_EXP_LNKCAP_DLLLARC implies PCI_EXP_LNKSTA_DLLLA, which
+         * we also hardwire to 1b here.  2.5GT/s hot-plug slots should also
+         * technically implement this, but it's not done here for compatibility.
+         */
+        pci_long_test_and_set_mask(exp_cap + PCI_EXP_LNKCAP,
+                                   PCI_EXP_LNKCAP_DLLLARC);
+        /* the PCI_EXP_LNKSTA_DLLLA will be set in the hotplug function */
+    }
+
+    pcie_cap_fill_lnk(exp_cap, s->width, s->speed);
+}
+
 int pcie_cap_init(PCIDevice *dev, uint8_t offset,
                   uint8_t type, uint8_t port,
                   Error **errp)
diff --git a/hw/rtc/ds1338.c b/hw/rtc/ds1338.c
index 13472c5670..c993182ae4 100644
--- a/hw/rtc/ds1338.c
+++ b/hw/rtc/ds1338.c
@@ -16,6 +16,7 @@
 #include "qemu/bcd.h"
 #include "qom/object.h"
 #include "sysemu/rtc.h"
+#include "trace.h"
 
 /* Size of NVRAM including both the user-accessible area and the
  * secondary register area.
@@ -125,6 +126,9 @@ static uint8_t ds1338_recv(I2CSlave *i2c)
     uint8_t res;
 
     res  = s->nvram[s->ptr];
+
+    trace_ds1338_recv(s->ptr, res);
+
     inc_regptr(s);
     return res;
 }
@@ -133,6 +137,8 @@ static int ds1338_send(I2CSlave *i2c, uint8_t data)
 {
     DS1338State *s = DS1338(i2c);
 
+    trace_ds1338_send(s->ptr, data);
+
     if (s->addr_byte) {
         s->ptr = data & (NVRAM_SIZE - 1);
         s->addr_byte = false;
diff --git a/hw/rtc/trace-events b/hw/rtc/trace-events
index ebb311a5b0..8012afe102 100644
--- a/hw/rtc/trace-events
+++ b/hw/rtc/trace-events
@@ -22,6 +22,10 @@ pl031_set_alarm(uint32_t ticks) "alarm set for %u ticks"
 aspeed_rtc_read(uint64_t addr, uint64_t value) "addr 0x%02" PRIx64 " value 0x%08" PRIx64
 aspeed_rtc_write(uint64_t addr, uint64_t value) "addr 0x%02" PRIx64 " value 0x%08" PRIx64
 
+# ds1338.c
+ds1338_recv(uint32_t addr, uint8_t value) "[0x%" PRIx32 "] -> 0x%02" PRIx8
+ds1338_send(uint32_t addr, uint8_t value) "[0x%" PRIx32 "] <- 0x%02" PRIx8
+
 # m48t59.c
 m48txx_nvram_io_read(uint64_t addr, uint64_t value) "io read addr:0x%04" PRIx64 " value:0x%02" PRIx64
 m48txx_nvram_io_write(uint64_t addr, uint64_t value) "io write addr:0x%04" PRIx64 " value:0x%02" PRIx64
diff --git a/hw/sensor/tmp105.c b/hw/sensor/tmp105.c
index 9d7b911f59..ef2824f3e1 100644
--- a/hw/sensor/tmp105.c
+++ b/hw/sensor/tmp105.c
@@ -27,6 +27,7 @@
 #include "qapi/visitor.h"
 #include "qemu/module.h"
 #include "hw/registerfields.h"
+#include "trace.h"
 
 FIELD(CONFIG, SHUTDOWN_MODE,        0, 1)
 FIELD(CONFIG, THERMOSTAT_MODE,      1, 1)
@@ -150,17 +151,21 @@ static void tmp105_read(TMP105State *s)
         s->buf[s->len++] = ((uint16_t) s->limit[1]) >> 0;
         break;
     }
+
+    trace_tmp105_read(s->i2c.address, s->pointer);
 }
 
 static void tmp105_write(TMP105State *s)
 {
+    trace_tmp105_write(s->i2c.address, s->pointer);
+
     switch (s->pointer & 3) {
     case TMP105_REG_TEMPERATURE:
         break;
 
     case TMP105_REG_CONFIG:
         if (FIELD_EX8(s->buf[0] & ~s->config, CONFIG, SHUTDOWN_MODE)) {
-            printf("%s: TMP105 shutdown\n", __func__);
+            trace_tmp105_write_shutdown(s->i2c.address);
         }
         s->config = FIELD_DP8(s->buf[0], CONFIG, ONE_SHOT, 0);
         s->faults = tmp105_faultq[FIELD_EX8(s->config, CONFIG, FAULT_QUEUE)];
diff --git a/hw/sensor/trace-events b/hw/sensor/trace-events
new file mode 100644
index 0000000000..a3fe54fa6d
--- /dev/null
+++ b/hw/sensor/trace-events
@@ -0,0 +1,6 @@
+# See docs/devel/tracing.rst for syntax documentation.
+
+# tmp105.c
+tmp105_read(uint8_t dev, uint8_t addr) "device: 0x%02x, addr: 0x%02x"
+tmp105_write(uint8_t dev, uint8_t addr) "device: 0x%02x, addr 0x%02x"
+tmp105_write_shutdown(uint8_t dev) "device: 0x%02x"
diff --git a/hw/sensor/trace.h b/hw/sensor/trace.h
new file mode 100644
index 0000000000..e4721560b0
--- /dev/null
+++ b/hw/sensor/trace.h
@@ -0,0 +1 @@
+#include "trace/trace-hw_sensor.h"
diff --git a/hw/timer/imx_gpt.c b/hw/timer/imx_gpt.c
index 23b3d79bdb..2663a9d9ef 100644
--- a/hw/timer/imx_gpt.c
+++ b/hw/timer/imx_gpt.c
@@ -18,19 +18,12 @@
 #include "migration/vmstate.h"
 #include "qemu/module.h"
 #include "qemu/log.h"
+#include "trace.h"
 
 #ifndef DEBUG_IMX_GPT
 #define DEBUG_IMX_GPT 0
 #endif
 
-#define DPRINTF(fmt, args...) \
-    do { \
-        if (DEBUG_IMX_GPT) { \
-            fprintf(stderr, "[%s]%s: " fmt , TYPE_IMX_GPT, \
-                                             __func__, ##args); \
-        } \
-    } while (0)
-
 static const char *imx_gpt_reg_name(uint32_t reg)
 {
     switch (reg) {
@@ -145,7 +138,7 @@ static void imx_gpt_set_freq(IMXGPTState *s)
     s->freq = imx_ccm_get_clock_frequency(s->ccm,
                                           s->clocks[clksrc]) / (1 + s->pr);
 
-    DPRINTF("Setting clksrc %d to frequency %d\n", clksrc, s->freq);
+    trace_imx_gpt_set_freq(clksrc, s->freq);
 
     if (s->freq) {
         ptimer_set_freq(s->timer, s->freq);
@@ -317,7 +310,7 @@ static uint64_t imx_gpt_read(void *opaque, hwaddr offset, unsigned size)
         break;
     }
 
-    DPRINTF("(%s) = 0x%08x\n", imx_gpt_reg_name(offset >> 2), reg_value);
+    trace_imx_gpt_read(imx_gpt_reg_name(offset >> 2), reg_value);
 
     return reg_value;
 }
@@ -384,8 +377,7 @@ static void imx_gpt_write(void *opaque, hwaddr offset, uint64_t value,
     IMXGPTState *s = IMX_GPT(opaque);
     uint32_t oldreg;
 
-    DPRINTF("(%s, value = 0x%08x)\n", imx_gpt_reg_name(offset >> 2),
-            (uint32_t)value);
+    trace_imx_gpt_write(imx_gpt_reg_name(offset >> 2), (uint32_t)value);
 
     switch (offset >> 2) {
     case 0:
@@ -485,7 +477,7 @@ static void imx_gpt_timeout(void *opaque)
 {
     IMXGPTState *s = IMX_GPT(opaque);
 
-    DPRINTF("\n");
+    trace_imx_gpt_timeout();
 
     s->sr |= s->next_int;
     s->next_int = 0;
diff --git a/hw/timer/trace-events b/hw/timer/trace-events
index f48a712801..5cfc369fba 100644
--- a/hw/timer/trace-events
+++ b/hw/timer/trace-events
@@ -49,6 +49,12 @@ cmsdk_apb_dualtimer_read(uint64_t offset, uint64_t data, unsigned size) "CMSDK A
 cmsdk_apb_dualtimer_write(uint64_t offset, uint64_t data, unsigned size) "CMSDK APB dualtimer write: offset 0x%" PRIx64 " data 0x%" PRIx64 " size %u"
 cmsdk_apb_dualtimer_reset(void) "CMSDK APB dualtimer: reset"
 
+# imx_gpt.c
+imx_gpt_set_freq(uint32_t clksrc, uint32_t freq) "Setting clksrc %u to %u Hz"
+imx_gpt_read(const char *name, uint64_t value) "%s -> 0x%08" PRIx64
+imx_gpt_write(const char *name, uint64_t value) "%s <- 0x%08" PRIx64
+imx_gpt_timeout(void) ""
+
 # npcm7xx_timer.c
 npcm7xx_timer_read(const char *id, uint64_t offset, uint64_t value) " %s offset: 0x%04" PRIx64 " value 0x%08" PRIx64
 npcm7xx_timer_write(const char *id, uint64_t offset, uint64_t value) "%s offset: 0x%04" PRIx64 " value 0x%08" PRIx64
diff --git a/hw/vfio/migration.c b/hw/vfio/migration.c
index 992dc3b102..01aa11013e 100644
--- a/hw/vfio/migration.c
+++ b/hw/vfio/migration.c
@@ -370,6 +370,10 @@ static ssize_t vfio_save_block(QEMUFile *f, VFIOMigration *migration)
          * please refer to the Linux kernel VFIO uAPI.
          */
         if (errno == ENOMSG) {
+            if (!migration->event_precopy_empty_hit) {
+                trace_vfio_save_block_precopy_empty_hit(migration->vbasedev->name);
+                migration->event_precopy_empty_hit = true;
+            }
             return 0;
         }
 
@@ -379,6 +383,9 @@ static ssize_t vfio_save_block(QEMUFile *f, VFIOMigration *migration)
         return 0;
     }
 
+    /* Non-empty read: re-arm the trace event */
+    migration->event_precopy_empty_hit = false;
+
     qemu_put_be64(f, VFIO_MIG_FLAG_DEV_DATA_STATE);
     qemu_put_be64(f, data_size);
     qemu_put_buffer(f, migration->data_buffer, data_size);
@@ -472,6 +479,9 @@ static int vfio_save_setup(QEMUFile *f, void *opaque, Error **errp)
         return -ENOMEM;
     }
 
+    migration->event_save_iterate_started = false;
+    migration->event_precopy_empty_hit = false;
+
     if (vfio_precopy_supported(vbasedev)) {
         switch (migration->device_state) {
         case VFIO_DEVICE_STATE_RUNNING:
@@ -602,6 +612,11 @@ static int vfio_save_iterate(QEMUFile *f, void *opaque)
     VFIOMigration *migration = vbasedev->migration;
     ssize_t data_size;
 
+    if (!migration->event_save_iterate_started) {
+        trace_vfio_save_iterate_start(vbasedev->name);
+        migration->event_save_iterate_started = true;
+    }
+
     data_size = vfio_save_block(f, migration);
     if (data_size < 0) {
         return data_size;
@@ -630,6 +645,8 @@ static int vfio_save_complete_precopy(QEMUFile *f, void *opaque)
     int ret;
     Error *local_err = NULL;
 
+    trace_vfio_save_complete_precopy_start(vbasedev->name);
+
     /* We reach here with device state STOP or STOP_COPY only */
     ret = vfio_migration_set_state(vbasedev, VFIO_DEVICE_STATE_STOP_COPY,
                                    VFIO_DEVICE_STATE_STOP, &local_err);
diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events
index 29789e8d27..cab1cf1de0 100644
--- a/hw/vfio/trace-events
+++ b/hw/vfio/trace-events
@@ -157,10 +157,13 @@ vfio_migration_set_device_state(const char *name, const char *state) " (%s) stat
 vfio_migration_set_state(const char *name, const char *new_state, const char *recover_state) " (%s) new state %s, recover state %s"
 vfio_migration_state_notifier(const char *name, int state) " (%s) state %d"
 vfio_save_block(const char *name, int data_size) " (%s) data_size %d"
+vfio_save_block_precopy_empty_hit(const char *name) " (%s)"
 vfio_save_cleanup(const char *name) " (%s)"
 vfio_save_complete_precopy(const char *name, int ret) " (%s) ret %d"
+vfio_save_complete_precopy_start(const char *name) " (%s)"
 vfio_save_device_config_state(const char *name) " (%s)"
 vfio_save_iterate(const char *name, uint64_t precopy_init_size, uint64_t precopy_dirty_size) " (%s) precopy initial size %"PRIu64" precopy dirty size %"PRIu64
+vfio_save_iterate_start(const char *name) " (%s)"
 vfio_save_setup(const char *name, uint64_t data_buffer_size) " (%s) data buffer size %"PRIu64
 vfio_state_pending_estimate(const char *name, uint64_t precopy, uint64_t postcopy, uint64_t precopy_init_size, uint64_t precopy_dirty_size) " (%s) precopy %"PRIu64" postcopy %"PRIu64" precopy initial size %"PRIu64" precopy dirty size %"PRIu64
 vfio_state_pending_exact(const char *name, uint64_t precopy, uint64_t postcopy, uint64_t stopcopy_size, uint64_t precopy_init_size, uint64_t precopy_dirty_size) " (%s) precopy %"PRIu64" postcopy %"PRIu64" stopcopy size %"PRIu64" precopy initial size %"PRIu64" precopy dirty size %"PRIu64
diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c
index 00561daa06..f170f0b25b 100644
--- a/hw/virtio/vhost-user.c
+++ b/hw/virtio/vhost-user.c
@@ -1185,9 +1185,16 @@ static int vhost_user_set_vring_num(struct vhost_dev *dev,
 
 static void vhost_user_host_notifier_free(VhostUserHostNotifier *n)
 {
-    assert(n && n->unmap_addr);
-    munmap(n->unmap_addr, qemu_real_host_page_size());
-    n->unmap_addr = NULL;
+    if (n->unmap_addr) {
+        munmap(n->unmap_addr, qemu_real_host_page_size());
+        n->unmap_addr = NULL;
+    }
+    if (n->destroy) {
+        memory_region_transaction_begin();
+        object_unparent(OBJECT(&n->mr));
+        memory_region_transaction_commit();
+        g_free(n);
+    }
 }
 
 /*
@@ -1195,17 +1202,28 @@ static void vhost_user_host_notifier_free(VhostUserHostNotifier *n)
  * under rcu.
  */
 static void vhost_user_host_notifier_remove(VhostUserHostNotifier *n,
-                                            VirtIODevice *vdev)
+                                            VirtIODevice *vdev, bool destroy)
 {
+    /*
+     * if destroy == false and n->addr == NULL, we have nothing to do.
+     * so, just return.
+     */
+    if (!n || (!destroy && !n->addr)) {
+        return;
+    }
+
     if (n->addr) {
         if (vdev) {
+            memory_region_transaction_begin();
             virtio_queue_set_host_notifier_mr(vdev, n->idx, &n->mr, false);
+            memory_region_transaction_commit();
         }
         assert(!n->unmap_addr);
         n->unmap_addr = n->addr;
         n->addr = NULL;
-        call_rcu(n, vhost_user_host_notifier_free, rcu);
     }
+    n->destroy = destroy;
+    call_rcu(n, vhost_user_host_notifier_free, rcu);
 }
 
 static int vhost_user_set_vring_base(struct vhost_dev *dev,
@@ -1279,9 +1297,7 @@ static int vhost_user_get_vring_base(struct vhost_dev *dev,
     struct vhost_user *u = dev->opaque;
 
     VhostUserHostNotifier *n = fetch_notifier(u->user, ring->index);
-    if (n) {
-        vhost_user_host_notifier_remove(n, dev->vdev);
-    }
+    vhost_user_host_notifier_remove(n, dev->vdev, false);
 
     ret = vhost_user_write(dev, &msg, NULL, 0);
     if (ret < 0) {
@@ -1562,7 +1578,7 @@ static int vhost_user_backend_handle_vring_host_notifier(struct vhost_dev *dev,
      * new mapped address.
      */
     n = fetch_or_create_notifier(user, queue_idx);
-    vhost_user_host_notifier_remove(n, vdev);
+    vhost_user_host_notifier_remove(n, vdev, false);
 
     if (area->u64 & VHOST_USER_VRING_NOFD_MASK) {
         return 0;
@@ -1607,9 +1623,14 @@ vhost_user_backend_handle_shared_object_add(struct vhost_dev *dev,
     QemuUUID uuid;
 
     memcpy(uuid.data, object->uuid, sizeof(object->uuid));
-    return virtio_add_vhost_device(&uuid, dev);
+    return !virtio_add_vhost_device(&uuid, dev);
 }
 
+/*
+ * Handle VHOST_USER_BACKEND_SHARED_OBJECT_REMOVE backend requests.
+ *
+ * Return: 0 on success, 1 on error.
+ */
 static int
 vhost_user_backend_handle_shared_object_remove(struct vhost_dev *dev,
                                                VhostUserShared *object)
@@ -1623,16 +1644,16 @@ vhost_user_backend_handle_shared_object_remove(struct vhost_dev *dev,
         struct vhost_dev *owner = virtio_lookup_vhost_device(&uuid);
         if (dev != owner) {
             /* Not allowed to remove non-owned entries */
-            return 0;
+            return 1;
         }
         break;
     }
     default:
         /* Not allowed to remove non-owned entries */
-        return 0;
+        return 1;
     }
 
-    return virtio_remove_resource(&uuid);
+    return !virtio_remove_resource(&uuid);
 }
 
 static bool vhost_user_send_resp(QIOChannel *ioc, VhostUserHeader *hdr,
@@ -2736,15 +2757,7 @@ static int vhost_user_set_inflight_fd(struct vhost_dev *dev,
 static void vhost_user_state_destroy(gpointer data)
 {
     VhostUserHostNotifier *n = (VhostUserHostNotifier *) data;
-    if (n) {
-        vhost_user_host_notifier_remove(n, NULL);
-        object_unparent(OBJECT(&n->mr));
-        /*
-         * We can't free until vhost_user_host_notifier_remove has
-         * done it's thing so schedule the free with RCU.
-         */
-        g_free_rcu(n, rcu);
-    }
+    vhost_user_host_notifier_remove(n, NULL, true);
 }
 
 bool vhost_user_init(VhostUserState *user, CharBackend *chr, Error **errp)
@@ -2765,9 +2778,7 @@ void vhost_user_cleanup(VhostUserState *user)
     if (!user->chr) {
         return;
     }
-    memory_region_transaction_begin();
     user->notifiers = (GPtrArray *) g_ptr_array_free(user->notifiers, true);
-    memory_region_transaction_commit();
     user->chr = NULL;
 }
 
diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c
index 4d832fe845..5a394821da 100644
--- a/hw/virtio/virtio-pci.c
+++ b/hw/virtio/virtio-pci.c
@@ -2057,6 +2057,8 @@ static void virtio_pci_device_plugged(DeviceState *d, Error **errp)
         if (modern_pio) {
             memory_region_init(&proxy->io_bar, OBJECT(proxy),
                                "virtio-pci-io", 0x4);
+            address_space_init(&proxy->modern_cfg_io_as, &proxy->io_bar,
+                               "virtio-pci-cfg-io-as");
 
             pci_register_bar(&proxy->pci_dev, proxy->modern_io_bar_idx,
                              PCI_BASE_ADDRESS_SPACE_IO, &proxy->io_bar);
@@ -2180,6 +2182,9 @@ static void virtio_pci_realize(PCIDevice *pci_dev, Error **errp)
                        /* PCI BAR regions must be powers of 2 */
                        pow2ceil(proxy->notify.offset + proxy->notify.size));
 
+    address_space_init(&proxy->modern_cfg_mem_as, &proxy->modern_bar,
+                       "virtio-pci-cfg-mem-as");
+
     if (proxy->disable_legacy == ON_OFF_AUTO_AUTO) {
         proxy->disable_legacy = pcie_port ? ON_OFF_AUTO_ON : ON_OFF_AUTO_OFF;
     }
@@ -2269,12 +2274,17 @@ static void virtio_pci_exit(PCIDevice *pci_dev)
     VirtIOPCIProxy *proxy = VIRTIO_PCI(pci_dev);
     bool pcie_port = pci_bus_is_express(pci_get_bus(pci_dev)) &&
                      !pci_bus_is_root(pci_get_bus(pci_dev));
+    bool modern_pio = proxy->flags & VIRTIO_PCI_FLAG_MODERN_PIO_NOTIFY;
 
     msix_uninit_exclusive_bar(pci_dev);
     if (proxy->flags & VIRTIO_PCI_FLAG_AER && pcie_port &&
         pci_is_express(pci_dev)) {
         pcie_aer_exit(pci_dev);
     }
+    address_space_destroy(&proxy->modern_cfg_mem_as);
+    if (modern_pio) {
+        address_space_destroy(&proxy->modern_cfg_io_as);
+    }
 }
 
 static void virtio_pci_reset(DeviceState *qdev)
@@ -2385,6 +2395,14 @@ static void virtio_pci_dc_realize(DeviceState *qdev, Error **errp)
     vpciklass->parent_dc_realize(qdev, errp);
 }
 
+static int virtio_pci_sync_config(DeviceState *dev, Error **errp)
+{
+    VirtIOPCIProxy *proxy = VIRTIO_PCI(dev);
+    VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
+
+    return qdev_sync_config(DEVICE(vdev), errp);
+}
+
 static void virtio_pci_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
@@ -2401,6 +2419,7 @@ static void virtio_pci_class_init(ObjectClass *klass, void *data)
     device_class_set_parent_realize(dc, virtio_pci_dc_realize,
                                     &vpciklass->parent_dc_realize);
     rc->phases.hold = virtio_pci_bus_reset_hold;
+    dc->sync_config = virtio_pci_sync_config;
 }
 
 static const TypeInfo virtio_pci_info = {
diff --git a/hw/watchdog/wdt_imx2.c b/hw/watchdog/wdt_imx2.c
index be63d421da..8162d58afa 100644
--- a/hw/watchdog/wdt_imx2.c
+++ b/hw/watchdog/wdt_imx2.c
@@ -39,7 +39,6 @@ static void imx2_wdt_expired(void *opaque)
 
     /* Perform watchdog action if watchdog is enabled */
     if (s->wcr & IMX2_WDT_WCR_WDE) {
-        s->wrsr = IMX2_WDT_WRSR_TOUT;
         watchdog_perform_action();
     }
 }
diff --git a/include/crypto/hash.h b/include/crypto/hash.h
index 712cac79ee..1868d4a0f7 100644
--- a/include/crypto/hash.h
+++ b/include/crypto/hash.h
@@ -31,6 +31,7 @@
 #define QCRYPTO_HASH_DIGEST_LEN_SHA384    48
 #define QCRYPTO_HASH_DIGEST_LEN_SHA512    64
 #define QCRYPTO_HASH_DIGEST_LEN_RIPEMD160 20
+#define QCRYPTO_HASH_DIGEST_LEN_SM3       32
 
 /* See also "QCryptoHashAlgo" defined in qapi/crypto.json */
 
diff --git a/include/disas/capstone.h b/include/disas/capstone.h
index a11985151d..c43033f7f6 100644
--- a/include/disas/capstone.h
+++ b/include/disas/capstone.h
@@ -4,6 +4,7 @@
 #ifdef CONFIG_CAPSTONE
 
 #define CAPSTONE_AARCH64_COMPAT_HEADER
+#define CAPSTONE_SYSTEMZ_COMPAT_HEADER
 #include <capstone.h>
 
 #else
diff --git a/include/exec/memory.h b/include/exec/memory.h
index e5e865d1a9..9458e2801d 100644
--- a/include/exec/memory.h
+++ b/include/exec/memory.h
@@ -1104,7 +1104,14 @@ struct AddressSpace {
     QTAILQ_HEAD(, MemoryListener) listeners;
     QTAILQ_ENTRY(AddressSpace) address_spaces_link;
 
-    /* Maximum DMA bounce buffer size used for indirect memory map requests */
+    /*
+     * Maximum DMA bounce buffer size used for indirect memory map requests.
+     * This limits the total size of bounce buffer allocations made for
+     * DMA requests to indirect memory regions within this AddressSpace. DMA
+     * requests that exceed the limit (e.g. due to overly large requested size
+     * or concurrent DMA requests having claimed too much buffer space) will be
+     * rejected and left to the caller to handle.
+     */
     size_t max_bounce_buffer_size;
     /* Total size of bounce buffers currently allocated, atomically accessed */
     size_t bounce_buffer_size;
diff --git a/include/fpu/softfloat-helpers.h b/include/fpu/softfloat-helpers.h
index 94cbe073ec..453188de70 100644
--- a/include/fpu/softfloat-helpers.h
+++ b/include/fpu/softfloat-helpers.h
@@ -75,6 +75,12 @@ static inline void set_floatx80_rounding_precision(FloatX80RoundPrec val,
     status->floatx80_rounding_precision = val;
 }
 
+static inline void set_float_2nan_prop_rule(Float2NaNPropRule rule,
+                                            float_status *status)
+{
+    status->float_2nan_prop_rule = rule;
+}
+
 static inline void set_flush_to_zero(bool val, float_status *status)
 {
     status->flush_to_zero = val;
@@ -126,6 +132,11 @@ get_floatx80_rounding_precision(float_status *status)
     return status->floatx80_rounding_precision;
 }
 
+static inline Float2NaNPropRule get_float_2nan_prop_rule(float_status *status)
+{
+    return status->float_2nan_prop_rule;
+}
+
 static inline bool get_flush_to_zero(float_status *status)
 {
     return status->flush_to_zero;
diff --git a/include/fpu/softfloat-types.h b/include/fpu/softfloat-types.h
index 0884ec4ef7..8f39691dfd 100644
--- a/include/fpu/softfloat-types.h
+++ b/include/fpu/softfloat-types.h
@@ -171,6 +171,43 @@ typedef enum __attribute__((__packed__)) {
 } FloatX80RoundPrec;
 
 /*
+ * 2-input NaN propagation rule. Individual architectures have
+ * different rules for which input NaN is propagated to the output
+ * when there is more than one NaN on the input.
+ *
+ * If default_nan_mode is enabled then it is valid not to set a
+ * NaN propagation rule, because the softfloat code guarantees
+ * not to try to pick a NaN to propagate in default NaN mode.
+ * When not in default-NaN mode, it is an error for the target
+ * not to set the rule in float_status, and we will assert if
+ * we need to handle an input NaN and no rule was selected.
+ */
+typedef enum __attribute__((__packed__)) {
+    /* No propagation rule specified */
+    float_2nan_prop_none = 0,
+    /* Prefer SNaN over QNaN, then operand A over B */
+    float_2nan_prop_s_ab,
+    /* Prefer SNaN over QNaN, then operand B over A */
+    float_2nan_prop_s_ba,
+    /* Prefer A over B regardless of SNaN vs QNaN */
+    float_2nan_prop_ab,
+    /* Prefer B over A regardless of SNaN vs QNaN */
+    float_2nan_prop_ba,
+    /*
+     * This implements x87 NaN propagation rules:
+     * SNaN + QNaN => return the QNaN
+     * two SNaNs => return the one with the larger significand, silenced
+     * two QNaNs => return the one with the larger significand
+     * SNaN and a non-NaN => return the SNaN, silenced
+     * QNaN and a non-NaN => return the QNaN
+     *
+     * If we get down to comparing significands and they are the same,
+     * return the NaN with the positive sign bit (if any).
+     */
+    float_2nan_prop_x87,
+} Float2NaNPropRule;
+
+/*
  * Floating Point Status. Individual architectures may maintain
  * several versions of float_status for different functions. The
  * correct status for the operation is then passed by reference to
@@ -181,6 +218,7 @@ typedef struct float_status {
     uint16_t float_exception_flags;
     FloatRoundMode float_rounding_mode;
     FloatX80RoundPrec floatx80_rounding_precision;
+    Float2NaNPropRule float_2nan_prop_rule;
     bool tininess_before_rounding;
     /* should denormalised results go to zero and set the inexact flag? */
     bool flush_to_zero;
diff --git a/include/hw/acpi/acpi_generic_initiator.h b/include/hw/acpi/acpi_generic_initiator.h
deleted file mode 100644
index a304bad73e..0000000000
--- a/include/hw/acpi/acpi_generic_initiator.h
+++ /dev/null
@@ -1,47 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Copyright (c) 2024, NVIDIA CORPORATION & AFFILIATES. All rights reserved
- */
-
-#ifndef ACPI_GENERIC_INITIATOR_H
-#define ACPI_GENERIC_INITIATOR_H
-
-#include "qom/object_interfaces.h"
-
-#define TYPE_ACPI_GENERIC_INITIATOR "acpi-generic-initiator"
-
-typedef struct AcpiGenericInitiator {
-    /* private */
-    Object parent;
-
-    /* public */
-    char *pci_dev;
-    uint16_t node;
-} AcpiGenericInitiator;
-
-/*
- * ACPI 6.3:
- * Table 5-81 Flags – Generic Initiator Affinity Structure
- */
-typedef enum {
-    /*
-     * If clear, the OSPM ignores the contents of the Generic
-     * Initiator/Port Affinity Structure. This allows system firmware
-     * to populate the SRAT with a static number of structures, but only
-     * enable them as necessary.
-     */
-    GEN_AFFINITY_ENABLED = (1 << 0),
-} GenericAffinityFlags;
-
-/*
- * ACPI 6.3:
- * Table 5-80 Device Handle - PCI
- */
-typedef struct PCIDeviceHandle {
-    uint16_t segment;
-    uint16_t bdf;
-} PCIDeviceHandle;
-
-void build_srat_generic_pci_initiator(GArray *table_data);
-
-#endif
diff --git a/include/hw/acpi/aml-build.h b/include/hw/acpi/aml-build.h
index a3784155cb..4fd5da49e7 100644
--- a/include/hw/acpi/aml-build.h
+++ b/include/hw/acpi/aml-build.h
@@ -486,6 +486,13 @@ Aml *build_crs(PCIHostState *host, CrsRangeSet *range_set, uint32_t io_offset,
 void build_srat_memory(GArray *table_data, uint64_t base,
                        uint64_t len, int node, MemoryAffinityFlags flags);
 
+void build_srat_pci_generic_initiator(GArray *table_data, uint32_t node,
+                                      uint16_t segment, uint8_t bus,
+                                      uint8_t devfn);
+
+void build_srat_acpi_generic_port(GArray *table_data, uint32_t node,
+                                  const char *hid, uint32_t uid);
+
 void build_slit(GArray *table_data, BIOSLinker *linker, MachineState *ms,
                 const char *oem_id, const char *oem_table_id);
 
diff --git a/include/hw/acpi/pci.h b/include/hw/acpi/pci.h
index 467a99461c..6359d574fd 100644
--- a/include/hw/acpi/pci.h
+++ b/include/hw/acpi/pci.h
@@ -40,4 +40,7 @@ Aml *aml_pci_device_dsm(void);
 
 void build_append_pci_bus_devices(Aml *parent_scope, PCIBus *bus);
 void build_pci_bridge_aml(AcpiDevAmlIf *adev, Aml *scope);
+
+void build_srat_generic_affinity_structures(GArray *table_data);
+
 #endif
diff --git a/include/hw/core/cpu.h b/include/hw/core/cpu.h
index c3ca0babcb..db8a6fbc6e 100644
--- a/include/hw/core/cpu.h
+++ b/include/hw/core/cpu.h
@@ -158,6 +158,8 @@ struct CPUClass {
     void (*dump_state)(CPUState *cpu, FILE *, int flags);
     void (*query_cpu_fast)(CPUState *cpu, CpuInfoFast *value);
     int64_t (*get_arch_id)(CPUState *cpu);
+    bool (*cpu_persistent_status)(CPUState *cpu);
+    bool (*cpu_enabled_status)(CPUState *cpu);
     void (*set_pc)(CPUState *cpu, vaddr value);
     vaddr (*get_pc)(CPUState *cpu);
     int (*gdb_read_register)(CPUState *cpu, GByteArray *buf, int reg);
diff --git a/include/hw/cxl/cxl_device.h b/include/hw/cxl/cxl_device.h
index fdd0f4e62b..561b375dc8 100644
--- a/include/hw/cxl/cxl_device.h
+++ b/include/hw/cxl/cxl_device.h
@@ -463,18 +463,6 @@ typedef struct CXLMemPatrolScrubWriteAttrs {
 #define CXL_MEMDEV_PS_ENABLE_DEFAULT    0
 
 /* CXL memory device DDR5 ECS control attributes */
-typedef struct CXLMemECSReadAttrs {
-        uint8_t ecs_log_cap;
-        uint8_t ecs_cap;
-        uint16_t ecs_config;
-        uint8_t ecs_flags;
-} QEMU_PACKED CXLMemECSReadAttrs;
-
-typedef struct CXLMemECSWriteAttrs {
-   uint8_t ecs_log_cap;
-    uint16_t ecs_config;
-} QEMU_PACKED CXLMemECSWriteAttrs;
-
 #define CXL_ECS_GET_FEATURE_VERSION    0x01
 #define CXL_ECS_SET_FEATURE_VERSION    0x01
 #define CXL_ECS_LOG_ENTRY_TYPE_DEFAULT    0x01
@@ -483,6 +471,26 @@ typedef struct CXLMemECSWriteAttrs {
 #define CXL_ECS_MODE_DEFAULT    0
 #define CXL_ECS_NUM_MEDIA_FRUS   3 /* Default */
 
+typedef struct CXLMemECSFRUReadAttrs {
+    uint8_t ecs_cap;
+    uint16_t ecs_config;
+    uint8_t ecs_flags;
+} QEMU_PACKED CXLMemECSFRUReadAttrs;
+
+typedef struct CXLMemECSReadAttrs {
+    uint8_t ecs_log_cap;
+    CXLMemECSFRUReadAttrs fru_attrs[CXL_ECS_NUM_MEDIA_FRUS];
+} QEMU_PACKED CXLMemECSReadAttrs;
+
+typedef struct CXLMemECSFRUWriteAttrs {
+    uint16_t ecs_config;
+} QEMU_PACKED CXLMemECSFRUWriteAttrs;
+
+typedef struct CXLMemECSWriteAttrs {
+    uint8_t ecs_log_cap;
+    CXLMemECSFRUWriteAttrs fru_attrs[CXL_ECS_NUM_MEDIA_FRUS];
+} QEMU_PACKED CXLMemECSWriteAttrs;
+
 #define DCD_MAX_NUM_REGION 8
 
 typedef struct CXLDCExtentRaw {
@@ -549,6 +557,10 @@ struct CXLType3Dev {
     CXLCCI vdm_fm_owned_ld_mctp_cci;
     CXLCCI ld0_cci;
 
+    /* PCIe link characteristics */
+    PCIExpLinkSpeed speed;
+    PCIExpLinkWidth width;
+
     /* DOE */
     DOECap doe_cdat;
 
@@ -571,8 +583,8 @@ struct CXLType3Dev {
     CXLMemPatrolScrubReadAttrs patrol_scrub_attrs;
     CXLMemPatrolScrubWriteAttrs patrol_scrub_wr_attrs;
     /* ECS control attributes */
-    CXLMemECSReadAttrs ecs_attrs[CXL_ECS_NUM_MEDIA_FRUS];
-    CXLMemECSWriteAttrs ecs_wr_attrs[CXL_ECS_NUM_MEDIA_FRUS];
+    CXLMemECSReadAttrs ecs_attrs;
+    CXLMemECSWriteAttrs ecs_wr_attrs;
 
     struct dynamic_capacity {
         HostMemoryBackend *host_dc;
diff --git a/include/hw/i386/intel_iommu.h b/include/hw/i386/intel_iommu.h
index 1eb05c29fc..d372cd396b 100644
--- a/include/hw/i386/intel_iommu.h
+++ b/include/hw/i386/intel_iommu.h
@@ -306,6 +306,9 @@ struct IntelIOMMUState {
     bool dma_translation;           /* Whether DMA translation supported */
     bool pasid;                     /* Whether to support PASID */
 
+    /* Transient Mapping, Reserved(0) since VTD spec revision 3.2 */
+    bool stale_tm;
+
     /*
      * Protects IOMMU states in general.  Currently it protects the
      * per-IOMMU IOTLB cache, and context entry cache in VTDAddressSpace.
diff --git a/include/hw/pci-bridge/cxl_upstream_port.h b/include/hw/pci-bridge/cxl_upstream_port.h
index 12635139f6..f208397ffe 100644
--- a/include/hw/pci-bridge/cxl_upstream_port.h
+++ b/include/hw/pci-bridge/cxl_upstream_port.h
@@ -12,6 +12,10 @@ typedef struct CXLUpstreamPort {
     /*< public >*/
     CXLComponentState cxl_cstate;
     CXLCCI swcci;
+
+    PCIExpLinkSpeed speed;
+    PCIExpLinkWidth width;
+
     DOECap doe_cdat;
     uint64_t sn;
 } CXLUpstreamPort;
diff --git a/include/hw/pci/pci.h b/include/hw/pci/pci.h
index 35d4fe0bbf..135695c551 100644
--- a/include/hw/pci/pci.h
+++ b/include/hw/pci/pci.h
@@ -16,7 +16,7 @@ extern bool pci_available;
 #define PCI_BUS_NUM(x)          (((x) >> 8) & 0xff)
 #define PCI_SLOT(devfn)         (((devfn) >> 3) & 0x1f)
 #define PCI_FUNC(devfn)         ((devfn) & 0x07)
-#define PCI_BUILD_BDF(bus, devfn)     ((bus << 8) | (devfn))
+#define PCI_BUILD_BDF(bus, devfn)     (((bus) << 8) | (devfn))
 #define PCI_BDF_TO_DEVFN(x)     ((x) & 0xff)
 #define PCI_BUS_MAX             256
 #define PCI_DEVFN_MAX           256
@@ -214,6 +214,8 @@ enum {
     QEMU_PCIE_ERR_UNC_MASK = (1 << QEMU_PCIE_ERR_UNC_MASK_BITNR),
 #define QEMU_PCIE_ARI_NEXTFN_1_BITNR 12
     QEMU_PCIE_ARI_NEXTFN_1 = (1 << QEMU_PCIE_ARI_NEXTFN_1_BITNR),
+#define QEMU_PCIE_EXT_TAG_BITNR 13
+    QEMU_PCIE_EXT_TAG = (1 << QEMU_PCIE_EXT_TAG_BITNR),
 };
 
 typedef struct PCIINTxRoute {
diff --git a/include/hw/pci/pci_bridge.h b/include/hw/pci/pci_bridge.h
index 5cd452115a..b0f5204d80 100644
--- a/include/hw/pci/pci_bridge.h
+++ b/include/hw/pci/pci_bridge.h
@@ -72,6 +72,8 @@ struct PCIBridge {
      */
     MemoryRegion address_space_mem;
     MemoryRegion address_space_io;
+    AddressSpace as_mem;
+    AddressSpace as_io;
 
     PCIBridgeWindows windows;
 
@@ -102,6 +104,7 @@ typedef struct PXBPCIEDev {
     PXBDev parent_obj;
 } PXBPCIEDev;
 
+#define TYPE_PXB_CXL_BUS "pxb-cxl-bus"
 #define TYPE_PXB_DEV "pxb"
 OBJECT_DECLARE_SIMPLE_TYPE(PXBDev, PXB_DEV)
 
diff --git a/include/hw/pci/pci_device.h b/include/hw/pci/pci_device.h
index 91df40f989..8eaf0d58bb 100644
--- a/include/hw/pci/pci_device.h
+++ b/include/hw/pci/pci_device.h
@@ -168,7 +168,11 @@ struct PCIDevice {
     char *failover_pair_id;
     uint32_t acpi_index;
 
-    /* Maximum DMA bounce buffer size used for indirect memory map requests */
+    /*
+     * Indirect DMA region bounce buffer size as configured for the device. This
+     * is a configuration parameter that is reflected into bus_master_as when
+     * realizing the device.
+     */
     uint32_t max_bounce_buffer_size;
 };
 
diff --git a/include/hw/pci/pcie.h b/include/hw/pci/pcie.h
index 5eddb90976..b8d59732bc 100644
--- a/include/hw/pci/pcie.h
+++ b/include/hw/pci/pcie.h
@@ -141,6 +141,8 @@ void pcie_acs_reset(PCIDevice *dev);
 void pcie_ari_init(PCIDevice *dev, uint16_t offset);
 void pcie_dev_ser_num_init(PCIDevice *dev, uint16_t offset, uint64_t ser_num);
 void pcie_ats_init(PCIDevice *dev, uint16_t offset, bool aligned);
+void pcie_cap_fill_link_ep_usp(PCIDevice *dev, PCIExpLinkWidth width,
+                               PCIExpLinkSpeed speed);
 
 void pcie_cap_slot_pre_plug_cb(HotplugHandler *hotplug_dev, DeviceState *dev,
                                Error **errp);
diff --git a/include/hw/qdev-core.h b/include/hw/qdev-core.h
index aa97c34a4b..94914858d8 100644
--- a/include/hw/qdev-core.h
+++ b/include/hw/qdev-core.h
@@ -95,6 +95,7 @@ typedef void (*DeviceUnrealize)(DeviceState *dev);
 typedef void (*DeviceReset)(DeviceState *dev);
 typedef void (*BusRealize)(BusState *bus, Error **errp);
 typedef void (*BusUnrealize)(BusState *bus);
+typedef int (*DeviceSyncConfig)(DeviceState *dev, Error **errp);
 
 /**
  * struct DeviceClass - The base class for all devices.
@@ -103,6 +104,9 @@ typedef void (*BusUnrealize)(BusState *bus);
  * property is changed to %true.
  * @unrealize: Callback function invoked when the #DeviceState:realized
  * property is changed to %false.
+ * @sync_config: Callback function invoked when QMP command device-sync-config
+ * is called. Should synchronize device configuration from host to guest part
+ * and notify the guest about the change.
  * @hotpluggable: indicates if #DeviceClass is hotpluggable, available
  * as readonly "hotpluggable" property of #DeviceState instance
  *
@@ -162,6 +166,7 @@ struct DeviceClass {
     DeviceReset legacy_reset;
     DeviceRealize realize;
     DeviceUnrealize unrealize;
+    DeviceSyncConfig sync_config;
 
     /**
      * @vmsd: device state serialisation description for
@@ -547,6 +552,7 @@ bool qdev_hotplug_allowed(DeviceState *dev, Error **errp);
  */
 HotplugHandler *qdev_get_hotplug_handler(DeviceState *dev);
 void qdev_unplug(DeviceState *dev, Error **errp);
+int qdev_sync_config(DeviceState *dev, Error **errp);
 void qdev_simple_device_unplug_cb(HotplugHandler *hotplug_dev,
                                   DeviceState *dev, Error **errp);
 void qdev_machine_creation_done(void);
diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
index fed499b199..e0ce6ec3a9 100644
--- a/include/hw/vfio/vfio-common.h
+++ b/include/hw/vfio/vfio-common.h
@@ -73,6 +73,9 @@ typedef struct VFIOMigration {
     uint64_t precopy_init_size;
     uint64_t precopy_dirty_size;
     bool initial_data_sent;
+
+    bool event_save_iterate_started;
+    bool event_precopy_empty_hit;
 } VFIOMigration;
 
 struct VFIOGroup;
diff --git a/include/hw/virtio/vhost-user.h b/include/hw/virtio/vhost-user.h
index 324cd8663a..9a3f238b43 100644
--- a/include/hw/virtio/vhost-user.h
+++ b/include/hw/virtio/vhost-user.h
@@ -54,6 +54,7 @@ typedef struct VhostUserHostNotifier {
     void *addr;
     void *unmap_addr;
     int idx;
+    bool destroy;
 } VhostUserHostNotifier;
 
 /**
diff --git a/include/hw/virtio/virtio-pci.h b/include/hw/virtio/virtio-pci.h
index 9e67ba38c7..971c5fabd4 100644
--- a/include/hw/virtio/virtio-pci.h
+++ b/include/hw/virtio/virtio-pci.h
@@ -147,6 +147,9 @@ struct VirtIOPCIProxy {
     };
     MemoryRegion modern_bar;
     MemoryRegion io_bar;
+    /* address space for VirtIOPCIRegions */
+    AddressSpace modern_cfg_mem_as;
+    AddressSpace modern_cfg_io_as;
     uint32_t legacy_io_bar_idx;
     uint32_t msix_bar_idx;
     uint32_t modern_io_bar_idx;
diff --git a/linux-user/arm/nwfpe/fpa11.c b/linux-user/arm/nwfpe/fpa11.c
index 9a93610d24..8356beb52c 100644
--- a/linux-user/arm/nwfpe/fpa11.c
+++ b/linux-user/arm/nwfpe/fpa11.c
@@ -51,6 +51,24 @@ void resetFPA11(void)
 #ifdef MAINTAIN_FPCR
   fpa11->fpcr = MASK_RESET;
 #endif
+
+  /*
+   * Real FPA11 hardware does not handle NaNs, but always takes an
+   * exception for them to be software-emulated (ARM7500FE datasheet
+   * section 10.4). There is no documented architectural requirement
+   * for NaN propagation rules and it will depend on how the OS
+   * level software emulation opted to do it. We here use prop_s_ab
+   * which matches the later VFP hardware choice and how QEMU's
+   * fpa11 emulation has worked in the past. The real Linux kernel
+   * does something slightly different: arch/arm/nwfpe/softfloat-specialize
+   * propagateFloat64NaN() has the curious behaviour that it prefers
+   * the QNaN over the SNaN, but if both are QNaN it picks A and
+   * if both are SNaN it picks B. In theory we could add this as
+   * a NaN propagation rule, but in practice FPA11 emulation is so
+   * close to totally dead that it's not worth trying to match it at
+   * this late date.
+   */
+  set_float_2nan_prop_rule(float_2nan_prop_s_ab, &fpa11->fp_status);
 }
 
 void SetRoundingMode(const unsigned int opcode)
diff --git a/linux-user/gen-vdso-elfn.c.inc b/linux-user/gen-vdso-elfn.c.inc
index 95856eb839..b47019e136 100644
--- a/linux-user/gen-vdso-elfn.c.inc
+++ b/linux-user/gen-vdso-elfn.c.inc
@@ -68,28 +68,45 @@ static void elfN(search_symtab)(ElfN(Shdr) *shdr, unsigned sym_idx,
                                 void *buf, bool need_bswap)
 {
     unsigned str_idx = shdr[sym_idx].sh_link;
-    ElfN(Sym) *sym = buf + shdr[sym_idx].sh_offset;
-    unsigned sym_n = shdr[sym_idx].sh_size / sizeof(*sym);
+    ElfN(Sym) *target_sym = buf + shdr[sym_idx].sh_offset;
+    unsigned sym_n = shdr[sym_idx].sh_size / sizeof(*target_sym);
     const char *str = buf + shdr[str_idx].sh_offset;
 
     for (unsigned i = 0; i < sym_n; ++i) {
         const char *name;
+        ElfN(Sym) sym;
 
+        memcpy(&sym, &target_sym[i], sizeof(sym));
         if (need_bswap) {
-            elfN(bswap_sym)(sym + i);
+            elfN(bswap_sym)(&sym);
         }
-        name = str + sym[i].st_name;
+        name = str + sym.st_name;
 
         if (sigreturn_sym && strcmp(sigreturn_sym, name) == 0) {
-            sigreturn_addr = sym[i].st_value;
+            sigreturn_addr = sym.st_value;
         }
         if (rt_sigreturn_sym && strcmp(rt_sigreturn_sym, name) == 0) {
-            rt_sigreturn_addr = sym[i].st_value;
+            rt_sigreturn_addr = sym.st_value;
         }
     }
 }
 
-static void elfN(process)(FILE *outf, void *buf, bool need_bswap)
+static void elfN(bswap_ps_hdrs)(ElfN(Ehdr) *ehdr)
+{
+    ElfN(Phdr) *phdr = (void *)ehdr + ehdr->e_phoff;
+    ElfN(Shdr) *shdr = (void *)ehdr + ehdr->e_shoff;
+    ElfN(Half) i;
+
+    for (i = 0; i < ehdr->e_phnum; ++i) {
+        elfN(bswap_phdr)(&phdr[i]);
+    }
+
+    for (i = 0; i < ehdr->e_shnum; ++i) {
+        elfN(bswap_shdr)(&shdr[i]);
+    }
+}
+
+static void elfN(process)(FILE *outf, void *buf, long len, bool need_bswap)
 {
     ElfN(Ehdr) *ehdr = buf;
     ElfN(Phdr) *phdr;
@@ -103,24 +120,14 @@ static void elfN(process)(FILE *outf, void *buf, bool need_bswap)
     int errors = 0;
 
     if (need_bswap) {
-        elfN(bswap_ehdr)(ehdr);
+        elfN(bswap_ehdr)(buf);
+        elfN(bswap_ps_hdrs)(buf);
     }
 
     phnum = ehdr->e_phnum;
     phdr = buf + ehdr->e_phoff;
-    if (need_bswap) {
-        for (unsigned i = 0; i < phnum; ++i) {
-            elfN(bswap_phdr)(phdr + i);
-        }
-    }
-
     shnum = ehdr->e_shnum;
     shdr = buf + ehdr->e_shoff;
-    if (need_bswap) {
-        for (unsigned i = 0; i < shnum; ++i) {
-            elfN(bswap_shdr)(shdr + i);
-        }
-    }
     for (unsigned i = 0; i < shnum; ++i) {
         switch (shdr[i].sh_type) {
         case SHT_SYMTAB:
@@ -154,7 +161,24 @@ static void elfN(process)(FILE *outf, void *buf, bool need_bswap)
             fprintf(stderr, "LOAD segment not loaded at address 0\n");
             errors++;
         }
-        first_segsz = phdr[i].p_filesz;
+        /*
+         * Extend the program header to cover the entire VDSO, so that
+         * load_elf_vdso() loads everything, including section headers.
+         *
+         * Require that there is no .bss, since it would break this
+         * approach.
+         */
+        if (phdr[i].p_filesz != phdr[i].p_memsz) {
+            fprintf(stderr, "LOAD segment's filesz and memsz differ\n");
+            errors++;
+        }
+        if (phdr[i].p_filesz > len) {
+            fprintf(stderr, "LOAD segment is larger than the whole VDSO\n");
+            errors++;
+        }
+        phdr[i].p_filesz = len;
+        phdr[i].p_memsz = len;
+        first_segsz = len;
         if (first_segsz < ehdr->e_phoff + phnum * sizeof(*phdr)) {
             fprintf(stderr, "LOAD segment does not cover PHDRs\n");
             errors++;
@@ -197,17 +221,24 @@ static void elfN(process)(FILE *outf, void *buf, bool need_bswap)
         output_reloc(outf, buf, &phdr[i].p_paddr);
     }
 
+    /* Relocate the section headers. */
+    for (unsigned i = 0; i < shnum; ++i) {
+        output_reloc(outf, buf, &shdr[i].sh_addr);
+    }
+
     /* Relocate the DYNAMIC entries. */
     if (dynamic_addr) {
-        ElfN(Dyn) *dyn = buf + dynamic_ofs;
-        __typeof(dyn->d_tag) tag;
+        ElfN(Dyn) *target_dyn = buf + dynamic_ofs;
+        __typeof(((ElfN(Dyn) *)target_dyn)->d_tag) tag;
 
         do {
+            ElfN(Dyn) dyn;
 
+            memcpy(&dyn, target_dyn, sizeof(dyn));
             if (need_bswap) {
-                elfN(bswap_dyn)(dyn);
+                elfN(bswap_dyn)(&dyn);
             }
-            tag = dyn->d_tag;
+            tag = dyn.d_tag;
 
             switch (tag) {
             case DT_HASH:
@@ -218,7 +249,7 @@ static void elfN(process)(FILE *outf, void *buf, bool need_bswap)
             case DT_PLTGOT:
             case DT_ADDRRNGLO ... DT_ADDRRNGHI:
                 /* These entries store an address in the entry. */
-                output_reloc(outf, buf, &dyn->d_un.d_val);
+                output_reloc(outf, buf, &target_dyn->d_un.d_val);
                 break;
 
             case DT_NULL:
@@ -235,7 +266,7 @@ static void elfN(process)(FILE *outf, void *buf, bool need_bswap)
                 break;
 
             case DT_SYMENT:
-                if (dyn->d_un.d_val != sizeof(ElfN(Sym))) {
+                if (dyn.d_un.d_val != sizeof(ElfN(Sym))) {
                     fprintf(stderr, "VDSO has incorrect dynamic symbol size\n");
                     errors++;
                 }
@@ -251,7 +282,7 @@ static void elfN(process)(FILE *outf, void *buf, bool need_bswap)
                  * ??? The RISC-V toolchain will emit these even when there
                  * are no relocations.  Validate zeros.
                  */
-                if (dyn->d_un.d_val != 0) {
+                if (dyn.d_un.d_val != 0) {
                     fprintf(stderr, "VDSO has dynamic relocations\n");
                     errors++;
                 }
@@ -287,7 +318,7 @@ static void elfN(process)(FILE *outf, void *buf, bool need_bswap)
                 errors++;
                 break;
             }
-            dyn++;
+            target_dyn++;
         } while (tag != DT_NULL);
         if (errors) {
             exit(EXIT_FAILURE);
@@ -296,11 +327,11 @@ static void elfN(process)(FILE *outf, void *buf, bool need_bswap)
 
     /* Relocate the dynamic symbol table. */
     if (dynsym_idx) {
-        ElfN(Sym) *sym = buf + shdr[dynsym_idx].sh_offset;
-        unsigned sym_n = shdr[dynsym_idx].sh_size / sizeof(*sym);
+        ElfN(Sym) *target_sym = buf + shdr[dynsym_idx].sh_offset;
+        unsigned sym_n = shdr[dynsym_idx].sh_size / sizeof(*target_sym);
 
         for (unsigned i = 0; i < sym_n; ++i) {
-            output_reloc(outf, buf, &sym[i].st_value);
+            output_reloc(outf, buf, &target_sym[i].st_value);
         }
     }
 
@@ -311,4 +342,9 @@ static void elfN(process)(FILE *outf, void *buf, bool need_bswap)
     if (symtab_idx) {
         elfN(search_symtab)(shdr, symtab_idx, buf, need_bswap);
     }
+
+    if (need_bswap) {
+        elfN(bswap_ps_hdrs)(buf);
+        elfN(bswap_ehdr)(buf);
+    }
 }
diff --git a/linux-user/gen-vdso.c b/linux-user/gen-vdso.c
index 31e333be80..721f38d5a3 100644
--- a/linux-user/gen-vdso.c
+++ b/linux-user/gen-vdso.c
@@ -132,23 +132,6 @@ int main(int argc, char **argv)
     fclose(inf);
 
     /*
-     * Write out the vdso image now, before we make local changes.
-     */
-
-    fprintf(outf,
-            "/* Automatically generated from linux-user/gen-vdso.c. */\n"
-            "\n"
-            "static const uint8_t %s_image[] = {",
-            prefix);
-    for (long i = 0; i < total_len; ++i) {
-        if (i % 12 == 0) {
-            fputs("\n   ", outf);
-        }
-        fprintf(outf, " 0x%02x,", buf[i]);
-    }
-    fprintf(outf, "\n};\n\n");
-
-    /*
      * Identify which elf flavor we're processing.
      * The first 16 bytes of the file are e_ident.
      */
@@ -179,14 +162,17 @@ int main(int argc, char **argv)
      * Output relocation addresses as we go.
      */
 
-    fprintf(outf, "static const unsigned %s_relocs[] = {\n", prefix);
+    fprintf(outf,
+            "/* Automatically generated by linux-user/gen-vdso.c. */\n"
+            "\n"
+            "static const unsigned %s_relocs[] = {\n", prefix);
 
     switch (buf[EI_CLASS]) {
     case ELFCLASS32:
-        elf32_process(outf, buf, need_bswap);
+        elf32_process(outf, buf, total_len, need_bswap);
         break;
     case ELFCLASS64:
-        elf64_process(outf, buf, need_bswap);
+        elf64_process(outf, buf, total_len, need_bswap);
         break;
     default:
         fprintf(stderr, "%s: invalid elf EI_CLASS (%u)\n",
@@ -196,6 +182,20 @@ int main(int argc, char **argv)
 
     fprintf(outf, "};\n\n");   /* end vdso_relocs. */
 
+    /*
+     * Write out the vdso image now, after we made local changes.
+     */
+    fprintf(outf,
+            "static const uint8_t %s_image[] = {",
+            prefix);
+    for (long i = 0; i < total_len; ++i) {
+        if (i % 12 == 0) {
+            fputs("\n   ", outf);
+        }
+        fprintf(outf, " 0x%02x,", buf[i]);
+    }
+    fprintf(outf, "\n};\n\n");
+
     fprintf(outf, "static const VdsoImageInfo %s_image_info = {\n", prefix);
     fprintf(outf, "    .image = %s_image,\n", prefix);
     fprintf(outf, "    .relocs = %s_relocs,\n", prefix);
diff --git a/linux-user/main.c b/linux-user/main.c
index 8143a0d4b0..b09af8d436 100644
--- a/linux-user/main.c
+++ b/linux-user/main.c
@@ -412,6 +412,13 @@ static void handle_arg_reserved_va(const char *arg)
     reserved_va = val ? val - 1 : 0;
 }
 
+static const char *rtsig_map = CONFIG_QEMU_RTSIG_MAP;
+
+static void handle_arg_rtsig_map(const char *arg)
+{
+    rtsig_map = arg;
+}
+
 static void handle_arg_one_insn_per_tb(const char *arg)
 {
     opt_one_insn_per_tb = true;
@@ -494,6 +501,9 @@ static const struct qemu_argument arg_table[] = {
      "address",    "set guest_base address to 'address'"},
     {"R",          "QEMU_RESERVED_VA", true,  handle_arg_reserved_va,
      "size",       "reserve 'size' bytes for guest virtual address space"},
+    {"t",          "QEMU_RTSIG_MAP",   true,  handle_arg_rtsig_map,
+     "tsig hsig n[,...]",
+                   "map target rt signals [tsig,tsig+n) to [hsig,hsig+n]"},
     {"d",          "QEMU_LOG",         true,  handle_arg_log,
      "item[,...]", "enable logging of specified items "
      "(use '-d help' for a list of items)"},
@@ -1002,7 +1012,7 @@ int main(int argc, char **argv, char **envp)
 
     target_set_brk(info->brk);
     syscall_init();
-    signal_init();
+    signal_init(rtsig_map);
 
     /* Now that we've loaded the binary, GUEST_BASE is fixed.  Delay
        generating the prologue until now so that the prologue can take
diff --git a/linux-user/signal-common.h b/linux-user/signal-common.h
index f4cbe6185e..8584d9ecc2 100644
--- a/linux-user/signal-common.h
+++ b/linux-user/signal-common.h
@@ -56,7 +56,7 @@ void setup_rt_frame(int sig, struct target_sigaction *ka,
                     target_sigset_t *set, CPUArchState *env);
 
 void process_pending_signals(CPUArchState *cpu_env);
-void signal_init(void);
+void signal_init(const char *rtsig_map);
 void queue_signal(CPUArchState *env, int sig, int si_type,
                   target_siginfo_t *info);
 void host_to_target_siginfo(target_siginfo_t *tinfo, const siginfo_t *info);
diff --git a/linux-user/signal.c b/linux-user/signal.c
index 63ac2df53b..9b6d772882 100644
--- a/linux-user/signal.c
+++ b/linux-user/signal.c
@@ -18,6 +18,7 @@
  */
 #include "qemu/osdep.h"
 #include "qemu/bitops.h"
+#include "qemu/cutils.h"
 #include "gdbstub/user.h"
 #include "exec/page-protection.h"
 #include "hw/core/tcg-cpu-ops.h"
@@ -513,20 +514,81 @@ static int core_dump_signal(int sig)
     }
 }
 
-static void signal_table_init(void)
+static void signal_table_init(const char *rtsig_map)
 {
     int hsig, tsig, count;
 
+    if (rtsig_map) {
+        /*
+         * Map host RT signals to target RT signals according to the
+         * user-provided specification.
+         */
+        const char *s = rtsig_map;
+
+        while (true) {
+            int i;
+
+            if (qemu_strtoi(s, &s, 10, &tsig) || *s++ != ' ') {
+                fprintf(stderr, "Malformed target signal in QEMU_RTSIG_MAP\n");
+                exit(EXIT_FAILURE);
+            }
+            if (qemu_strtoi(s, &s, 10, &hsig) || *s++ != ' ') {
+                fprintf(stderr, "Malformed host signal in QEMU_RTSIG_MAP\n");
+                exit(EXIT_FAILURE);
+            }
+            if (qemu_strtoi(s, &s, 10, &count) || (*s && *s != ',')) {
+                fprintf(stderr, "Malformed signal count in QEMU_RTSIG_MAP\n");
+                exit(EXIT_FAILURE);
+            }
+
+            for (i = 0; i < count; i++, tsig++, hsig++) {
+                if (tsig < TARGET_SIGRTMIN || tsig > TARGET_NSIG) {
+                    fprintf(stderr, "%d is not a target rt signal\n", tsig);
+                    exit(EXIT_FAILURE);
+                }
+                if (hsig < SIGRTMIN || hsig > SIGRTMAX) {
+                    fprintf(stderr, "%d is not a host rt signal\n", hsig);
+                    exit(EXIT_FAILURE);
+                }
+                if (host_to_target_signal_table[hsig]) {
+                    fprintf(stderr, "%d already maps %d\n",
+                            hsig, host_to_target_signal_table[hsig]);
+                    exit(EXIT_FAILURE);
+                }
+                host_to_target_signal_table[hsig] = tsig;
+            }
+
+            if (*s) {
+                s++;
+            } else {
+                break;
+            }
+        }
+    } else {
+        /*
+         * Default host-to-target RT signal mapping.
+         *
+         * Signals are supported starting from TARGET_SIGRTMIN and going up
+         * until we run out of host realtime signals.  Glibc uses the lower 2
+         * RT signals and (hopefully) nobody uses the upper ones.
+         * This is why SIGRTMIN (34) is generally greater than __SIGRTMIN (32).
+         * To fix this properly we would need to do manual signal delivery
+         * multiplexed over a single host signal.
+         * Attempts for configure "missing" signals via sigaction will be
+         * silently ignored.
+         *
+         * Reserve one signal for internal usage (see below).
+         */
+
+        hsig = SIGRTMIN + 1;
+        for (tsig = TARGET_SIGRTMIN;
+             hsig <= SIGRTMAX && tsig <= TARGET_NSIG;
+             hsig++, tsig++) {
+            host_to_target_signal_table[hsig] = tsig;
+        }
+    }
+
     /*
-     * Signals are supported starting from TARGET_SIGRTMIN and going up
-     * until we run out of host realtime signals.  Glibc uses the lower 2
-     * RT signals and (hopefully) nobody uses the upper ones.
-     * This is why SIGRTMIN (34) is generally greater than __SIGRTMIN (32).
-     * To fix this properly we would need to do manual signal delivery
-     * multiplexed over a single host signal.
-     * Attempts for configure "missing" signals via sigaction will be
-     * silently ignored.
-     *
      * Remap the target SIGABRT, so that we can distinguish host abort
      * from guest abort.  When the guest registers a signal handler or
      * calls raise(SIGABRT), the host will raise SIG_RTn.  If the guest
@@ -536,21 +598,27 @@ static void signal_table_init(void)
      * parent sees the correct mapping from wait status.
      */
 
-    hsig = SIGRTMIN;
     host_to_target_signal_table[SIGABRT] = 0;
-    host_to_target_signal_table[hsig++] = TARGET_SIGABRT;
-
-    for (tsig = TARGET_SIGRTMIN;
-         hsig <= SIGRTMAX && tsig <= TARGET_NSIG;
-         hsig++, tsig++) {
-        host_to_target_signal_table[hsig] = tsig;
+    for (hsig = SIGRTMIN; hsig <= SIGRTMAX; hsig++) {
+        if (!host_to_target_signal_table[hsig]) {
+            host_to_target_signal_table[hsig] = TARGET_SIGABRT;
+            break;
+        }
+    }
+    if (hsig > SIGRTMAX) {
+        fprintf(stderr, "No rt signals left for SIGABRT mapping\n");
+        exit(EXIT_FAILURE);
     }
 
     /* Invert the mapping that has already been assigned. */
     for (hsig = 1; hsig < _NSIG; hsig++) {
         tsig = host_to_target_signal_table[hsig];
         if (tsig) {
-            assert(target_to_host_signal_table[tsig] == 0);
+            if (target_to_host_signal_table[tsig]) {
+                fprintf(stderr, "%d is already mapped to %d\n",
+                        tsig, target_to_host_signal_table[tsig]);
+                exit(EXIT_FAILURE);
+            }
             target_to_host_signal_table[tsig] = hsig;
         }
     }
@@ -573,13 +641,13 @@ static void signal_table_init(void)
     trace_signal_table_init(count);
 }
 
-void signal_init(void)
+void signal_init(const char *rtsig_map)
 {
     TaskState *ts = get_task_state(thread_cpu);
     struct sigaction act, oact;
 
     /* initialize signal conversion tables */
-    signal_table_init();
+    signal_table_init(rtsig_map);
 
     /* Set the signal mask from the host mask. */
     sigprocmask(0, 0, &ts->signal_mask);
diff --git a/meson.build b/meson.build
index c386593c52..34e2bdb0c2 100644
--- a/meson.build
+++ b/meson.build
@@ -1760,6 +1760,7 @@ gcrypt = not_found
 nettle = not_found
 hogweed = not_found
 crypto_sm4 = not_found
+crypto_sm3 = not_found
 xts = 'none'
 
 if get_option('nettle').enabled() and get_option('gcrypt').enabled()
@@ -1795,6 +1796,17 @@ if not gnutls_crypto.found()
       }''', dependencies: gcrypt)
       crypto_sm4 = not_found
     endif
+    crypto_sm3 = gcrypt
+    # SM3 ALG is available in libgcrypt >= 1.9
+    if gcrypt.found() and not cc.links('''
+      #include <gcrypt.h>
+      int main(void) {
+        gcry_md_hd_t handler;
+        gcry_md_open(&handler, GCRY_MD_SM3, 0);
+        return 0;
+      }''', dependencies: gcrypt)
+      crypto_sm3 = not_found
+    endif
   endif
   if (not get_option('nettle').auto() or have_system) and not gcrypt.found()
     nettle = dependency('nettle', version: '>=3.4',
@@ -1815,6 +1827,31 @@ if not gnutls_crypto.found()
       }''', dependencies: nettle)
       crypto_sm4 = not_found
     endif
+    crypto_sm3 = nettle
+    # SM3 ALG is available in nettle >= 3.8
+    if nettle.found() and not cc.links('''
+      #include <nettle/sm3.h>
+      #include <nettle/hmac.h>
+      int main(void) {
+      struct sm3_ctx ctx;
+      struct hmac_sm3_ctx hmac_ctx;
+      unsigned char data[64] = {0};
+      unsigned char output[32];
+
+      // SM3 hash function test
+      sm3_init(&ctx);
+      sm3_update(&ctx, 64, data);
+      sm3_digest(&ctx, 32, data);
+
+      // HMAC-SM3 test
+      hmac_sm3_set_key(&hmac_ctx, 32, data);
+      hmac_sm3_update(&hmac_ctx, 64, data);
+      hmac_sm3_digest(&hmac_ctx, 32, output);
+
+      return 0;
+      }''', dependencies: nettle)
+      crypto_sm3 = not_found
+    endif
   endif
 endif
 
@@ -2462,6 +2499,7 @@ config_host_data.set('CONFIG_TASN1', tasn1.found())
 config_host_data.set('CONFIG_GCRYPT', gcrypt.found())
 config_host_data.set('CONFIG_NETTLE', nettle.found())
 config_host_data.set('CONFIG_CRYPTO_SM4', crypto_sm4.found())
+config_host_data.set('CONFIG_CRYPTO_SM3', crypto_sm3.found())
 config_host_data.set('CONFIG_HOGWEED', hogweed.found())
 config_host_data.set('CONFIG_QEMU_PRIVATE_XTS', xts == 'private')
 config_host_data.set('CONFIG_MALLOC_TRIM', has_malloc_trim)
@@ -3178,7 +3216,8 @@ foreach target : target_dirs
     config_target += {
       'CONFIG_USER_ONLY': 'y',
       'CONFIG_QEMU_INTERP_PREFIX':
-        get_option('interp_prefix').replace('%M', config_target['TARGET_NAME'])
+        get_option('interp_prefix').replace('%M', config_target['TARGET_NAME']),
+      'CONFIG_QEMU_RTSIG_MAP': get_option('rtsig_map'),
     }
   endif
 
@@ -3484,6 +3523,7 @@ if have_system
     'hw/s390x',
     'hw/scsi',
     'hw/sd',
+    'hw/sensor',
     'hw/sh4',
     'hw/sparc',
     'hw/sparc64',
@@ -3690,6 +3730,10 @@ subdir('accel')
 subdir('plugins')
 subdir('ebpf')
 
+if 'CONFIG_TCG' in config_all_accel
+  subdir('contrib/plugins')
+endif
+
 common_user_inc = []
 
 subdir('common-user')
@@ -4590,6 +4634,7 @@ if nettle.found()
    summary_info += {'  XTS':             xts != 'private'}
 endif
 summary_info += {'SM4 ALG support':   crypto_sm4}
+summary_info += {'SM3 ALG support':   crypto_sm3}
 summary_info += {'AF_ALG support':    have_afalg}
 summary_info += {'rng-none':          get_option('rng_none')}
 summary_info += {'Linux keyring':     have_keyring}
diff --git a/meson_options.txt b/meson_options.txt
index 24bf009056..ac4887a622 100644
--- a/meson_options.txt
+++ b/meson_options.txt
@@ -27,6 +27,8 @@ option('block_drv_ro_whitelist', type : 'string', value : '',
        description: 'set block driver read-only whitelist (by default affects only QEMU, not tools like qemu-img)')
 option('interp_prefix', type : 'string', value : '/usr/gnemul/qemu-%M',
        description: 'where to find shared libraries etc., use %M for cpu name')
+option('rtsig_map', type : 'string', value : 'NULL',
+       description: 'default value of QEMU_RTSIG_MAP')
 option('fuzzing_engine', type : 'string', value : '',
        description: 'fuzzing engine library for OSS-Fuzz')
 option('trace_file', type: 'string', value: 'trace',
diff --git a/qapi/crypto.json b/qapi/crypto.json
index 9431522768..c9d967d782 100644
--- a/qapi/crypto.json
+++ b/qapi/crypto.json
@@ -55,11 +55,12 @@
 # @sha512: SHA-512.  (since 2.7)
 #
 # @ripemd160: RIPEMD-160.  (since 2.7)
+# @sm3: SM3. (since 9.2.0)
 #
 # Since: 2.6
 ##
 { 'enum': 'QCryptoHashAlgo',
-  'data': ['md5', 'sha1', 'sha224', 'sha256', 'sha384', 'sha512', 'ripemd160']}
+  'data': ['md5', 'sha1', 'sha224', 'sha256', 'sha384', 'sha512', 'ripemd160', 'sm3']}
 
 ##
 # @QCryptoCipherAlgo:
@@ -419,11 +420,6 @@
 #
 # Properties for objects of classes derived from secret-common.
 #
-# @loaded: if true, the secret is loaded immediately when applying
-#     this option and will probably fail when processing the next
-#     option.  Don't use; only provided for compatibility.
-#     (default: false)
-#
 # @format: the data format that the secret is provided in
 #     (default: raw)
 #
@@ -436,16 +432,10 @@
 #     16-byte IV.  Mandatory if @keyid is given.  Ignored if @keyid is
 #     absent.
 #
-# Features:
-#
-# @deprecated: Member @loaded is deprecated.  Setting true doesn't
-#     make sense, and false is already the default.
-#
 # Since: 2.6
 ##
 { 'struct': 'SecretCommonProperties',
-  'data': { '*loaded': { 'type': 'bool', 'features': ['deprecated'] },
-            '*format': 'QCryptoSecretFormat',
+  'data': { '*format': 'QCryptoSecretFormat',
             '*keyid': 'str',
             '*iv': 'str' } }
 
@@ -512,58 +502,32 @@
 #
 # Properties for tls-creds-anon objects.
 #
-# @loaded: if true, the credentials are loaded immediately when
-#     applying this option and will ignore options that are processed
-#     later.  Don't use; only provided for compatibility.
-#     (default: false)
-#
-# Features:
-#
-# @deprecated: Member @loaded is deprecated.  Setting true doesn't
-#     make sense, and false is already the default.
-#
 # Since: 2.5
 ##
 { 'struct': 'TlsCredsAnonProperties',
   'base': 'TlsCredsProperties',
-  'data': { '*loaded': { 'type': 'bool', 'features': ['deprecated'] } } }
+  'data': { } }
 
 ##
 # @TlsCredsPskProperties:
 #
 # Properties for tls-creds-psk objects.
 #
-# @loaded: if true, the credentials are loaded immediately when
-#     applying this option and will ignore options that are processed
-#     later.  Don't use; only provided for compatibility.
-#     (default: false)
-#
 # @username: the username which will be sent to the server.  For
 #     clients only.  If absent, "qemu" is sent and the property will
 #     read back as an empty string.
 #
-# Features:
-#
-# @deprecated: Member @loaded is deprecated.  Setting true doesn't
-#     make sense, and false is already the default.
-#
 # Since: 3.0
 ##
 { 'struct': 'TlsCredsPskProperties',
   'base': 'TlsCredsProperties',
-  'data': { '*loaded': { 'type': 'bool', 'features': ['deprecated'] },
-            '*username': 'str' } }
+  'data': { '*username': 'str' } }
 
 ##
 # @TlsCredsX509Properties:
 #
 # Properties for tls-creds-x509 objects.
 #
-# @loaded: if true, the credentials are loaded immediately when
-#     applying this option and will ignore options that are processed
-#     later.  Don't use; only provided for compatibility.
-#     (default: false)
-#
 # @sanity-check: if true, perform some sanity checks before using the
 #     credentials (default: true)
 #
@@ -573,17 +537,11 @@
 #     provides the ID of a previously created secret object containing
 #     the password for decryption.
 #
-# Features:
-#
-# @deprecated: Member @loaded is deprecated.  Setting true doesn't
-#     make sense, and false is already the default.
-#
 # Since: 2.5
 ##
 { 'struct': 'TlsCredsX509Properties',
   'base': 'TlsCredsProperties',
-  'data': { '*loaded': { 'type': 'bool', 'features': ['deprecated'] },
-            '*sanity-check': 'bool',
+  'data': { '*sanity-check': 'bool',
             '*passwordid': 'str' } }
 ##
 # @QCryptoAkCipherAlgo:
diff --git a/qapi/qdev.json b/qapi/qdev.json
index 53d147c7b4..2a581129c9 100644
--- a/qapi/qdev.json
+++ b/qapi/qdev.json
@@ -163,3 +163,27 @@
 ##
 { 'event': 'DEVICE_UNPLUG_GUEST_ERROR',
   'data': { '*device': 'str', 'path': 'str' } }
+
+##
+# @device-sync-config:
+#
+# Synchronize device configuration from host to guest part.  First,
+# copy the configuration from the host part (backend) to the guest
+# part (frontend).  Then notify guest software that device
+# configuration changed.
+#
+# The command may be used to notify the guest about block device
+# capcity change.  Currently only vhost-user-blk device supports
+# this.
+#
+# @id: the device's ID or QOM path
+#
+# Features:
+#
+# @unstable: The command is experimental.
+#
+# Since: 9.1
+##
+{ 'command': 'device-sync-config',
+  'features': [ 'unstable' ],
+  'data': {'id': 'str'} }
diff --git a/qapi/qom.json b/qapi/qom.json
index 321ccd708a..a8beeabf1f 100644
--- a/qapi/qom.json
+++ b/qapi/qom.json
@@ -845,6 +845,45 @@
             'node': 'uint32' } }
 
 ##
+# @AcpiGenericPortProperties:
+#
+# Properties for acpi-generic-port objects.
+#
+# @pci-bus: QOM path of the PCI bus of the hostbridge associated with
+#     this SRAT Generic Port Affinity Structure.  This is the same as
+#     the bus parameter for the root ports attached to this host
+#     bridge.  The resulting SRAT Generic Port Affinity Structure will
+#     refer to the ACPI object in DSDT that represents the host bridge
+#     (e.g.  ACPI0016 for CXL host bridges).  See ACPI 6.5 Section
+#     5.2.16.7 for more information.
+#
+# @node: Similar to a NUMA node ID, but instead of providing a
+#     reference point used for defining NUMA distances and access
+#     characteristics to memory or from an initiator (e.g. CPU), this
+#     node defines the boundary point between non-discoverable system
+#     buses which must be described by firmware, and a discoverable
+#     bus.  NUMA distances and access characteristics are defined to
+#     and from that point.  For system software to establish full
+#     initiator to target characteristics this information must be
+#     combined with information retrieved from the discoverable part
+#     of the path.  An example would use CDAT (see UEFI.org)
+#     information read from devices and switches in conjunction with
+#     link characteristics read from PCIe Configuration space.
+#     To get the full path latency from CPU to CXL attached DRAM
+#     CXL device:  Add the latency from CPU to Generic Port (from
+#     HMAT indexed via the the node ID in this SRAT structure) to
+#     that for CXL bus links, the latency across intermediate switches
+#     and from the EP port to the actual memory.  Bandwidth is more
+#     complex as there may be interleaving across multiple devices
+#     and shared links in the path.
+#
+# Since: 9.1
+##
+{ 'struct': 'AcpiGenericPortProperties',
+  'data': { 'pci-bus': 'str',
+            'node': 'uint32' } }
+
+##
 # @RngProperties:
 #
 # Properties for objects of classes derived from rng.
@@ -1043,6 +1082,7 @@
 { 'enum': 'ObjectType',
   'data': [
     'acpi-generic-initiator',
+    'acpi-generic-port',
     'authz-list',
     'authz-listfile',
     'authz-pam',
@@ -1118,6 +1158,7 @@
   'discriminator': 'qom-type',
   'data': {
       'acpi-generic-initiator':     'AcpiGenericInitiatorProperties',
+      'acpi-generic-port':          'AcpiGenericPortProperties',
       'authz-list':                 'AuthZListProperties',
       'authz-listfile':             'AuthZListFileProperties',
       'authz-pam':                  'AuthZPAMProperties',
diff --git a/scripts/meson-buildoptions.sh b/scripts/meson-buildoptions.sh
index 6f2bb08ecd..51ed46e46a 100644
--- a/scripts/meson-buildoptions.sh
+++ b/scripts/meson-buildoptions.sh
@@ -72,6 +72,7 @@ meson_options_help() {
   printf "%s\n" '                           "manufacturer" name for qemu-ga registry entries'
   printf "%s\n" '                           [QEMU]'
   printf "%s\n" '  --qemu-ga-version=VALUE  version number for qemu-ga installer'
+  printf "%s\n" '  --rtsig-map=VALUE        default value of QEMU_RTSIG_MAP [NULL]'
   printf "%s\n" '  --smbd=VALUE             Path to smbd for slirp networking'
   printf "%s\n" '  --sysconfdir=VALUE       Sysconf data directory [etc]'
   printf "%s\n" '  --tls-priority=VALUE     Default TLS protocol/cipher priority string'
@@ -460,6 +461,7 @@ _meson_option_parse() {
     --disable-replication) printf "%s" -Dreplication=disabled ;;
     --enable-rng-none) printf "%s" -Drng_none=true ;;
     --disable-rng-none) printf "%s" -Drng_none=false ;;
+    --rtsig-map=*) quote_sh "-Drtsig_map=$2" ;;
     --enable-rust) printf "%s" -Drust=enabled ;;
     --disable-rust) printf "%s" -Drust=disabled ;;
     --enable-rutabaga-gfx) printf "%s" -Drutabaga_gfx=enabled ;;
diff --git a/system/qdev-monitor.c b/system/qdev-monitor.c
index 320c47b72d..d25325c4e3 100644
--- a/system/qdev-monitor.c
+++ b/system/qdev-monitor.c
@@ -23,6 +23,7 @@
 #include "monitor/monitor.h"
 #include "monitor/qdev.h"
 #include "sysemu/arch_init.h"
+#include "sysemu/runstate.h"
 #include "qapi/error.h"
 #include "qapi/qapi-commands-qdev.h"
 #include "qapi/qmp/dispatch.h"
@@ -885,13 +886,20 @@ void qmp_device_add(QDict *qdict, QObject **ret_data, Error **errp)
     object_unref(OBJECT(dev));
 }
 
-static DeviceState *find_device_state(const char *id, Error **errp)
+/*
+ * Note that creating new APIs using error classes other than GenericError is
+ * not recommended. Set use_generic_error=true for new interfaces.
+ */
+static DeviceState *find_device_state(const char *id, bool use_generic_error,
+                                      Error **errp)
 {
     Object *obj = object_resolve_path_at(qdev_get_peripheral(), id);
     DeviceState *dev;
 
     if (!obj) {
-        error_set(errp, ERROR_CLASS_DEVICE_NOT_FOUND,
+        error_set(errp,
+                  (use_generic_error ?
+                   ERROR_CLASS_GENERIC_ERROR : ERROR_CLASS_DEVICE_NOT_FOUND),
                   "Device '%s' not found", id);
         return NULL;
     }
@@ -956,7 +964,7 @@ void qdev_unplug(DeviceState *dev, Error **errp)
 
 void qmp_device_del(const char *id, Error **errp)
 {
-    DeviceState *dev = find_device_state(id, errp);
+    DeviceState *dev = find_device_state(id, false, errp);
     if (dev != NULL) {
         if (dev->pending_deleted_event &&
             (dev->pending_deleted_expires_ms == 0 ||
@@ -970,6 +978,43 @@ void qmp_device_del(const char *id, Error **errp)
     }
 }
 
+int qdev_sync_config(DeviceState *dev, Error **errp)
+{
+    DeviceClass *dc = DEVICE_GET_CLASS(dev);
+
+    if (!dc->sync_config) {
+        error_setg(errp, "device-sync-config is not supported for '%s'",
+                   object_get_typename(OBJECT(dev)));
+        return -ENOTSUP;
+    }
+
+    return dc->sync_config(dev, errp);
+}
+
+void qmp_device_sync_config(const char *id, Error **errp)
+{
+    DeviceState *dev;
+
+    /*
+     * During migration there is a race between syncing`configuration
+     * and migrating it (if migrate first, that target would get
+     * outdated version), so let's just not allow it.
+     */
+
+    if (migration_is_running()) {
+        error_setg(errp, "Config synchronization is not allowed "
+                   "during migration");
+        return;
+    }
+
+    dev = find_device_state(id, true, errp);
+    if (!dev) {
+        return;
+    }
+
+    qdev_sync_config(dev, errp);
+}
+
 void hmp_device_add(Monitor *mon, const QDict *qdict)
 {
     Error *err = NULL;
@@ -1076,7 +1121,7 @@ BlockBackend *blk_by_qdev_id(const char *id, Error **errp)
 
     GLOBAL_STATE_CODE();
 
-    dev = find_device_state(id, errp);
+    dev = find_device_state(id, false, errp);
     if (dev == NULL) {
         return NULL;
     }
diff --git a/target/alpha/cpu.c b/target/alpha/cpu.c
index 9db1dffc03..5d75c941f7 100644
--- a/target/alpha/cpu.c
+++ b/target/alpha/cpu.c
@@ -24,6 +24,7 @@
 #include "qemu/qemu-print.h"
 #include "cpu.h"
 #include "exec/exec-all.h"
+#include "fpu/softfloat.h"
 
 
 static void alpha_cpu_set_pc(CPUState *cs, vaddr value)
@@ -187,7 +188,17 @@ static void alpha_cpu_initfn(Object *obj)
 {
     CPUAlphaState *env = cpu_env(CPU(obj));
 
+    /* TODO all this should be done in reset, not init */
+
     env->lock_addr = -1;
+
+    /*
+     * TODO: this is incorrect. The Alpha Architecture Handbook version 4
+     * describes NaN propagation in section 4.7.10.4. We should prefer
+     * the operand in Fb (whether it is a QNaN or an SNaN), then the
+     * operand in Fa. That is float_2nan_prop_ba.
+     */
+    set_float_2nan_prop_rule(float_2nan_prop_x87, &env->fp_status);
 #if defined(CONFIG_USER_ONLY)
     env->flags = ENV_FLAG_PS_USER | ENV_FLAG_FEN;
     cpu_alpha_store_fpcr(env, (uint64_t)(FPCR_INVD | FPCR_DZED | FPCR_OVFD
diff --git a/target/arm/cpu-features.h b/target/arm/cpu-features.h
index 04ce281826..e806f138b8 100644
--- a/target/arm/cpu-features.h
+++ b/target/arm/cpu-features.h
@@ -802,6 +802,11 @@ static inline bool isar_feature_aa64_tidcp1(const ARMISARegisters *id)
     return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, TIDCP1) != 0;
 }
 
+static inline bool isar_feature_aa64_cmow(const ARMISARegisters *id)
+{
+    return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, CMOW) != 0;
+}
+
 static inline bool isar_feature_aa64_hafs(const ARMISARegisters *id)
 {
     return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, HAFDBS) != 0;
diff --git a/target/arm/cpu.c b/target/arm/cpu.c
index 5b751439bd..6938161b95 100644
--- a/target/arm/cpu.c
+++ b/target/arm/cpu.c
@@ -168,6 +168,18 @@ void arm_register_el_change_hook(ARMCPU *cpu, ARMELChangeHookFn *hook,
     QLIST_INSERT_HEAD(&cpu->el_change_hooks, entry, node);
 }
 
+/*
+ * Set the float_status behaviour to match the Arm defaults:
+ *  * tininess-before-rounding
+ *  * 2-input NaN propagation prefers SNaN over QNaN, and then
+ *    operand A over operand B (see FPProcessNaNs() pseudocode)
+ */
+static void arm_set_default_fp_behaviours(float_status *s)
+{
+    set_float_detect_tininess(float_tininess_before_rounding, s);
+    set_float_2nan_prop_rule(float_2nan_prop_s_ab, s);
+}
+
 static void cp_reg_reset(gpointer key, gpointer value, gpointer opaque)
 {
     /* Reset a single ARMCPRegInfo register */
@@ -549,14 +561,11 @@ static void arm_cpu_reset_hold(Object *obj, ResetType type)
     set_flush_inputs_to_zero(1, &env->vfp.standard_fp_status);
     set_default_nan_mode(1, &env->vfp.standard_fp_status);
     set_default_nan_mode(1, &env->vfp.standard_fp_status_f16);
-    set_float_detect_tininess(float_tininess_before_rounding,
-                              &env->vfp.fp_status);
-    set_float_detect_tininess(float_tininess_before_rounding,
-                              &env->vfp.standard_fp_status);
-    set_float_detect_tininess(float_tininess_before_rounding,
-                              &env->vfp.fp_status_f16);
-    set_float_detect_tininess(float_tininess_before_rounding,
-                              &env->vfp.standard_fp_status_f16);
+    arm_set_default_fp_behaviours(&env->vfp.fp_status);
+    arm_set_default_fp_behaviours(&env->vfp.standard_fp_status);
+    arm_set_default_fp_behaviours(&env->vfp.fp_status_f16);
+    arm_set_default_fp_behaviours(&env->vfp.standard_fp_status_f16);
+
 #ifndef CONFIG_USER_ONLY
     if (kvm_enabled()) {
         kvm_arm_reset_vcpu(cpu);
diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index 8fc8b6398f..d86e641280 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -1367,6 +1367,7 @@ void pmu_init(ARMCPU *cpu);
 #define SCTLR_EnIB    (1U << 30) /* v8.3, AArch64 only */
 #define SCTLR_EnIA    (1U << 31) /* v8.3, AArch64 only */
 #define SCTLR_DSSBS_32 (1U << 31) /* v8.5, AArch32 only */
+#define SCTLR_CMOW    (1ULL << 32) /* FEAT_CMOW */
 #define SCTLR_MSCEN   (1ULL << 33) /* FEAT_MOPS */
 #define SCTLR_BT0     (1ULL << 35) /* v8.5-BTI */
 #define SCTLR_BT1     (1ULL << 36) /* v8.5-BTI */
@@ -2805,38 +2806,38 @@ bool write_cpustate_to_list(ARMCPU *cpu, bool kvm_sync);
  *     The only use of stage 2 translations is either as part of an s1+2
  *     lookup or when loading the descriptors during a stage 1 page table walk,
  *     and in both those cases we don't use the TLB.
- *  4. we want to be able to use the TLB for accesses done as part of a
+ *  4. we can also safely fold together the "32 bit EL3" and "64 bit EL3"
+ *     translation regimes, because they map reasonably well to each other
+ *     and they can't both be active at the same time.
+ *  5. we want to be able to use the TLB for accesses done as part of a
  *     stage1 page table walk, rather than having to walk the stage2 page
  *     table over and over.
- *  5. we need separate EL1/EL2 mmu_idx for handling the Privileged Access
+ *  6. we need separate EL1/EL2 mmu_idx for handling the Privileged Access
  *     Never (PAN) bit within PSTATE.
- *  6. we fold together most secure and non-secure regimes for A-profile,
+ *  7. we fold together most secure and non-secure regimes for A-profile,
  *     because there are no banked system registers for aarch64, so the
  *     process of switching between secure and non-secure is
  *     already heavyweight.
- *  7. we cannot fold together Stage 2 Secure and Stage 2 NonSecure,
+ *  8. we cannot fold together Stage 2 Secure and Stage 2 NonSecure,
  *     because both are in use simultaneously for Secure EL2.
  *
  * This gives us the following list of cases:
  *
- * EL0 EL1&0 stage 1+2 (or AArch32 PL0 PL1&0 stage 1+2)
- * EL1 EL1&0 stage 1+2 (or AArch32 PL1 PL1&0 stage 1+2)
- * EL1 EL1&0 stage 1+2 +PAN (or AArch32 PL1 PL1&0 stage 1+2 +PAN)
+ * EL0 EL1&0 stage 1+2 (aka NS PL0 PL1&0 stage 1+2)
+ * EL1 EL1&0 stage 1+2 (aka NS PL1 PL1&0 stage 1+2)
+ * EL1 EL1&0 stage 1+2 +PAN (aka NS PL1 P1&0 stage 1+2 +PAN)
  * EL0 EL2&0
  * EL2 EL2&0
  * EL2 EL2&0 +PAN
  * EL2 (aka NS PL2)
- * EL3 (not used when EL3 is AArch32)
+ * EL3 (aka AArch32 S PL1 PL1&0)
+ * AArch32 S PL0 PL1&0 (we call this EL30_0)
+ * AArch32 S PL1 PL1&0 +PAN (we call this EL30_3_PAN)
  * Stage2 Secure
  * Stage2 NonSecure
  * plus one TLB per Physical address space: S, NS, Realm, Root
  *
- * for a total of 14 different mmu_idx.
- *
- * Note that when EL3 is AArch32, the usage is potentially confusing
- * because the MMU indexes are named for their AArch64 use, so code
- * using the ARMMMUIdx_E10_1 might be at EL3, not EL1. This is because
- * Secure PL1 is always at EL3.
+ * for a total of 16 different mmu_idx.
  *
  * R profile CPUs have an MPU, but can use the same set of MMU indexes
  * as A profile. They only need to distinguish EL0 and EL1 (and
@@ -2900,6 +2901,8 @@ typedef enum ARMMMUIdx {
     ARMMMUIdx_E20_2_PAN = 5 | ARM_MMU_IDX_A,
     ARMMMUIdx_E2        = 6 | ARM_MMU_IDX_A,
     ARMMMUIdx_E3        = 7 | ARM_MMU_IDX_A,
+    ARMMMUIdx_E30_0     = 8 | ARM_MMU_IDX_A,
+    ARMMMUIdx_E30_3_PAN = 9 | ARM_MMU_IDX_A,
 
     /*
      * Used for second stage of an S12 page table walk, or for descriptor
@@ -2907,14 +2910,14 @@ typedef enum ARMMMUIdx {
      * are in use simultaneously for SecureEL2: the security state for
      * the S2 ptw is selected by the NS bit from the S1 ptw.
      */
-    ARMMMUIdx_Stage2_S  = 8 | ARM_MMU_IDX_A,
-    ARMMMUIdx_Stage2    = 9 | ARM_MMU_IDX_A,
+    ARMMMUIdx_Stage2_S  = 10 | ARM_MMU_IDX_A,
+    ARMMMUIdx_Stage2    = 11 | ARM_MMU_IDX_A,
 
     /* TLBs with 1-1 mapping to the physical address spaces. */
-    ARMMMUIdx_Phys_S     = 10 | ARM_MMU_IDX_A,
-    ARMMMUIdx_Phys_NS    = 11 | ARM_MMU_IDX_A,
-    ARMMMUIdx_Phys_Root  = 12 | ARM_MMU_IDX_A,
-    ARMMMUIdx_Phys_Realm = 13 | ARM_MMU_IDX_A,
+    ARMMMUIdx_Phys_S     = 12 | ARM_MMU_IDX_A,
+    ARMMMUIdx_Phys_NS    = 13 | ARM_MMU_IDX_A,
+    ARMMMUIdx_Phys_Root  = 14 | ARM_MMU_IDX_A,
+    ARMMMUIdx_Phys_Realm = 15 | ARM_MMU_IDX_A,
 
     /*
      * These are not allocated TLBs and are used only for AT system
@@ -2953,6 +2956,8 @@ typedef enum ARMMMUIdxBit {
     TO_CORE_BIT(E20_2),
     TO_CORE_BIT(E20_2_PAN),
     TO_CORE_BIT(E3),
+    TO_CORE_BIT(E30_0),
+    TO_CORE_BIT(E30_3_PAN),
     TO_CORE_BIT(Stage2),
     TO_CORE_BIT(Stage2_S),
 
@@ -3130,10 +3135,6 @@ FIELD(TBFLAG_A32, NS, 10, 1)
  * This requires an SME trap from AArch32 mode when using NEON.
  */
 FIELD(TBFLAG_A32, SME_TRAP_NONSTREAMING, 11, 1)
-/*
- * Indicates whether we are in the Secure PL1&0 translation regime
- */
-FIELD(TBFLAG_A32, S_PL1_0, 12, 1)
 
 /*
  * Bit usage when in AArch32 state, for M-profile only.
diff --git a/target/arm/helper.c b/target/arm/helper.c
index 0a731a38e8..f38eb054c0 100644
--- a/target/arm/helper.c
+++ b/target/arm/helper.c
@@ -444,6 +444,9 @@ static int alle1_tlbmask(CPUARMState *env)
      * Note that the 'ALL' scope must invalidate both stage 1 and
      * stage 2 translations, whereas most other scopes only invalidate
      * stage 1 translations.
+     *
+     * For AArch32 this is only used for TLBIALLNSNH and VTTBR
+     * writes, so only needs to apply to NS PL1&0, not S PL1&0.
      */
     return (ARMMMUIdxBit_E10_1 |
             ARMMMUIdxBit_E10_1_PAN |
@@ -3701,7 +3704,7 @@ static uint64_t do_ats_write(CPUARMState *env, uint64_t value,
          */
         format64 = arm_s1_regime_using_lpae_format(env, mmu_idx);
 
-        if (arm_feature(env, ARM_FEATURE_EL2) && !arm_aa32_secure_pl1_0(env)) {
+        if (arm_feature(env, ARM_FEATURE_EL2)) {
             if (mmu_idx == ARMMMUIdx_E10_0 ||
                 mmu_idx == ARMMMUIdx_E10_1 ||
                 mmu_idx == ARMMMUIdx_E10_1_PAN) {
@@ -3775,11 +3778,17 @@ static void ats_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value)
     case 0:
         /* stage 1 current state PL1: ATS1CPR, ATS1CPW, ATS1CPRP, ATS1CPWP */
         switch (el) {
+        case 3:
+            if (ri->crm == 9 && arm_pan_enabled(env)) {
+                mmu_idx = ARMMMUIdx_E30_3_PAN;
+            } else {
+                mmu_idx = ARMMMUIdx_E3;
+            }
+            break;
         case 2:
             g_assert(ss != ARMSS_Secure);  /* ARMv8.4-SecEL2 is 64-bit only */
             /* fall through */
         case 1:
-        case 3:
             if (ri->crm == 9 && arm_pan_enabled(env)) {
                 mmu_idx = ARMMMUIdx_Stage1_E1_PAN;
             } else {
@@ -3794,7 +3803,7 @@ static void ats_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value)
         /* stage 1 current state PL0: ATS1CUR, ATS1CUW */
         switch (el) {
         case 3:
-            mmu_idx = ARMMMUIdx_E10_0;
+            mmu_idx = ARMMMUIdx_E30_0;
             break;
         case 2:
             g_assert(ss != ARMSS_Secure);  /* ARMv8.4-SecEL2 is 64-bit only */
@@ -4904,11 +4913,14 @@ static int vae1_tlbmask(CPUARMState *env)
     uint64_t hcr = arm_hcr_el2_eff(env);
     uint16_t mask;
 
+    assert(arm_feature(env, ARM_FEATURE_AARCH64));
+
     if ((hcr & (HCR_E2H | HCR_TGE)) == (HCR_E2H | HCR_TGE)) {
         mask = ARMMMUIdxBit_E20_2 |
                ARMMMUIdxBit_E20_2_PAN |
                ARMMMUIdxBit_E20_0;
     } else {
+        /* This is AArch64 only, so we don't need to touch the EL30_x TLBs */
         mask = ARMMMUIdxBit_E10_1 |
                ARMMMUIdxBit_E10_1_PAN |
                ARMMMUIdxBit_E10_0;
@@ -4947,6 +4959,8 @@ static int vae1_tlbbits(CPUARMState *env, uint64_t addr)
     uint64_t hcr = arm_hcr_el2_eff(env);
     ARMMMUIdx mmu_idx;
 
+    assert(arm_feature(env, ARM_FEATURE_AARCH64));
+
     /* Only the regime of the mmu_idx below is significant. */
     if ((hcr & (HCR_E2H | HCR_TGE)) == (HCR_E2H | HCR_TGE)) {
         mmu_idx = ARMMMUIdx_E20_0;
@@ -6215,6 +6229,11 @@ static void hcrx_write(CPUARMState *env, const ARMCPRegInfo *ri,
     if (cpu_isar_feature(aa64_nmi, cpu)) {
         valid_mask |= HCRX_TALLINT | HCRX_VINMI | HCRX_VFNMI;
     }
+    /* FEAT_CMOW adds CMOW */
+
+    if (cpu_isar_feature(aa64_cmow, cpu)) {
+        valid_mask |= HCRX_CMOW;
+    }
 
     /* Clear RES0 bits.  */
     env->cp15.hcrx_el2 = value & valid_mask;
@@ -11860,13 +11879,20 @@ void arm_cpu_do_interrupt(CPUState *cs)
 
 uint64_t arm_sctlr(CPUARMState *env, int el)
 {
-    if (arm_aa32_secure_pl1_0(env)) {
-        /* In Secure PL1&0 SCTLR_S is always controlling */
-        el = 3;
-    } else if (el == 0) {
-        /* Only EL0 needs to be adjusted for EL1&0 or EL2&0. */
+    /* Only EL0 needs to be adjusted for EL1&0 or EL2&0 or EL3&0 */
+    if (el == 0) {
         ARMMMUIdx mmu_idx = arm_mmu_idx_el(env, 0);
-        el = mmu_idx == ARMMMUIdx_E20_0 ? 2 : 1;
+        switch (mmu_idx) {
+        case ARMMMUIdx_E20_0:
+            el = 2;
+            break;
+        case ARMMMUIdx_E30_0:
+            el = 3;
+            break;
+        default:
+            el = 1;
+            break;
+        }
     }
     return env->cp15.sctlr_el[el];
 }
@@ -12524,12 +12550,8 @@ int fp_exception_el(CPUARMState *env, int cur_el)
     return 0;
 }
 
-/*
- * Return the exception level we're running at if this is our mmu_idx.
- * s_pl1_0 should be true if this is the AArch32 Secure PL1&0 translation
- * regime.
- */
-int arm_mmu_idx_to_el(ARMMMUIdx mmu_idx, bool s_pl1_0)
+/* Return the exception level we're running at if this is our mmu_idx */
+int arm_mmu_idx_to_el(ARMMMUIdx mmu_idx)
 {
     if (mmu_idx & ARM_MMU_IDX_M) {
         return mmu_idx & ARM_MMU_IDX_M_PRIV;
@@ -12538,15 +12560,17 @@ int arm_mmu_idx_to_el(ARMMMUIdx mmu_idx, bool s_pl1_0)
     switch (mmu_idx) {
     case ARMMMUIdx_E10_0:
     case ARMMMUIdx_E20_0:
+    case ARMMMUIdx_E30_0:
         return 0;
     case ARMMMUIdx_E10_1:
     case ARMMMUIdx_E10_1_PAN:
-        return s_pl1_0 ? 3 : 1;
+        return 1;
     case ARMMMUIdx_E2:
     case ARMMMUIdx_E20_2:
     case ARMMMUIdx_E20_2_PAN:
         return 2;
     case ARMMMUIdx_E3:
+    case ARMMMUIdx_E30_3_PAN:
         return 3;
     default:
         g_assert_not_reached();
@@ -12575,19 +12599,13 @@ ARMMMUIdx arm_mmu_idx_el(CPUARMState *env, int el)
         hcr = arm_hcr_el2_eff(env);
         if ((hcr & (HCR_E2H | HCR_TGE)) == (HCR_E2H | HCR_TGE)) {
             idx = ARMMMUIdx_E20_0;
+        } else if (arm_is_secure_below_el3(env) &&
+                   !arm_el_is_aa64(env, 3)) {
+            idx = ARMMMUIdx_E30_0;
         } else {
             idx = ARMMMUIdx_E10_0;
         }
         break;
-    case 3:
-        /*
-         * AArch64 EL3 has its own translation regime; AArch32 EL3
-         * uses the Secure PL1&0 translation regime.
-         */
-        if (arm_el_is_aa64(env, 3)) {
-            return ARMMMUIdx_E3;
-        }
-        /* fall through */
     case 1:
         if (arm_pan_enabled(env)) {
             idx = ARMMMUIdx_E10_1_PAN;
@@ -12607,6 +12625,11 @@ ARMMMUIdx arm_mmu_idx_el(CPUARMState *env, int el)
             idx = ARMMMUIdx_E2;
         }
         break;
+    case 3:
+        if (!arm_el_is_aa64(env, 3) && arm_pan_enabled(env)) {
+            return ARMMMUIdx_E30_3_PAN;
+        }
+        return ARMMMUIdx_E3;
     default:
         g_assert_not_reached();
     }
diff --git a/target/arm/internals.h b/target/arm/internals.h
index fd8f7c82aa..e37f459af3 100644
--- a/target/arm/internals.h
+++ b/target/arm/internals.h
@@ -276,20 +276,6 @@ FIELD(CNTHCTL, CNTPMASK, 19, 1)
 #define M_FAKE_FSR_SFAULT 0xe /* SecureFault INVTRAN, INVEP or AUVIOL */
 
 /**
- * arm_aa32_secure_pl1_0(): Return true if in Secure PL1&0 regime
- *
- * Return true if the CPU is in the Secure PL1&0 translation regime.
- * This requires that EL3 exists and is AArch32 and we are currently
- * Secure. If this is the case then the ARMMMUIdx_E10* apply and
- * mean we are in EL3, not EL1.
- */
-static inline bool arm_aa32_secure_pl1_0(CPUARMState *env)
-{
-    return arm_feature(env, ARM_FEATURE_EL3) &&
-        !arm_el_is_aa64(env, 3) && arm_is_secure(env);
-}
-
-/**
  * raise_exception: Raise the specified exception.
  * Raise a guest exception with the specified value, syndrome register
  * and target exception level. This should be called from helper functions,
@@ -841,12 +827,7 @@ static inline ARMMMUIdx core_to_aa64_mmu_idx(int mmu_idx)
     return mmu_idx | ARM_MMU_IDX_A;
 }
 
-/**
- * Return the exception level we're running at if our current MMU index
- * is @mmu_idx. @s_pl1_0 should be true if this is the AArch32
- * Secure PL1&0 translation regime.
- */
-int arm_mmu_idx_to_el(ARMMMUIdx mmu_idx, bool s_pl1_0);
+int arm_mmu_idx_to_el(ARMMMUIdx mmu_idx);
 
 /* Return the MMU index for a v7M CPU in the specified security state */
 ARMMMUIdx arm_v7m_mmu_idx_for_secstate(CPUARMState *env, bool secstate);
@@ -890,7 +871,16 @@ static inline void arm_call_el_change_hook(ARMCPU *cpu)
     }
 }
 
-/* Return true if this address translation regime has two ranges.  */
+/*
+ * Return true if this address translation regime has two ranges.
+ * Note that this will not return the correct answer for AArch32
+ * Secure PL1&0 (i.e. mmu indexes E3, E30_0, E30_3_PAN), but it is
+ * never called from a context where EL3 can be AArch32. (The
+ * correct return value for ARMMMUIdx_E3 would be different for
+ * that case, so we can't just make the function return the
+ * correct value anyway; we would need an extra "bool e3_is_aarch32"
+ * argument which all the current callsites would pass as 'false'.)
+ */
 static inline bool regime_has_2_ranges(ARMMMUIdx mmu_idx)
 {
     switch (mmu_idx) {
@@ -915,6 +905,7 @@ static inline bool regime_is_pan(CPUARMState *env, ARMMMUIdx mmu_idx)
     case ARMMMUIdx_Stage1_E1_PAN:
     case ARMMMUIdx_E10_1_PAN:
     case ARMMMUIdx_E20_2_PAN:
+    case ARMMMUIdx_E30_3_PAN:
         return true;
     default:
         return false;
@@ -938,14 +929,15 @@ static inline uint32_t regime_el(CPUARMState *env, ARMMMUIdx mmu_idx)
     case ARMMMUIdx_E2:
         return 2;
     case ARMMMUIdx_E3:
+    case ARMMMUIdx_E30_0:
+    case ARMMMUIdx_E30_3_PAN:
         return 3;
     case ARMMMUIdx_E10_0:
     case ARMMMUIdx_Stage1_E0:
-    case ARMMMUIdx_E10_1:
-    case ARMMMUIdx_E10_1_PAN:
     case ARMMMUIdx_Stage1_E1:
     case ARMMMUIdx_Stage1_E1_PAN:
-        return arm_el_is_aa64(env, 3) || !arm_is_secure_below_el3(env) ? 1 : 3;
+    case ARMMMUIdx_E10_1:
+    case ARMMMUIdx_E10_1_PAN:
     case ARMMMUIdx_MPrivNegPri:
     case ARMMMUIdx_MUserNegPri:
     case ARMMMUIdx_MPriv:
@@ -965,6 +957,7 @@ static inline bool regime_is_user(CPUARMState *env, ARMMMUIdx mmu_idx)
     switch (mmu_idx) {
     case ARMMMUIdx_E10_0:
     case ARMMMUIdx_E20_0:
+    case ARMMMUIdx_E30_0:
     case ARMMMUIdx_Stage1_E0:
     case ARMMMUIdx_MUser:
     case ARMMMUIdx_MSUser:
diff --git a/target/arm/ptw.c b/target/arm/ptw.c
index dd40268397..9849949508 100644
--- a/target/arm/ptw.c
+++ b/target/arm/ptw.c
@@ -280,6 +280,8 @@ static bool regime_translation_disabled(CPUARMState *env, ARMMMUIdx mmu_idx,
     case ARMMMUIdx_E20_2_PAN:
     case ARMMMUIdx_E2:
     case ARMMMUIdx_E3:
+    case ARMMMUIdx_E30_0:
+    case ARMMMUIdx_E30_3_PAN:
         break;
 
     case ARMMMUIdx_Phys_S:
@@ -3607,11 +3609,7 @@ bool get_phys_addr(CPUARMState *env, vaddr address,
     case ARMMMUIdx_Stage1_E1:
     case ARMMMUIdx_Stage1_E1_PAN:
     case ARMMMUIdx_E2:
-        if (arm_aa32_secure_pl1_0(env)) {
-            ss = ARMSS_Secure;
-        } else {
-            ss = arm_security_space_below_el3(env);
-        }
+        ss = arm_security_space_below_el3(env);
         break;
     case ARMMMUIdx_Stage2:
         /*
@@ -3639,6 +3637,8 @@ bool get_phys_addr(CPUARMState *env, vaddr address,
         ss = ARMSS_Secure;
         break;
     case ARMMMUIdx_E3:
+    case ARMMMUIdx_E30_0:
+    case ARMMMUIdx_E30_3_PAN:
         if (arm_feature(env, ARM_FEATURE_AARCH64) &&
             cpu_isar_feature(aa64_rme, env_archcpu(env))) {
             ss = ARMSS_Root;
diff --git a/target/arm/tcg/cpu64.c b/target/arm/tcg/cpu64.c
index 0168920828..2963d7510f 100644
--- a/target/arm/tcg/cpu64.c
+++ b/target/arm/tcg/cpu64.c
@@ -1218,6 +1218,7 @@ void aarch64_max_tcg_initfn(Object *obj)
     t = FIELD_DP64(t, ID_AA64MMFR1, ETS, 2);      /* FEAT_ETS2 */
     t = FIELD_DP64(t, ID_AA64MMFR1, HCX, 1);      /* FEAT_HCX */
     t = FIELD_DP64(t, ID_AA64MMFR1, TIDCP1, 1);   /* FEAT_TIDCP1 */
+    t = FIELD_DP64(t, ID_AA64MMFR1, CMOW, 1);     /* FEAT_CMOW */
     cpu->isar.id_aa64mmfr1 = t;
 
     t = cpu->isar.id_aa64mmfr2;
diff --git a/target/arm/tcg/hflags.c b/target/arm/tcg/hflags.c
index bab7822ef6..f03977b4b0 100644
--- a/target/arm/tcg/hflags.c
+++ b/target/arm/tcg/hflags.c
@@ -198,10 +198,6 @@ static CPUARMTBFlags rebuild_hflags_a32(CPUARMState *env, int fp_el,
         DP_TBFLAG_A32(flags, SME_TRAP_NONSTREAMING, 1);
     }
 
-    if (arm_aa32_secure_pl1_0(env)) {
-        DP_TBFLAG_A32(flags, S_PL1_0, 1);
-    }
-
     return rebuild_hflags_common_32(env, fp_el, mmu_idx, flags);
 }
 
diff --git a/target/arm/tcg/op_helper.c b/target/arm/tcg/op_helper.c
index c083e5cfb8..1ecb465988 100644
--- a/target/arm/tcg/op_helper.c
+++ b/target/arm/tcg/op_helper.c
@@ -912,7 +912,19 @@ void HELPER(tidcp_el0)(CPUARMState *env, uint32_t syndrome)
 {
     /* See arm_sctlr(), but we also need the sctlr el. */
     ARMMMUIdx mmu_idx = arm_mmu_idx_el(env, 0);
-    int target_el = mmu_idx == ARMMMUIdx_E20_0 ? 2 : 1;
+    int target_el;
+
+    switch (mmu_idx) {
+    case ARMMMUIdx_E20_0:
+        target_el = 2;
+        break;
+    case ARMMMUIdx_E30_0:
+        target_el = 3;
+        break;
+    default:
+        target_el = 1;
+        break;
+    }
 
     /*
      * The bit is not valid unless the target el is aa64, but since the
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index ec0b1ee252..b2851ea503 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -11690,7 +11690,7 @@ static void aarch64_tr_init_disas_context(DisasContextBase *dcbase,
     dc->tbii = EX_TBFLAG_A64(tb_flags, TBII);
     dc->tbid = EX_TBFLAG_A64(tb_flags, TBID);
     dc->tcma = EX_TBFLAG_A64(tb_flags, TCMA);
-    dc->current_el = arm_mmu_idx_to_el(dc->mmu_idx, false);
+    dc->current_el = arm_mmu_idx_to_el(dc->mmu_idx);
 #if !defined(CONFIG_USER_ONLY)
     dc->user = (dc->current_el == 0);
 #endif
diff --git a/target/arm/tcg/translate.c b/target/arm/tcg/translate.c
index e2748ff2bb..9ee761fc64 100644
--- a/target/arm/tcg/translate.c
+++ b/target/arm/tcg/translate.c
@@ -228,6 +228,9 @@ static inline int get_a32_user_mem_index(DisasContext *s)
      */
     switch (s->mmu_idx) {
     case ARMMMUIdx_E3:
+    case ARMMMUIdx_E30_0:
+    case ARMMMUIdx_E30_3_PAN:
+        return arm_to_core_mmu_idx(ARMMMUIdx_E30_0);
     case ARMMMUIdx_E2:        /* this one is UNPREDICTABLE */
     case ARMMMUIdx_E10_0:
     case ARMMMUIdx_E10_1:
@@ -7546,6 +7549,10 @@ static void arm_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs)
 
     core_mmu_idx = EX_TBFLAG_ANY(tb_flags, MMUIDX);
     dc->mmu_idx = core_to_arm_mmu_idx(env, core_mmu_idx);
+    dc->current_el = arm_mmu_idx_to_el(dc->mmu_idx);
+#if !defined(CONFIG_USER_ONLY)
+    dc->user = (dc->current_el == 0);
+#endif
     dc->fp_excp_el = EX_TBFLAG_ANY(tb_flags, FPEXC_EL);
     dc->align_mem = EX_TBFLAG_ANY(tb_flags, ALIGN_MEM);
     dc->pstate_il = EX_TBFLAG_ANY(tb_flags, PSTATE__IL);
@@ -7576,12 +7583,7 @@ static void arm_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs)
         }
         dc->sme_trap_nonstreaming =
             EX_TBFLAG_A32(tb_flags, SME_TRAP_NONSTREAMING);
-        dc->s_pl1_0 = EX_TBFLAG_A32(tb_flags, S_PL1_0);
     }
-    dc->current_el = arm_mmu_idx_to_el(dc->mmu_idx, dc->s_pl1_0);
-#if !defined(CONFIG_USER_ONLY)
-    dc->user = (dc->current_el == 0);
-#endif
     dc->lse2 = false; /* applies only to aarch64 */
     dc->cp_regs = cpu->cp_regs;
     dc->features = env->features;
diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h
index 5a2e10d64d..20cd0e851c 100644
--- a/target/arm/tcg/translate.h
+++ b/target/arm/tcg/translate.h
@@ -165,8 +165,6 @@ typedef struct DisasContext {
     uint8_t gm_blocksize;
     /* True if the current insn_start has been updated. */
     bool insn_start_updated;
-    /* True if this is the AArch32 Secure PL1&0 translation regime */
-    bool s_pl1_0;
     /* Bottom two bits of XScale c15_cpar coprocessor access control reg */
     int c15_cpar;
     /* Offset from VNCR_EL2 when FEAT_NV2 redirects this reg to memory */
diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c
index 22ddb96881..e825d501a2 100644
--- a/target/arm/tcg/vec_helper.c
+++ b/target/arm/tcg/vec_helper.c
@@ -836,6 +836,13 @@ void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc)  \
 {                                                                         \
     intptr_t i = 0, opr_sz = simd_oprsz(desc);                            \
     intptr_t opr_sz_n = opr_sz / sizeof(TYPED);                           \
+    /*                                                                    \
+     * Special case: opr_sz == 8 from AA64/AA32 advsimd means the         \
+     * first iteration might not be a full 16 byte segment. But           \
+     * for vector lengths beyond that this must be SVE and we know        \
+     * opr_sz is a multiple of 16, so we need not clamp segend            \
+     * to opr_sz_n when we advance it at the end of the loop.             \
+     */                                                                   \
     intptr_t segend = MIN(16 / sizeof(TYPED), opr_sz_n);                  \
     intptr_t index = simd_data(desc);                                     \
     TYPED *d = vd, *a = va;                                               \
@@ -853,7 +860,7 @@ void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc)  \
                     n[i * 4 + 2] * m2 +                                   \
                     n[i * 4 + 3] * m3);                                   \
         } while (++i < segend);                                           \
-        segend = i + 4;                                                   \
+        segend = i + (16 / sizeof(TYPED));                                \
     } while (i < opr_sz_n);                                               \
     clear_tail(d, opr_sz, simd_maxsz(desc));                              \
 }
diff --git a/target/hppa/fpu_helper.c b/target/hppa/fpu_helper.c
index deaed2b65d..0e44074ba8 100644
--- a/target/hppa/fpu_helper.c
+++ b/target/hppa/fpu_helper.c
@@ -49,6 +49,12 @@ void HELPER(loaded_fr0)(CPUHPPAState *env)
     d = FIELD_EX32(shadow, FPSR, D);
     set_flush_to_zero(d, &env->fp_status);
     set_flush_inputs_to_zero(d, &env->fp_status);
+
+    /*
+     * TODO: we only need to do this at CPU reset, but currently
+     * HPPA does note implement a CPU reset method at all...
+     */
+    set_float_2nan_prop_rule(float_2nan_prop_s_ab, &env->fp_status);
 }
 
 void cpu_hppa_loaded_fr0(CPUHPPAState *env)
diff --git a/target/i386/cpu.c b/target/i386/cpu.c
index d46710a403..58c96eafea 100644
--- a/target/i386/cpu.c
+++ b/target/i386/cpu.c
@@ -7203,6 +7203,10 @@ static void x86_cpu_reset_hold(Object *obj, ResetType type)
 
     memset(env, 0, offsetof(CPUX86State, end_reset_fields));
 
+    if (tcg_enabled()) {
+        cpu_init_fp_statuses(env);
+    }
+
     env->old_exception = -1;
 
     /* init to reset state */
diff --git a/target/i386/cpu.h b/target/i386/cpu.h
index 00b23bc5d1..b65eedb617 100644
--- a/target/i386/cpu.h
+++ b/target/i386/cpu.h
@@ -2614,6 +2614,9 @@ static inline bool cpu_vmx_maybe_enabled(CPUX86State *env)
 int get_pg_mode(CPUX86State *env);
 
 /* fpu_helper.c */
+
+/* Set all non-runtime-variable float_status fields to x86 handling */
+void cpu_init_fp_statuses(CPUX86State *env);
 void update_fp_status(CPUX86State *env);
 void update_mxcsr_status(CPUX86State *env);
 void update_mxcsr_from_sse_status(CPUX86State *env);
diff --git a/target/i386/tcg/fpu_helper.c b/target/i386/tcg/fpu_helper.c
index e1b850f3fc..53b49bb297 100644
--- a/target/i386/tcg/fpu_helper.c
+++ b/target/i386/tcg/fpu_helper.c
@@ -135,6 +135,46 @@ static void fpu_set_exception(CPUX86State *env, int mask)
     }
 }
 
+void cpu_init_fp_statuses(CPUX86State *env)
+{
+    /*
+     * Initialise the non-runtime-varying fields of the various
+     * float_status words to x86 behaviour. This must be called at
+     * CPU reset because the float_status words are in the
+     * "zeroed on reset" portion of the CPU state struct.
+     * Fields in float_status that vary under guest control are set
+     * via the codepath for setting that register, eg cpu_set_fpuc().
+     */
+    /*
+     * Use x87 NaN propagation rules:
+     * SNaN + QNaN => return the QNaN
+     * two SNaNs => return the one with the larger significand, silenced
+     * two QNaNs => return the one with the larger significand
+     * SNaN and a non-NaN => return the SNaN, silenced
+     * QNaN and a non-NaN => return the QNaN
+     *
+     * If we get down to comparing significands and they are the same,
+     * return the NaN with the positive sign bit (if any).
+     */
+    set_float_2nan_prop_rule(float_2nan_prop_x87, &env->fp_status);
+    /*
+     * TODO: These are incorrect: the x86 Software Developer's Manual vol 1
+     * section 4.8.3.5 "Operating on SNaNs and QNaNs" says that the
+     * "larger significand" behaviour is only used for x87 FPU operations.
+     * For SSE the required behaviour is to always return the first NaN,
+     * which is float_2nan_prop_ab.
+     *
+     * mmx_status is used only for the AMD 3DNow! instructions, which
+     * are documented in the "3DNow! Technology Manual" as not supporting
+     * NaNs or infinities as inputs. The result of passing two NaNs is
+     * documented as "undefined", so we can do what we choose.
+     * (Strictly there is some behaviour we don't implement correctly
+     * for these "unsupported" NaN and Inf values, like "NaN * 0 == 0".)
+     */
+    set_float_2nan_prop_rule(float_2nan_prop_x87, &env->mmx_status);
+    set_float_2nan_prop_rule(float_2nan_prop_x87, &env->sse_status);
+}
+
 static inline uint8_t save_exception_flags(CPUX86State *env)
 {
     uint8_t old_flags = get_float_exception_flags(&env->fp_status);
diff --git a/target/loongarch/tcg/fpu_helper.c b/target/loongarch/tcg/fpu_helper.c
index f6753c5875..21bc3b04a9 100644
--- a/target/loongarch/tcg/fpu_helper.c
+++ b/target/loongarch/tcg/fpu_helper.c
@@ -31,6 +31,7 @@ void restore_fp_status(CPULoongArchState *env)
     set_float_rounding_mode(ieee_rm[(env->fcsr0 >> FCSR0_RM) & 0x3],
                             &env->fp_status);
     set_flush_to_zero(0, &env->fp_status);
+    set_float_2nan_prop_rule(float_2nan_prop_s_ab, &env->fp_status);
 }
 
 int ieee_ex_to_loongarch(int xcpt)
diff --git a/target/m68k/cpu.c b/target/m68k/cpu.c
index 1d49f4cb23..5fe335558a 100644
--- a/target/m68k/cpu.c
+++ b/target/m68k/cpu.c
@@ -93,6 +93,22 @@ static void m68k_cpu_reset_hold(Object *obj, ResetType type)
         env->fregs[i].d = nan;
     }
     cpu_m68k_set_fpcr(env, 0);
+    /*
+     * M68000 FAMILY PROGRAMMER'S REFERENCE MANUAL
+     * 3.4 FLOATING-POINT INSTRUCTION DETAILS
+     * If either operand, but not both operands, of an operation is a
+     * nonsignaling NaN, then that NaN is returned as the result. If both
+     * operands are nonsignaling NaNs, then the destination operand
+     * nonsignaling NaN is returned as the result.
+     * If either operand to an operation is a signaling NaN (SNaN), then the
+     * SNaN bit is set in the FPSR EXC byte. If the SNaN exception enable bit
+     * is set in the FPCR ENABLE byte, then the exception is taken and the
+     * destination is not modified. If the SNaN exception enable bit is not
+     * set, setting the SNaN bit in the operand to a one converts the SNaN to
+     * a nonsignaling NaN. The operation then continues as described in the
+     * preceding paragraph for nonsignaling NaNs.
+     */
+    set_float_2nan_prop_rule(float_2nan_prop_ab, &env->fp_status);
     env->fpsr = 0;
 
     /* TODO: We should set PC from the interrupt vector.  */
diff --git a/target/m68k/fpu_helper.c b/target/m68k/fpu_helper.c
index 8314791f50..a605162b71 100644
--- a/target/m68k/fpu_helper.c
+++ b/target/m68k/fpu_helper.c
@@ -620,6 +620,7 @@ void HELPER(frem)(CPUM68KState *env, FPReg *res, FPReg *val0, FPReg *val1)
         int sign;
 
         /* Calculate quotient directly using round to nearest mode */
+        set_float_2nan_prop_rule(float_2nan_prop_ab, &fp_status);
         set_float_rounding_mode(float_round_nearest_even, &fp_status);
         set_floatx80_rounding_precision(
             get_floatx80_rounding_precision(&env->fp_status), &fp_status);
diff --git a/target/m68k/helper.c b/target/m68k/helper.c
index 9d3db8419d..9bfc6ae97c 100644
--- a/target/m68k/helper.c
+++ b/target/m68k/helper.c
@@ -36,7 +36,7 @@ static int cf_fpu_gdb_get_reg(CPUState *cs, GByteArray *mem_buf, int n)
     CPUM68KState *env = &cpu->env;
 
     if (n < 8) {
-        float_status s;
+        float_status s = {};
         return gdb_get_reg64(mem_buf, floatx80_to_float64(env->fregs[n].d, &s));
     }
     switch (n) {
@@ -56,7 +56,7 @@ static int cf_fpu_gdb_set_reg(CPUState *cs, uint8_t *mem_buf, int n)
     CPUM68KState *env = &cpu->env;
 
     if (n < 8) {
-        float_status s;
+        float_status s = {};
         env->fregs[n].d = float64_to_floatx80(ldq_be_p(mem_buf), &s);
         return 8;
     }
diff --git a/target/microblaze/cpu.c b/target/microblaze/cpu.c
index b322f06077..710eb1146c 100644
--- a/target/microblaze/cpu.c
+++ b/target/microblaze/cpu.c
@@ -201,6 +201,13 @@ static void mb_cpu_reset_hold(Object *obj, ResetType type)
 
     env->pc = cpu->cfg.base_vectors;
 
+    set_float_rounding_mode(float_round_nearest_even, &env->fp_status);
+    /*
+     * TODO: this is probably not the correct NaN propagation rule for
+     * this architecture.
+     */
+    set_float_2nan_prop_rule(float_2nan_prop_x87, &env->fp_status);
+
 #if defined(CONFIG_USER_ONLY)
     /* start in user mode with interrupts enabled.  */
     mb_cpu_write_msr(env, MSR_EE | MSR_IE | MSR_VM | MSR_UM);
@@ -311,15 +318,12 @@ static void mb_cpu_realizefn(DeviceState *dev, Error **errp)
 static void mb_cpu_initfn(Object *obj)
 {
     MicroBlazeCPU *cpu = MICROBLAZE_CPU(obj);
-    CPUMBState *env = &cpu->env;
 
     gdb_register_coprocessor(CPU(cpu), mb_cpu_gdb_read_stack_protect,
                              mb_cpu_gdb_write_stack_protect,
                              gdb_find_static_feature("microblaze-stack-protect.xml"),
                              0);
 
-    set_float_rounding_mode(float_round_nearest_even, &env->fp_status);
-
 #ifndef CONFIG_USER_ONLY
     /* Inbound IRQ and FIR lines */
     qdev_init_gpio_in(DEVICE(cpu), microblaze_cpu_set_irq, 2);
diff --git a/target/mips/cpu.c b/target/mips/cpu.c
index 9724e71a5e..d0a43b6d5c 100644
--- a/target/mips/cpu.c
+++ b/target/mips/cpu.c
@@ -407,9 +407,9 @@ static void mips_cpu_reset_hold(Object *obj, ResetType type)
     }
 
     msa_reset(env);
+    fp_reset(env);
 
     compute_hflags(env);
-    restore_fp_status(env);
     restore_pamask(env);
     cs->exception_index = EXCP_NONE;
 
diff --git a/target/mips/fpu_helper.h b/target/mips/fpu_helper.h
index ad1116e8c1..7c3c7897b4 100644
--- a/target/mips/fpu_helper.h
+++ b/target/mips/fpu_helper.h
@@ -44,6 +44,28 @@ static inline void restore_fp_status(CPUMIPSState *env)
     restore_snan_bit_mode(env);
 }
 
+static inline void fp_reset(CPUMIPSState *env)
+{
+    restore_fp_status(env);
+
+    /*
+     * According to MIPS specifications, if one of the two operands is
+     * a sNaN, a new qNaN has to be generated. This is done in
+     * floatXX_silence_nan(). For qNaN inputs the specifications
+     * says: "When possible, this QNaN result is one of the operand QNaN
+     * values." In practice it seems that most implementations choose
+     * the first operand if both operands are qNaN. In short this gives
+     * the following rules:
+     *  1. A if it is signaling
+     *  2. B if it is signaling
+     *  3. A (quiet)
+     *  4. B (quiet)
+     * A signaling NaN is always silenced before returning it.
+     */
+    set_float_2nan_prop_rule(float_2nan_prop_s_ab,
+                             &env->active_fpu.fp_status);
+}
+
 /* MSA */
 
 enum CPUMIPSMSADataFormat {
diff --git a/target/mips/msa.c b/target/mips/msa.c
index 61f1a9a593..9dffc428f5 100644
--- a/target/mips/msa.c
+++ b/target/mips/msa.c
@@ -49,6 +49,23 @@ void msa_reset(CPUMIPSState *env)
     set_float_detect_tininess(float_tininess_after_rounding,
                               &env->active_tc.msa_fp_status);
 
+    /*
+     * According to MIPS specifications, if one of the two operands is
+     * a sNaN, a new qNaN has to be generated. This is done in
+     * floatXX_silence_nan(). For qNaN inputs the specifications
+     * says: "When possible, this QNaN result is one of the operand QNaN
+     * values." In practice it seems that most implementations choose
+     * the first operand if both operands are qNaN. In short this gives
+     * the following rules:
+     *  1. A if it is signaling
+     *  2. B if it is signaling
+     *  3. A (quiet)
+     *  4. B (quiet)
+     * A signaling NaN is always silenced before returning it.
+     */
+    set_float_2nan_prop_rule(float_2nan_prop_s_ab,
+                             &env->active_tc.msa_fp_status);
+
     /* clear float_status exception flags */
     set_float_exception_flags(0, &env->active_tc.msa_fp_status);
 
diff --git a/target/openrisc/cpu.c b/target/openrisc/cpu.c
index 6ec54ad7a6..b96561d1f2 100644
--- a/target/openrisc/cpu.c
+++ b/target/openrisc/cpu.c
@@ -105,6 +105,12 @@ static void openrisc_cpu_reset_hold(Object *obj, ResetType type)
 
     set_float_detect_tininess(float_tininess_before_rounding,
                               &cpu->env.fp_status);
+    /*
+     * TODO: this is probably not the correct NaN propagation rule for
+     * this architecture.
+     */
+    set_float_2nan_prop_rule(float_2nan_prop_x87, &cpu->env.fp_status);
+
 
 #ifndef CONFIG_USER_ONLY
     cpu->env.picmr = 0x00000000;
diff --git a/target/ppc/cpu_init.c b/target/ppc/cpu_init.c
index 6f352550db..efcb80d1c2 100644
--- a/target/ppc/cpu_init.c
+++ b/target/ppc/cpu_init.c
@@ -7262,6 +7262,14 @@ static void ppc_cpu_reset_hold(Object *obj, ResetType type)
     /* tininess for underflow is detected before rounding */
     set_float_detect_tininess(float_tininess_before_rounding,
                               &env->fp_status);
+    /*
+     * PowerPC propagation rules:
+     *  1. A if it sNaN or qNaN
+     *  2. B if it sNaN or qNaN
+     * A signaling NaN is always silenced before returning it.
+     */
+    set_float_2nan_prop_rule(float_2nan_prop_ab, &env->fp_status);
+    set_float_2nan_prop_rule(float_2nan_prop_ab, &env->vec_status);
 
     for (i = 0; i < ARRAY_SIZE(env->spr_cb); i++) {
         ppc_spr_t *spr = &env->spr_cb[i];
diff --git a/target/rx/cpu.c b/target/rx/cpu.c
index 36d2a6f189..65a74ce720 100644
--- a/target/rx/cpu.c
+++ b/target/rx/cpu.c
@@ -93,6 +93,13 @@ static void rx_cpu_reset_hold(Object *obj, ResetType type)
     env->fpsw = 0;
     set_flush_to_zero(1, &env->fp_status);
     set_flush_inputs_to_zero(1, &env->fp_status);
+    /*
+     * TODO: this is not the correct NaN propagation rule for this
+     * architecture. The "RX Family User's Manual: Software" table 1.6
+     * defines the propagation rules as "prefer SNaN over QNaN;
+     * then prefer dest over source", which is float_2nan_prop_s_ab.
+     */
+    set_float_2nan_prop_rule(float_2nan_prop_x87, &env->fp_status);
 }
 
 static ObjectClass *rx_cpu_class_by_name(const char *cpu_model)
diff --git a/target/s390x/cpu.c b/target/s390x/cpu.c
index 4e41a3dff5..514c70f301 100644
--- a/target/s390x/cpu.c
+++ b/target/s390x/cpu.c
@@ -205,6 +205,7 @@ static void s390_cpu_reset_hold(Object *obj, ResetType type)
         /* tininess for underflow is detected before rounding */
         set_float_detect_tininess(float_tininess_before_rounding,
                                   &env->fpu_status);
+        set_float_2nan_prop_rule(float_2nan_prop_s_ab, &env->fpu_status);
        /* fall through */
     case RESET_TYPE_S390_CPU_NORMAL:
         env->psw.mask &= ~PSW_MASK_RI;
diff --git a/target/sparc/cpu.c b/target/sparc/cpu.c
index 54cb269e0a..dd7af86de7 100644
--- a/target/sparc/cpu.c
+++ b/target/sparc/cpu.c
@@ -26,6 +26,7 @@
 #include "hw/qdev-properties.h"
 #include "qapi/visitor.h"
 #include "tcg/tcg.h"
+#include "fpu/softfloat.h"
 
 //#define DEBUG_FEATURES
 
@@ -76,6 +77,7 @@ static void sparc_cpu_reset_hold(Object *obj, ResetType type)
     env->npc = env->pc + 4;
 #endif
     env->cache_control = 0;
+    cpu_put_fsr(env, 0);
 }
 
 #ifndef CONFIG_USER_ONLY
@@ -805,7 +807,13 @@ static void sparc_cpu_realizefn(DeviceState *dev, Error **errp)
     env->version |= env->def.maxtl << 8;
     env->version |= env->def.nwindows - 1;
 #endif
-    cpu_put_fsr(env, 0);
+
+    /*
+     * Prefer SNaN over QNaN, order B then A. It's OK to do this in realize
+     * rather than reset, because fp_status is after 'end_reset_fields' in
+     * the CPU state struct so it won't get zeroed on reset.
+     */
+    set_float_2nan_prop_rule(float_2nan_prop_s_ba, &env->fp_status);
 
     cpu_exec_realizefn(cs, &local_err);
     if (local_err != NULL) {
diff --git a/target/sparc/fop_helper.c b/target/sparc/fop_helper.c
index b6692382b3..6f9ccc008a 100644
--- a/target/sparc/fop_helper.c
+++ b/target/sparc/fop_helper.c
@@ -497,7 +497,10 @@ uint32_t helper_flcmps(float32 src1, float32 src2)
      * Perform the comparison with a dummy fp environment.
      */
     float_status discard = { };
-    FloatRelation r = float32_compare_quiet(src1, src2, &discard);
+    FloatRelation r;
+
+    set_float_2nan_prop_rule(float_2nan_prop_s_ba, &discard);
+    r = float32_compare_quiet(src1, src2, &discard);
 
     switch (r) {
     case float_relation_equal:
@@ -518,7 +521,10 @@ uint32_t helper_flcmps(float32 src1, float32 src2)
 uint32_t helper_flcmpd(float64 src1, float64 src2)
 {
     float_status discard = { };
-    FloatRelation r = float64_compare_quiet(src1, src2, &discard);
+    FloatRelation r;
+
+    set_float_2nan_prop_rule(float_2nan_prop_s_ba, &discard);
+    r = float64_compare_quiet(src1, src2, &discard);
 
     switch (r) {
     case float_relation_equal:
diff --git a/target/xtensa/cpu.c b/target/xtensa/cpu.c
index a08c7a0b1f..6f9039abae 100644
--- a/target/xtensa/cpu.c
+++ b/target/xtensa/cpu.c
@@ -134,7 +134,7 @@ static void xtensa_cpu_reset_hold(Object *obj, ResetType type)
     cs->halted = env->runstall;
 #endif
     set_no_signaling_nans(!dfpu, &env->fp_status);
-    set_use_first_nan(!dfpu, &env->fp_status);
+    xtensa_use_first_nan(env, !dfpu);
 }
 
 static ObjectClass *xtensa_cpu_class_by_name(const char *cpu_model)
diff --git a/target/xtensa/cpu.h b/target/xtensa/cpu.h
index 9f2341d856..77e48eef19 100644
--- a/target/xtensa/cpu.h
+++ b/target/xtensa/cpu.h
@@ -802,4 +802,10 @@ static inline void cpu_get_tb_cpu_state(CPUXtensaState *env, vaddr *pc,
 XtensaCPU *xtensa_cpu_create_with_clock(const char *cpu_type,
                                         Clock *cpu_refclk);
 
+/*
+ * Set the NaN propagation rule for future FPU operations:
+ * use_first is true to pick the first NaN as the result if both
+ * inputs are NaNs, false to pick the second.
+ */
+void xtensa_use_first_nan(CPUXtensaState *env, bool use_first);
 #endif
diff --git a/target/xtensa/fpu_helper.c b/target/xtensa/fpu_helper.c
index 381e83ded8..f2d212d05d 100644
--- a/target/xtensa/fpu_helper.c
+++ b/target/xtensa/fpu_helper.c
@@ -57,6 +57,13 @@ static const struct {
     { XTENSA_FP_V, float_flag_invalid, },
 };
 
+void xtensa_use_first_nan(CPUXtensaState *env, bool use_first)
+{
+    set_use_first_nan(use_first, &env->fp_status);
+    set_float_2nan_prop_rule(use_first ? float_2nan_prop_ab : float_2nan_prop_ba,
+                             &env->fp_status);
+}
+
 void HELPER(wur_fpu2k_fcr)(CPUXtensaState *env, uint32_t v)
 {
     static const int rounding_mode[] = {
@@ -171,87 +178,87 @@ float32 HELPER(fpu2k_msub_s)(CPUXtensaState *env,
 
 float64 HELPER(add_d)(CPUXtensaState *env, float64 a, float64 b)
 {
-    set_use_first_nan(true, &env->fp_status);
+    xtensa_use_first_nan(env, true);
     return float64_add(a, b, &env->fp_status);
 }
 
 float32 HELPER(add_s)(CPUXtensaState *env, float32 a, float32 b)
 {
-    set_use_first_nan(env->config->use_first_nan, &env->fp_status);
+    xtensa_use_first_nan(env, env->config->use_first_nan);
     return float32_add(a, b, &env->fp_status);
 }
 
 float64 HELPER(sub_d)(CPUXtensaState *env, float64 a, float64 b)
 {
-    set_use_first_nan(true, &env->fp_status);
+    xtensa_use_first_nan(env, true);
     return float64_sub(a, b, &env->fp_status);
 }
 
 float32 HELPER(sub_s)(CPUXtensaState *env, float32 a, float32 b)
 {
-    set_use_first_nan(env->config->use_first_nan, &env->fp_status);
+    xtensa_use_first_nan(env, env->config->use_first_nan);
     return float32_sub(a, b, &env->fp_status);
 }
 
 float64 HELPER(mul_d)(CPUXtensaState *env, float64 a, float64 b)
 {
-    set_use_first_nan(true, &env->fp_status);
+    xtensa_use_first_nan(env, true);
     return float64_mul(a, b, &env->fp_status);
 }
 
 float32 HELPER(mul_s)(CPUXtensaState *env, float32 a, float32 b)
 {
-    set_use_first_nan(env->config->use_first_nan, &env->fp_status);
+    xtensa_use_first_nan(env, env->config->use_first_nan);
     return float32_mul(a, b, &env->fp_status);
 }
 
 float64 HELPER(madd_d)(CPUXtensaState *env, float64 a, float64 b, float64 c)
 {
-    set_use_first_nan(env->config->use_first_nan, &env->fp_status);
+    xtensa_use_first_nan(env, env->config->use_first_nan);
     return float64_muladd(b, c, a, 0, &env->fp_status);
 }
 
 float32 HELPER(madd_s)(CPUXtensaState *env, float32 a, float32 b, float32 c)
 {
-    set_use_first_nan(env->config->use_first_nan, &env->fp_status);
+    xtensa_use_first_nan(env, env->config->use_first_nan);
     return float32_muladd(b, c, a, 0, &env->fp_status);
 }
 
 float64 HELPER(msub_d)(CPUXtensaState *env, float64 a, float64 b, float64 c)
 {
-    set_use_first_nan(env->config->use_first_nan, &env->fp_status);
+    xtensa_use_first_nan(env, env->config->use_first_nan);
     return float64_muladd(b, c, a, float_muladd_negate_product,
                           &env->fp_status);
 }
 
 float32 HELPER(msub_s)(CPUXtensaState *env, float32 a, float32 b, float32 c)
 {
-    set_use_first_nan(env->config->use_first_nan, &env->fp_status);
+    xtensa_use_first_nan(env, env->config->use_first_nan);
     return float32_muladd(b, c, a, float_muladd_negate_product,
                           &env->fp_status);
 }
 
 float64 HELPER(mkdadj_d)(CPUXtensaState *env, float64 a, float64 b)
 {
-    set_use_first_nan(true, &env->fp_status);
+    xtensa_use_first_nan(env, true);
     return float64_div(b, a, &env->fp_status);
 }
 
 float32 HELPER(mkdadj_s)(CPUXtensaState *env, float32 a, float32 b)
 {
-    set_use_first_nan(env->config->use_first_nan, &env->fp_status);
+    xtensa_use_first_nan(env, env->config->use_first_nan);
     return float32_div(b, a, &env->fp_status);
 }
 
 float64 HELPER(mksadj_d)(CPUXtensaState *env, float64 v)
 {
-    set_use_first_nan(true, &env->fp_status);
+    xtensa_use_first_nan(env, true);
     return float64_sqrt(v, &env->fp_status);
 }
 
 float32 HELPER(mksadj_s)(CPUXtensaState *env, float32 v)
 {
-    set_use_first_nan(env->config->use_first_nan, &env->fp_status);
+    xtensa_use_first_nan(env, env->config->use_first_nan);
     return float32_sqrt(v, &env->fp_status);
 }
 
diff --git a/tests/data/acpi/disassemle-aml.sh b/tests/data/acpi/disassemle-aml.sh
index 253b7620a0..89561d233d 100755
--- a/tests/data/acpi/disassemle-aml.sh
+++ b/tests/data/acpi/disassemle-aml.sh
@@ -14,7 +14,7 @@ while getopts "o:" arg; do
   esac
 done
 
-for machine in tests/data/acpi/*
+for machine in tests/data/acpi/*/*
 do
     if [[ ! -d "$machine" ]];
     then
diff --git a/tests/data/acpi/x86/pc/DSDT b/tests/data/acpi/x86/pc/DSDT
index 92225236e7..f68a32e606 100644
--- a/tests/data/acpi/x86/pc/DSDT
+++ b/tests/data/acpi/x86/pc/DSDT
Binary files differdiff --git a/tests/data/acpi/x86/pc/DSDT.acpierst b/tests/data/acpi/x86/pc/DSDT.acpierst
index 25b3995505..0fd79699eb 100644
--- a/tests/data/acpi/x86/pc/DSDT.acpierst
+++ b/tests/data/acpi/x86/pc/DSDT.acpierst
Binary files differdiff --git a/tests/data/acpi/x86/pc/DSDT.acpihmat b/tests/data/acpi/x86/pc/DSDT.acpihmat
index 73a9ce59e9..a4dd09e5ef 100644
--- a/tests/data/acpi/x86/pc/DSDT.acpihmat
+++ b/tests/data/acpi/x86/pc/DSDT.acpihmat
Binary files differdiff --git a/tests/data/acpi/x86/pc/DSDT.bridge b/tests/data/acpi/x86/pc/DSDT.bridge
index 4cef454e37..7ef58152d2 100644
--- a/tests/data/acpi/x86/pc/DSDT.bridge
+++ b/tests/data/acpi/x86/pc/DSDT.bridge
Binary files differdiff --git a/tests/data/acpi/x86/pc/DSDT.cphp b/tests/data/acpi/x86/pc/DSDT.cphp
index 1dc928333d..1079ff81c1 100644
--- a/tests/data/acpi/x86/pc/DSDT.cphp
+++ b/tests/data/acpi/x86/pc/DSDT.cphp
Binary files differdiff --git a/tests/data/acpi/x86/pc/DSDT.dimmpxm b/tests/data/acpi/x86/pc/DSDT.dimmpxm
index 9f71d2e58b..34fe3fcad9 100644
--- a/tests/data/acpi/x86/pc/DSDT.dimmpxm
+++ b/tests/data/acpi/x86/pc/DSDT.dimmpxm
Binary files differdiff --git a/tests/data/acpi/x86/pc/DSDT.hpbridge b/tests/data/acpi/x86/pc/DSDT.hpbridge
index db420593a3..33c7529f5c 100644
--- a/tests/data/acpi/x86/pc/DSDT.hpbridge
+++ b/tests/data/acpi/x86/pc/DSDT.hpbridge
Binary files differdiff --git a/tests/data/acpi/x86/pc/DSDT.hpbrroot b/tests/data/acpi/x86/pc/DSDT.hpbrroot
index 31b6adb4eb..2661170c83 100644
--- a/tests/data/acpi/x86/pc/DSDT.hpbrroot
+++ b/tests/data/acpi/x86/pc/DSDT.hpbrroot
Binary files differdiff --git a/tests/data/acpi/x86/pc/DSDT.ipmikcs b/tests/data/acpi/x86/pc/DSDT.ipmikcs
index c2a0330d97..688faf83cb 100644
--- a/tests/data/acpi/x86/pc/DSDT.ipmikcs
+++ b/tests/data/acpi/x86/pc/DSDT.ipmikcs
Binary files differdiff --git a/tests/data/acpi/x86/pc/DSDT.memhp b/tests/data/acpi/x86/pc/DSDT.memhp
index c15a9fae94..6ede4361f4 100644
--- a/tests/data/acpi/x86/pc/DSDT.memhp
+++ b/tests/data/acpi/x86/pc/DSDT.memhp
Binary files differdiff --git a/tests/data/acpi/x86/pc/DSDT.nohpet b/tests/data/acpi/x86/pc/DSDT.nohpet
index dd29f5cb62..9d6040733f 100644
--- a/tests/data/acpi/x86/pc/DSDT.nohpet
+++ b/tests/data/acpi/x86/pc/DSDT.nohpet
Binary files differdiff --git a/tests/data/acpi/x86/pc/DSDT.numamem b/tests/data/acpi/x86/pc/DSDT.numamem
index 8a6b56fe7d..aa9986f74b 100644
--- a/tests/data/acpi/x86/pc/DSDT.numamem
+++ b/tests/data/acpi/x86/pc/DSDT.numamem
Binary files differdiff --git a/tests/data/acpi/x86/pc/DSDT.roothp b/tests/data/acpi/x86/pc/DSDT.roothp
index a16b0d9d4b..86c2ae11dc 100644
--- a/tests/data/acpi/x86/pc/DSDT.roothp
+++ b/tests/data/acpi/x86/pc/DSDT.roothp
Binary files differdiff --git a/tests/data/acpi/x86/q35/DSDT b/tests/data/acpi/x86/q35/DSDT
index fb89ae0ac6..b0bbff7686 100644
--- a/tests/data/acpi/x86/q35/DSDT
+++ b/tests/data/acpi/x86/q35/DSDT
Binary files differdiff --git a/tests/data/acpi/x86/q35/DSDT.acpierst b/tests/data/acpi/x86/q35/DSDT.acpierst
index 46fd25400b..f91cbe55fc 100644
--- a/tests/data/acpi/x86/q35/DSDT.acpierst
+++ b/tests/data/acpi/x86/q35/DSDT.acpierst
Binary files differdiff --git a/tests/data/acpi/x86/q35/DSDT.acpihmat b/tests/data/acpi/x86/q35/DSDT.acpihmat
index 61c5bd52a4..0949fb9d67 100644
--- a/tests/data/acpi/x86/q35/DSDT.acpihmat
+++ b/tests/data/acpi/x86/q35/DSDT.acpihmat
Binary files differdiff --git a/tests/data/acpi/x86/q35/DSDT.acpihmat-noinitiator b/tests/data/acpi/x86/q35/DSDT.acpihmat-noinitiator
index 3aaa2bbdf5..0fa4daa35c 100644
--- a/tests/data/acpi/x86/q35/DSDT.acpihmat-noinitiator
+++ b/tests/data/acpi/x86/q35/DSDT.acpihmat-noinitiator
Binary files differdiff --git a/tests/data/acpi/x86/q35/DSDT.applesmc b/tests/data/acpi/x86/q35/DSDT.applesmc
index 944209adea..a5d032b7d9 100644
--- a/tests/data/acpi/x86/q35/DSDT.applesmc
+++ b/tests/data/acpi/x86/q35/DSDT.applesmc
Binary files differdiff --git a/tests/data/acpi/x86/q35/DSDT.bridge b/tests/data/acpi/x86/q35/DSDT.bridge
index d9938dba8f..3464f55297 100644
--- a/tests/data/acpi/x86/q35/DSDT.bridge
+++ b/tests/data/acpi/x86/q35/DSDT.bridge
Binary files differdiff --git a/tests/data/acpi/x86/q35/DSDT.core-count b/tests/data/acpi/x86/q35/DSDT.core-count
index a24b04cbdb..08f5d5f54b 100644
--- a/tests/data/acpi/x86/q35/DSDT.core-count
+++ b/tests/data/acpi/x86/q35/DSDT.core-count
Binary files differdiff --git a/tests/data/acpi/x86/q35/DSDT.core-count2 b/tests/data/acpi/x86/q35/DSDT.core-count2
index 3a0cb8c581..d29a7108f8 100644
--- a/tests/data/acpi/x86/q35/DSDT.core-count2
+++ b/tests/data/acpi/x86/q35/DSDT.core-count2
Binary files differdiff --git a/tests/data/acpi/x86/q35/DSDT.cphp b/tests/data/acpi/x86/q35/DSDT.cphp
index 20955d0aa3..7fd59bf670 100644
--- a/tests/data/acpi/x86/q35/DSDT.cphp
+++ b/tests/data/acpi/x86/q35/DSDT.cphp
Binary files differdiff --git a/tests/data/acpi/x86/q35/DSDT.cxl b/tests/data/acpi/x86/q35/DSDT.cxl
index f561750cab..613a40b957 100644
--- a/tests/data/acpi/x86/q35/DSDT.cxl
+++ b/tests/data/acpi/x86/q35/DSDT.cxl
Binary files differdiff --git a/tests/data/acpi/x86/q35/DSDT.dimmpxm b/tests/data/acpi/x86/q35/DSDT.dimmpxm
index 228374b55b..1db0bf454a 100644
--- a/tests/data/acpi/x86/q35/DSDT.dimmpxm
+++ b/tests/data/acpi/x86/q35/DSDT.dimmpxm
Binary files differdiff --git a/tests/data/acpi/x86/q35/DSDT.ipmibt b/tests/data/acpi/x86/q35/DSDT.ipmibt
index 45f911ada5..25f43ae8ef 100644
--- a/tests/data/acpi/x86/q35/DSDT.ipmibt
+++ b/tests/data/acpi/x86/q35/DSDT.ipmibt
Binary files differdiff --git a/tests/data/acpi/x86/q35/DSDT.ipmismbus b/tests/data/acpi/x86/q35/DSDT.ipmismbus
index e5d6811bee..32bcd25bda 100644
--- a/tests/data/acpi/x86/q35/DSDT.ipmismbus
+++ b/tests/data/acpi/x86/q35/DSDT.ipmismbus
Binary files differdiff --git a/tests/data/acpi/x86/q35/DSDT.ivrs b/tests/data/acpi/x86/q35/DSDT.ivrs
index 46fd25400b..f91cbe55fc 100644
--- a/tests/data/acpi/x86/q35/DSDT.ivrs
+++ b/tests/data/acpi/x86/q35/DSDT.ivrs
Binary files differdiff --git a/tests/data/acpi/x86/q35/DSDT.memhp b/tests/data/acpi/x86/q35/DSDT.memhp
index 5ce081187a..be90eb71d8 100644
--- a/tests/data/acpi/x86/q35/DSDT.memhp
+++ b/tests/data/acpi/x86/q35/DSDT.memhp
Binary files differdiff --git a/tests/data/acpi/x86/q35/DSDT.mmio64 b/tests/data/acpi/x86/q35/DSDT.mmio64
index bdf36c4d57..01f276a6af 100644
--- a/tests/data/acpi/x86/q35/DSDT.mmio64
+++ b/tests/data/acpi/x86/q35/DSDT.mmio64
Binary files differdiff --git a/tests/data/acpi/x86/q35/DSDT.multi-bridge b/tests/data/acpi/x86/q35/DSDT.multi-bridge
index 1db43a69e4..1bd2ee8d2e 100644
--- a/tests/data/acpi/x86/q35/DSDT.multi-bridge
+++ b/tests/data/acpi/x86/q35/DSDT.multi-bridge
Binary files differdiff --git a/tests/data/acpi/x86/q35/DSDT.noacpihp b/tests/data/acpi/x86/q35/DSDT.noacpihp
index 8bc16887e1..45cc2bcffa 100644
--- a/tests/data/acpi/x86/q35/DSDT.noacpihp
+++ b/tests/data/acpi/x86/q35/DSDT.noacpihp
Binary files differdiff --git a/tests/data/acpi/x86/q35/DSDT.nohpet b/tests/data/acpi/x86/q35/DSDT.nohpet
index c13e45e361..f110504b9c 100644
--- a/tests/data/acpi/x86/q35/DSDT.nohpet
+++ b/tests/data/acpi/x86/q35/DSDT.nohpet
Binary files differdiff --git a/tests/data/acpi/x86/q35/DSDT.numamem b/tests/data/acpi/x86/q35/DSDT.numamem
index ba6669437e..6090958f39 100644
--- a/tests/data/acpi/x86/q35/DSDT.numamem
+++ b/tests/data/acpi/x86/q35/DSDT.numamem
Binary files differdiff --git a/tests/data/acpi/x86/q35/DSDT.pvpanic-isa b/tests/data/acpi/x86/q35/DSDT.pvpanic-isa
index 6ad42873e9..7a8e568315 100644
--- a/tests/data/acpi/x86/q35/DSDT.pvpanic-isa
+++ b/tests/data/acpi/x86/q35/DSDT.pvpanic-isa
Binary files differdiff --git a/tests/data/acpi/x86/q35/DSDT.thread-count b/tests/data/acpi/x86/q35/DSDT.thread-count
index a24b04cbdb..08f5d5f54b 100644
--- a/tests/data/acpi/x86/q35/DSDT.thread-count
+++ b/tests/data/acpi/x86/q35/DSDT.thread-count
Binary files differdiff --git a/tests/data/acpi/x86/q35/DSDT.thread-count2 b/tests/data/acpi/x86/q35/DSDT.thread-count2
index 3a0cb8c581..d29a7108f8 100644
--- a/tests/data/acpi/x86/q35/DSDT.thread-count2
+++ b/tests/data/acpi/x86/q35/DSDT.thread-count2
Binary files differdiff --git a/tests/data/acpi/x86/q35/DSDT.tis.tpm12 b/tests/data/acpi/x86/q35/DSDT.tis.tpm12
index e381ce4cbf..29a416f050 100644
--- a/tests/data/acpi/x86/q35/DSDT.tis.tpm12
+++ b/tests/data/acpi/x86/q35/DSDT.tis.tpm12
Binary files differdiff --git a/tests/data/acpi/x86/q35/DSDT.tis.tpm2 b/tests/data/acpi/x86/q35/DSDT.tis.tpm2
index a09253042c..59288f02c4 100644
--- a/tests/data/acpi/x86/q35/DSDT.tis.tpm2
+++ b/tests/data/acpi/x86/q35/DSDT.tis.tpm2
Binary files differdiff --git a/tests/data/acpi/x86/q35/DSDT.type4-count b/tests/data/acpi/x86/q35/DSDT.type4-count
index edc23198cd..eaca76e8e6 100644
--- a/tests/data/acpi/x86/q35/DSDT.type4-count
+++ b/tests/data/acpi/x86/q35/DSDT.type4-count
Binary files differdiff --git a/tests/data/acpi/x86/q35/DSDT.viot b/tests/data/acpi/x86/q35/DSDT.viot
index 8d98dd8845..de0942a13d 100644
--- a/tests/data/acpi/x86/q35/DSDT.viot
+++ b/tests/data/acpi/x86/q35/DSDT.viot
Binary files differdiff --git a/tests/data/acpi/x86/q35/DSDT.xapic b/tests/data/acpi/x86/q35/DSDT.xapic
index d4acd851c6..9059812b58 100644
--- a/tests/data/acpi/x86/q35/DSDT.xapic
+++ b/tests/data/acpi/x86/q35/DSDT.xapic
Binary files differdiff --git a/tests/fp/fp-bench.c b/tests/fp/fp-bench.c
index 8ce0ca1545..75c07d5d1f 100644
--- a/tests/fp/fp-bench.c
+++ b/tests/fp/fp-bench.c
@@ -488,6 +488,8 @@ static void run_bench(void)
 {
     bench_func_t f;
 
+    set_float_2nan_prop_rule(float_2nan_prop_s_ab, &soft_status);
+
     f = bench_funcs[operation][precision];
     g_assert(f);
     f();
diff --git a/tests/fp/fp-test-log2.c b/tests/fp/fp-test-log2.c
index 4eae93eb7c..de702c4c80 100644
--- a/tests/fp/fp-test-log2.c
+++ b/tests/fp/fp-test-log2.c
@@ -70,6 +70,7 @@ int main(int ac, char **av)
     float_status qsf = {0};
     int i;
 
+    set_float_2nan_prop_rule(float_2nan_prop_s_ab, &qsf);
     set_float_rounding_mode(float_round_nearest_even, &qsf);
 
     test.d = 0.0;
diff --git a/tests/fp/fp-test.c b/tests/fp/fp-test.c
index 36b5712cda..5f6f25c882 100644
--- a/tests/fp/fp-test.c
+++ b/tests/fp/fp-test.c
@@ -935,6 +935,8 @@ void run_test(void)
 {
     unsigned int i;
 
+    set_float_2nan_prop_rule(float_2nan_prop_s_ab, &qsf);
+
     genCases_setLevel(test_level);
     verCases_maxErrorCount = n_max_errors;
 
diff --git a/tests/qtest/fuzz-virtio-balloon-test.c b/tests/qtest/fuzz-virtio-balloon-test.c
new file mode 100644
index 0000000000..ecb597fbee
--- /dev/null
+++ b/tests/qtest/fuzz-virtio-balloon-test.c
@@ -0,0 +1,37 @@
+/*
+ * QTest fuzzer-generated testcase for virtio balloon device
+ *
+ * Copyright (c) 2024 Gao Shiyuan <gaoshiyuan@baidu.com>
+ *
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ */
+
+#include "qemu/osdep.h"
+#include "libqtest.h"
+
+/*
+ * https://gitlab.com/qemu-project/qemu/-/issues/2576
+ * Used to trigger:
+ *   virtio_address_space_lookup: Assertion `mrs.mr' failed.
+ */
+static void oss_fuzz_71649(void)
+{
+    QTestState *s = qtest_init("-device virtio-balloon -machine q35"
+                               " -nodefaults");
+
+    qtest_outl(s, 0xcf8, 0x80000890);
+    qtest_outl(s, 0xcfc, 0x2);
+    qtest_outl(s, 0xcf8, 0x80000891);
+    qtest_inl(s, 0xcfc);
+    qtest_quit(s);
+}
+
+int main(int argc, char **argv)
+{
+    g_test_init(&argc, &argv, NULL);
+
+    qtest_add_func("fuzz/virtio/oss_fuzz_71649", oss_fuzz_71649);
+
+    return g_test_run();
+}
+
diff --git a/tests/qtest/meson.build b/tests/qtest/meson.build
index 0dbdb59a55..aa93e98418 100644
--- a/tests/qtest/meson.build
+++ b/tests/qtest/meson.build
@@ -88,6 +88,7 @@ qtests_i386 = \
   (config_all_devices.has_key('CONFIG_MEGASAS_SCSI_PCI') ? ['fuzz-megasas-test'] : []) +    \
   (config_all_devices.has_key('CONFIG_LSI_SCSI_PCI') ? ['fuzz-lsi53c895a-test'] : []) +     \
   (config_all_devices.has_key('CONFIG_VIRTIO_SCSI') ? ['fuzz-virtio-scsi-test'] : []) +     \
+  (config_all_devices.has_key('CONFIG_VIRTIO_BALLOON') ? ['fuzz-virtio-balloon-test'] : []) + \
   (config_all_devices.has_key('CONFIG_Q35') ? ['q35-test'] : []) +                          \
   (config_all_devices.has_key('CONFIG_SB16') ? ['fuzz-sb16-test'] : []) +                   \
   (config_all_devices.has_key('CONFIG_SDHCI_PCI') ? ['fuzz-sdcard-test'] : []) +            \
diff --git a/tests/tcg/Makefile.target b/tests/tcg/Makefile.target
index 9722145b97..95ff76ea44 100644
--- a/tests/tcg/Makefile.target
+++ b/tests/tcg/Makefile.target
@@ -179,10 +179,10 @@ run-plugin-%-with-libmem.so: PLUGIN_ARGS=$(COMMA)inline=true
 
 ifeq ($(filter %-softmmu, $(TARGET)),)
 run-%: %
-	$(call run-test, $<, $(QEMU) $(QEMU_OPTS) $<)
+	$(call run-test, $<, env QEMU=$(QEMU) $(QEMU) $(QEMU_OPTS) $<)
 
 run-plugin-%:
-	$(call run-test, $@, $(QEMU) $(QEMU_OPTS) \
+	$(call run-test, $@, env QEMU=$(QEMU) $(QEMU) $(QEMU_OPTS) \
 		-plugin $(PLUGIN_LIB)/$(call extract-plugin,$@)$(PLUGIN_ARGS) \
 		-d plugin -D $*.pout \
 		 $(call strip-plugin,$<))
diff --git a/tests/tcg/multiarch/linux/linux-sigrtminmax.c b/tests/tcg/multiarch/linux/linux-sigrtminmax.c
new file mode 100644
index 0000000000..a7059aacd9
--- /dev/null
+++ b/tests/tcg/multiarch/linux/linux-sigrtminmax.c
@@ -0,0 +1,74 @@
+/*
+ * Test the lowest and the highest real-time signals.
+ *
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ */
+#include <assert.h>
+#include <signal.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+/* For hexagon and microblaze. */
+#ifndef __SIGRTMIN
+#define __SIGRTMIN 32
+#endif
+
+extern char **environ;
+
+static bool seen_sigrtmin, seen_sigrtmax;
+
+static void handle_signal(int sig)
+{
+    if (sig == SIGRTMIN) {
+        seen_sigrtmin = true;
+    } else if (sig == SIGRTMAX) {
+        seen_sigrtmax = true;
+    } else {
+        _exit(1);
+    }
+}
+
+int main(int argc, char **argv)
+{
+    char *qemu = getenv("QEMU");
+    struct sigaction act;
+
+    assert(qemu);
+
+    if (!getenv("QEMU_RTSIG_MAP")) {
+        char **new_argv = malloc((argc + 2) + sizeof(char *));
+        int tsig1, hsig1, count1, tsig2, hsig2, count2;
+        char rt_sigmap[64];
+
+        /* Re-exec with a mapping that includes SIGRTMIN and SIGRTMAX. */
+        new_argv[0] = qemu;
+        memcpy(&new_argv[1], argv, (argc + 1) * sizeof(char *));
+        tsig1 = __SIGRTMIN;
+        /* The host must have a few signals starting from this one. */
+        hsig1 = 36;
+        count1 = SIGRTMIN - __SIGRTMIN + 1;
+        tsig2 = SIGRTMAX;
+        hsig2 = hsig1 + count1;
+        count2 = 1;
+        snprintf(rt_sigmap, sizeof(rt_sigmap), "%d %d %d,%d %d %d",
+                 tsig1, hsig1, count1, tsig2, hsig2, count2);
+        setenv("QEMU_RTSIG_MAP", rt_sigmap, 0);
+        assert(execve(new_argv[0], new_argv, environ) == 0);
+        return EXIT_FAILURE;
+    }
+
+    memset(&act, 0, sizeof(act));
+    act.sa_handler = handle_signal;
+    assert(sigaction(SIGRTMIN, &act, NULL) == 0);
+    assert(sigaction(SIGRTMAX, &act, NULL) == 0);
+
+    assert(kill(getpid(), SIGRTMIN) == 0);
+    assert(seen_sigrtmin);
+    assert(kill(getpid(), SIGRTMAX) == 0);
+    assert(seen_sigrtmax);
+
+    return EXIT_SUCCESS;
+}
diff --git a/tests/unit/test-crypto-hash.c b/tests/unit/test-crypto-hash.c
index 76c4699c15..8fee1593f9 100644
--- a/tests/unit/test-crypto-hash.c
+++ b/tests/unit/test-crypto-hash.c
@@ -43,6 +43,9 @@
                       "63b54e4cb2d2032b393994aa263c0dbb" \
                       "e00a9f2fe9ef6037352232a1eec55ee7"
 #define OUTPUT_RIPEMD160 "f3d658fad3fdfb2b52c9369cf0d441249ddfa8a0"
+#ifdef CONFIG_CRYPTO_SM3
+#define OUTPUT_SM3 "d4a97db105b477b84c4f20ec9c31a6c814e2705a0b83a5a89748d75f0ef456a1"
+#endif
 
 #define OUTPUT_MD5_B64 "Yo0gY3FWMDWrjvYvSSveyQ=="
 #define OUTPUT_SHA1_B64 "sudPJnWKOkIeUJzuBFJEt4dTzAI="
@@ -55,6 +58,10 @@
                           "7sVe5w=="
 #define OUTPUT_RIPEMD160_B64 "89ZY+tP9+ytSyTac8NRBJJ3fqKA="
 
+#ifdef CONFIG_CRYPTO_SM3
+#define OUTPUT_SM3_B64 "1Kl9sQW0d7hMTyDsnDGmyBTicFoLg6Wol0jXXw70VqE="
+#endif
+
 static const char *expected_outputs[] = {
     [QCRYPTO_HASH_ALGO_MD5] = OUTPUT_MD5,
     [QCRYPTO_HASH_ALGO_SHA1] = OUTPUT_SHA1,
@@ -63,6 +70,9 @@ static const char *expected_outputs[] = {
     [QCRYPTO_HASH_ALGO_SHA384] = OUTPUT_SHA384,
     [QCRYPTO_HASH_ALGO_SHA512] = OUTPUT_SHA512,
     [QCRYPTO_HASH_ALGO_RIPEMD160] = OUTPUT_RIPEMD160,
+#ifdef CONFIG_CRYPTO_SM3
+    [QCRYPTO_HASH_ALGO_SM3] = OUTPUT_SM3,
+#endif
 };
 static const char *expected_outputs_b64[] = {
     [QCRYPTO_HASH_ALGO_MD5] = OUTPUT_MD5_B64,
@@ -72,6 +82,9 @@ static const char *expected_outputs_b64[] = {
     [QCRYPTO_HASH_ALGO_SHA384] = OUTPUT_SHA384_B64,
     [QCRYPTO_HASH_ALGO_SHA512] = OUTPUT_SHA512_B64,
     [QCRYPTO_HASH_ALGO_RIPEMD160] = OUTPUT_RIPEMD160_B64,
+#ifdef CONFIG_CRYPTO_SM3
+    [QCRYPTO_HASH_ALGO_SM3] = OUTPUT_SM3_B64,
+#endif
 };
 static const int expected_lens[] = {
     [QCRYPTO_HASH_ALGO_MD5] = 16,
@@ -81,6 +94,9 @@ static const int expected_lens[] = {
     [QCRYPTO_HASH_ALGO_SHA384] = 48,
     [QCRYPTO_HASH_ALGO_SHA512] = 64,
     [QCRYPTO_HASH_ALGO_RIPEMD160] = 20,
+#ifdef CONFIG_CRYPTO_SM3
+    [QCRYPTO_HASH_ALGO_SM3] = 32,
+#endif
 };
 
 static const char hex[] = "0123456789abcdef";
diff --git a/tests/unit/test-crypto-hmac.c b/tests/unit/test-crypto-hmac.c
index cdb8774443..20c60eb9d8 100644
--- a/tests/unit/test-crypto-hmac.c
+++ b/tests/unit/test-crypto-hmac.c
@@ -76,6 +76,14 @@ static QCryptoHmacTestData test_data[] = {
             "94964ed4c1155b62b668c241d67279e5"
             "8a711676",
     },
+#ifdef CONFIG_CRYPTO_SM3
+    {
+        .alg = QCRYPTO_HASH_ALGO_SM3,
+        .hex_digest =
+            "760e3799332bc913819b930085360ddb"
+    "c05529261313d5b15b75bab4fd7ae91e",
+    },
+#endif
 };
 
 static const char hex[] = "0123456789abcdef";
diff --git a/tests/unit/test-crypto-pbkdf.c b/tests/unit/test-crypto-pbkdf.c
index 12ee808fbc..ddb7244e21 100644
--- a/tests/unit/test-crypto-pbkdf.c
+++ b/tests/unit/test-crypto-pbkdf.c
@@ -325,6 +325,22 @@ static QCryptoPbkdfTestData test_data[] = {
                "\xce\xbf\x91\x14\x8b\x5c\x48\x41",
         .nout = 32
     },
+#ifdef CONFIG_CRYPTO_SM3
+    {
+        .path = "/crypto/pbkdf/nonrfc/sm3/iter2",
+        .hash = QCRYPTO_HASH_ALGO_SM3,
+        .iterations = 2,
+        .key = "password",
+        .nkey = 8,
+        .salt = "ATHENA.MIT.EDUraeburn",
+        .nsalt = 21,
+        .out = "\x48\x71\x1b\x58\xa3\xcb\xce\x06"
+ "\xba\xad\x77\xa8\xb5\xb9\xd8\x07"
+ "\x6a\xe2\xb3\x5b\x95\xce\xc8\xce"
+ "\xe7\xb1\xcb\xee\x61\xdf\x04\xea",
+        .nout = 32
+    },
+#endif
 #if 0
     {
         .path = "/crypto/pbkdf/nonrfc/whirlpool/iter1200",