Merge remote-tracking branch 'upstream/master' into main

MAINTAINERS

@@ -2189,6 +2189,7 @@ F: tests/qtest/prom-env-test.c
 
 VM Generation ID
 S: Orphan
+R: Ani Sinha <ani@anisinha.ca>
 F: hw/acpi/vmgenid.c
 F: include/hw/acpi/vmgenid.h
 F: docs/specs/vmgenid.txt
@@ -2204,6 +2205,7 @@ F: hw/misc/led.c
 Unimplemented device
 M: Peter Maydell <peter.maydell@linaro.org>
 R: Philippe Mathieu-Daudé <f4bug@amsat.org>
+R: Ani Sinha <ani@anisinha.ca>
 S: Maintained
 F: include/hw/misc/unimp.h
 F: hw/misc/unimp.c
@@ -2211,6 +2213,7 @@ F: hw/misc/unimp.c
 Empty slot
 M: Artyom Tarasenko <atar4qemu@gmail.com>
 R: Philippe Mathieu-Daudé <f4bug@amsat.org>
+R: Ani Sinha <ani@anisinha.ca>
 S: Maintained
 F: include/hw/misc/empty_slot.h
 F: hw/misc/empty_slot.c
@@ -2413,6 +2416,7 @@ F: audio/alsaaudio.c
 Core Audio framework backend
 M: Gerd Hoffmann <kraxel@redhat.com>
 R: Christian Schoenebeck <qemu_oss@crudebyte.com>
+R: Akihiko Odaki <akihiko.odaki@gmail.com>
 S: Odd Fixes
 F: audio/coreaudio.c
 
@@ -2665,6 +2669,7 @@ F: util/drm.c
 
 Cocoa graphics
 M: Peter Maydell <peter.maydell@linaro.org>
+R: Akihiko Odaki <akihiko.odaki@gmail.com>
 S: Odd Fixes
 F: ui/cocoa.m
 
@@ -2985,10 +2990,11 @@ F: docs/sphinx/fakedbusdoc.py
 F: tests/qtest/dbus*
 
 Seccomp
-M: Eduardo Otubo <otubo@redhat.com>
+M: Daniel P. Berrange <berrange@redhat.com>
-S: Supported
+S: Odd Fixes
 F: softmmu/qemu-seccomp.c
 F: include/sysemu/seccomp.h
+F: tests/unit/test-seccomp.c
 
 Cryptography
 M: Daniel P. Berrange <berrange@redhat.com>

accel/tcg/translate-all.c

@@ -51,6 +51,7 @@
 #include "qemu/qemu-print.h"
 #include "qemu/timer.h"
 #include "qemu/main-loop.h"
+#include "qemu/cacheinfo.h"
 #include "exec/log.h"
 #include "sysemu/cpus.h"
 #include "sysemu/cpu-timers.h"

backends/hostmem-file.c

@@ -14,6 +14,7 @@
 #include "qapi/error.h"
 #include "qemu/error-report.h"
 #include "qemu/module.h"
+#include "qemu/madvise.h"
 #include "sysemu/hostmem.h"
 #include "qom/object_interfaces.h"
 #include "qom/object.h"

backends/hostmem.c

@@ -19,6 +19,7 @@
 #include "qemu/config-file.h"
 #include "qom/object_interfaces.h"
 #include "qemu/mmap-alloc.h"
+#include "qemu/madvise.h"
 
 #ifdef CONFIG_NUMA
 #include <numaif.h>

backends/tpm/meson.build

@@ -1,8 +1,6 @@
-tpm_ss = ss.source_set()
+if have_tpm
-
+  softmmu_ss.add(files('tpm_backend.c'))
-tpm_ss.add(files('tpm_backend.c'))
+  softmmu_ss.add(files('tpm_util.c'))
-tpm_ss.add(files('tpm_util.c'))
+  softmmu_ss.add(when: 'CONFIG_TPM_PASSTHROUGH', if_true: files('tpm_passthrough.c'))
-tpm_ss.add(when: 'CONFIG_TPM_PASSTHROUGH', if_true: files('tpm_passthrough.c'))
+  softmmu_ss.add(when: 'CONFIG_TPM_EMULATOR', if_true: files('tpm_emulator.c'))
-tpm_ss.add(when: 'CONFIG_TPM_EMULATOR', if_true: files('tpm_emulator.c'))
+endif
-
-softmmu_ss.add_all(when: 'CONFIG_TPM', if_true: tpm_ss)

block/meson.build

@@ -45,25 +45,44 @@ block_ss.add(files(
 
 softmmu_ss.add(when: 'CONFIG_TCG', if_true: files('blkreplay.c'))
 
-block_ss.add(when: 'CONFIG_QCOW1', if_true: files('qcow.c'))
+if get_option('qcow1').allowed()
-block_ss.add(when: 'CONFIG_VDI', if_true: files('vdi.c'))
+  block_ss.add(files('qcow.c'))
-block_ss.add(when: 'CONFIG_CLOOP', if_true: files('cloop.c'))
+endif
-block_ss.add(when: 'CONFIG_BOCHS', if_true: files('bochs.c'))
+if get_option('vdi').allowed()
-block_ss.add(when: 'CONFIG_VVFAT', if_true: files('vvfat.c'))
+  block_ss.add(files('vdi.c'))
-block_ss.add(when: 'CONFIG_DMG', if_true: files('dmg.c'))
+endif
-block_ss.add(when: 'CONFIG_QED', if_true: files(
+if get_option('cloop').allowed()
+  block_ss.add(files('cloop.c'))
+endif
+if get_option('bochs').allowed()
+  block_ss.add(files('bochs.c'))
+endif
+if get_option('vvfat').allowed()
+  block_ss.add(files('vvfat.c'))
+endif
+if get_option('dmg').allowed()
+  block_ss.add(files('dmg.c'))
+endif
+if get_option('qed').allowed()
+  block_ss.add(files(
     'qed-check.c',
     'qed-cluster.c',
     'qed-l2-cache.c',
     'qed-table.c',
     'qed.c',
-))
+  ))
-block_ss.add(when: 'CONFIG_PARALLELS', if_true: files('parallels.c', 'parallels-ext.c'))
+endif
+if get_option('parallels').allowed()
+  block_ss.add(files('parallels.c', 'parallels-ext.c'))
+endif
+
 block_ss.add(when: 'CONFIG_WIN32', if_true: files('file-win32.c', 'win32-aio.c'))
 block_ss.add(when: 'CONFIG_POSIX', if_true: [files('file-posix.c'), coref, iokit])
 block_ss.add(when: libiscsi, if_true: files('iscsi-opts.c'))
 block_ss.add(when: 'CONFIG_LINUX', if_true: files('nvme.c'))
-block_ss.add(when: 'CONFIG_REPLICATION', if_true: files('replication.c'))
+if not get_option('replication').disabled()
+  block_ss.add(files('replication.c'))
+endif
 block_ss.add(when: libaio, if_true: files('linux-aio.c'))
 block_ss.add(when: linux_io_uring, if_true: files('io_uring.c'))
 
@@ -89,7 +108,7 @@ foreach m : [
 endforeach
 
 # those are not exactly regular block modules, so treat them apart
-if 'CONFIG_DMG' in config_host
+if get_option('dmg').allowed()
   foreach m : [
     [liblzfse, 'dmg-lzfse', liblzfse, 'dmg-lzfse.c'],
     [libbzip2, 'dmg-bz2', [glib, libbzip2], 'dmg-bz2.c']

block/ssh.c

@@ -386,14 +386,28 @@ static int compare_fingerprint(const unsigned char *fingerprint, size_t len,
     return *host_key_check - '\0';
 }
 
+static char *format_fingerprint(const unsigned char *fingerprint, size_t len)
+{
+    static const char *hex = "0123456789abcdef";
+    char *ret = g_new0(char, (len * 2) + 1);
+    for (size_t i = 0; i < len; i++) {
+        ret[i * 2] = hex[((fingerprint[i] >> 4) & 0xf)];
+        ret[(i * 2) + 1] = hex[(fingerprint[i] & 0xf)];
+    }
+    ret[len * 2] = '\0';
+    return ret;
+}
+
 static int
 check_host_key_hash(BDRVSSHState *s, const char *hash,
-                    enum ssh_publickey_hash_type type, Error **errp)
+                    enum ssh_publickey_hash_type type, const char *typestr,
+                    Error **errp)
 {
     int r;
     ssh_key pubkey;
     unsigned char *server_hash;
     size_t server_hash_len;
+    const char *keytype;
 
     r = ssh_get_server_publickey(s->session, &pubkey);
     if (r != SSH_OK) {
@@ -401,6 +415,8 @@ check_host_key_hash(BDRVSSHState *s, const char *hash,
         return -EINVAL;
     }
 
+    keytype = ssh_key_type_to_char(ssh_key_type(pubkey));
+
     r = ssh_get_publickey_hash(pubkey, type, &server_hash, &server_hash_len);
     ssh_key_free(pubkey);
     if (r != 0) {
@@ -410,12 +426,16 @@ check_host_key_hash(BDRVSSHState *s, const char *hash,
     }
 
     r = compare_fingerprint(server_hash, server_hash_len, hash);
-    ssh_clean_pubkey_hash(&server_hash);
     if (r != 0) {
-        error_setg(errp, "remote host key does not match host_key_check '%s'",
+        g_autofree char *server_fp = format_fingerprint(server_hash,
-                   hash);
+                                                        server_hash_len);
+        error_setg(errp, "remote host %s key fingerprint '%s:%s' "
+                   "does not match host_key_check '%s:%s'",
+                   keytype, typestr, server_fp, typestr, hash);
+        ssh_clean_pubkey_hash(&server_hash);
         return -EPERM;
     }
+    ssh_clean_pubkey_hash(&server_hash);
 
     return 0;
 }
@@ -436,13 +456,16 @@ static int check_host_key(BDRVSSHState *s, SshHostKeyCheck *hkc, Error **errp)
     case SSH_HOST_KEY_CHECK_MODE_HASH:
         if (hkc->u.hash.type == SSH_HOST_KEY_CHECK_HASH_TYPE_MD5) {
             return check_host_key_hash(s, hkc->u.hash.hash,
-                                       SSH_PUBLICKEY_HASH_MD5, errp);
+                                       SSH_PUBLICKEY_HASH_MD5, "md5",
+                                       errp);
         } else if (hkc->u.hash.type == SSH_HOST_KEY_CHECK_HASH_TYPE_SHA1) {
             return check_host_key_hash(s, hkc->u.hash.hash,
-                                       SSH_PUBLICKEY_HASH_SHA1, errp);
+                                       SSH_PUBLICKEY_HASH_SHA1, "sha1",
+                                       errp);
         } else if (hkc->u.hash.type == SSH_HOST_KEY_CHECK_HASH_TYPE_SHA256) {
             return check_host_key_hash(s, hkc->u.hash.hash,
-                                       SSH_PUBLICKEY_HASH_SHA256, errp);
+                                       SSH_PUBLICKEY_HASH_SHA256, "sha256",
+                                       errp);
         }
         g_assert_not_reached();
         break;
@@ -556,6 +579,11 @@ static bool ssh_process_legacy_options(QDict *output_opts,
             qdict_put_str(output_opts, "host-key-check.type", "sha1");
             qdict_put_str(output_opts, "host-key-check.hash",
                           &host_key_check[5]);
+        } else if (strncmp(host_key_check, "sha256:", 7) == 0) {
+            qdict_put_str(output_opts, "host-key-check.mode", "hash");
+            qdict_put_str(output_opts, "host-key-check.type", "sha256");
+            qdict_put_str(output_opts, "host-key-check.hash",
+                          &host_key_check[7]);
         } else if (strcmp(host_key_check, "yes") == 0) {
             qdict_put_str(output_opts, "host-key-check.mode", "known_hosts");
         } else {

bsd-user/signal.c

@@ -19,6 +19,7 @@
  */
 
 #include "qemu/osdep.h"
+#include "qemu/log.h"
 #include "qemu.h"
 #include "signal-common.h"
 #include "trace.h"

configure

@@ -238,9 +238,7 @@ cross_prefix=""
 audio_drv_list="default"
 block_drv_rw_whitelist=""
 block_drv_ro_whitelist=""
-block_drv_whitelist_tools="no"
 host_cc="cc"
-libs_qga=""
 debug_info="yes"
 lto="false"
 stack_protector=""
@@ -290,7 +288,6 @@ EXTRA_CXXFLAGS=""
 EXTRA_LDFLAGS=""
 
 xen_ctrl_version="$default_feature"
-membarrier="$default_feature"
 vhost_kernel="$default_feature"
 vhost_net="$default_feature"
 vhost_crypto="$default_feature"
@@ -301,7 +298,6 @@ vhost_user_fs="$default_feature"
 vhost_vdpa="$default_feature"
 rdma="$default_feature"
 pvrdma="$default_feature"
-gprof="no"
 debug_tcg="no"
 debug="no"
 sanitizers="no"
@@ -313,57 +309,36 @@ modules="no"
 module_upgrades="no"
 prefix="/usr/local"
 qemu_suffix="qemu"
-profiler="no"
 softmmu="yes"
 linux_user=""
 bsd_user=""
 pkgversion=""
 pie=""
-qom_cast_debug="yes"
 trace_backends="log"
 trace_file="trace"
 opengl="$default_feature"
-cpuid_h="no"
-avx2_opt="$default_feature"
-guest_agent="$default_feature"
-vss_win32_sdk="$default_feature"
-win_sdk="no"
-want_tools="$default_feature"
 coroutine=""
-coroutine_pool="$default_feature"
-debug_stack_usage="no"
-crypto_afalg="no"
 tls_priority="NORMAL"
-tpm="$default_feature"
-live_block_migration=${default_feature:-yes}
-numa="$default_feature"
-replication=${default_feature:-yes}
-bochs=${default_feature:-yes}
-cloop=${default_feature:-yes}
-dmg=${default_feature:-yes}
-qcow1=${default_feature:-yes}
-vdi=${default_feature:-yes}
-vvfat=${default_feature:-yes}
-qed=${default_feature:-yes}
-parallels=${default_feature:-yes}
-debug_mutex="no"
 plugins="$default_feature"
-rng_none="no"
 secret_keyring="$default_feature"
 meson=""
 meson_args=""
 ninja=""
 gio="$default_feature"
 skip_meson=no
-slirp_smbd="$default_feature"
 
 # The following Meson options are handled manually (still they
 # are included in the automatically generated help message)
 
 # 1. Track which submodules are needed
-capstone="auto"
+if test "$default_feature" = no ; then
+  capstone="disabled"
+  slirp="disabled"
+else
+  capstone="auto"
+  slirp="auto"
+fi
 fdt="auto"
-slirp="auto"
 
 # 2. Support --with/--without option
 default_devices="true"
@@ -441,6 +416,7 @@ objcopy="${OBJCOPY-${cross_prefix}objcopy}"
 ld="${LD-${cross_prefix}ld}"
 ranlib="${RANLIB-${cross_prefix}ranlib}"
 nm="${NM-${cross_prefix}nm}"
+smbd="$SMBD"
 strip="${STRIP-${cross_prefix}strip}"
 windres="${WINDRES-${cross_prefix}windres}"
 pkg_config_exe="${PKG_CONFIG-${cross_prefix}pkg-config}"
@@ -560,7 +536,6 @@ darwin)
 sunos)
   solaris="yes"
   make="${MAKE-gmake}"
-  smbd="${SMBD-/usr/sfw/sbin/smbd}"
 # needed for CMSG_ macros in sys/socket.h
   QEMU_CFLAGS="-D_XOPEN_SOURCE=600 $QEMU_CFLAGS"
 # needed for TIOCWIN* defines in termios.h
@@ -714,7 +689,6 @@ if test "$mingw32" = "yes" ; then
   write_c_skeleton;
   prefix="/qemu"
   qemu_suffix=""
-  libs_qga="-lws2_32 -lwinmm -lpowrprof -lwtsapi32 -lwininet -liphlpapi -lnetapi32 $libs_qga"
 fi
 
 werror=""
@@ -826,8 +800,6 @@ for opt do
   ;;
   --without-default-features) # processed above
   ;;
-  --enable-gprof) gprof="yes"
-  ;;
   --enable-gcov) gcov="yes"
   ;;
   --static)
@@ -868,20 +840,12 @@ for opt do
     # configure to be used by RPM and similar macros that set
     # lots of directory switches by default.
   ;;
-  --disable-qom-cast-debug) qom_cast_debug="no"
-  ;;
-  --enable-qom-cast-debug) qom_cast_debug="yes"
-  ;;
   --audio-drv-list=*) audio_drv_list="$optarg"
   ;;
   --block-drv-rw-whitelist=*|--block-drv-whitelist=*) block_drv_rw_whitelist=$(echo "$optarg" | sed -e 's/,/ /g')
   ;;
   --block-drv-ro-whitelist=*) block_drv_ro_whitelist=$(echo "$optarg" | sed -e 's/,/ /g')
   ;;
-  --enable-block-drv-whitelist-in-tools) block_drv_whitelist_tools="yes"
-  ;;
-  --disable-block-drv-whitelist-in-tools) block_drv_whitelist_tools="no"
-  ;;
   --enable-debug-tcg) debug_tcg="yes"
   ;;
   --disable-debug-tcg) debug_tcg="no"
@@ -889,7 +853,7 @@ for opt do
   --enable-debug)
       # Enable debugging options that aren't excessively noisy
       debug_tcg="yes"
-      debug_mutex="yes"
+      meson_option_parse --enable-debug-mutex ""
       debug="yes"
       fortify_source="no"
   ;;
@@ -918,8 +882,6 @@ for opt do
   ;;
   --enable-tcg) tcg="enabled"
   ;;
-  --enable-profiler) profiler="yes"
-  ;;
   --disable-system) softmmu="no"
   ;;
   --enable-system) softmmu="yes"
@@ -971,24 +933,10 @@ for opt do
   ;;
   --enable-fdt=*) fdt="$optarg"
   ;;
-  --disable-membarrier) membarrier="no"
-  ;;
-  --enable-membarrier) membarrier="yes"
-  ;;
   --with-pkgversion=*) pkgversion="$optarg"
   ;;
   --with-coroutine=*) coroutine="$optarg"
   ;;
-  --disable-coroutine-pool) coroutine_pool="no"
-  ;;
-  --enable-coroutine-pool) coroutine_pool="yes"
-  ;;
-  --enable-debug-stack-usage) debug_stack_usage="yes"
-  ;;
-  --enable-crypto-afalg) crypto_afalg="yes"
-  ;;
-  --disable-crypto-afalg) crypto_afalg="no"
-  ;;
   --disable-vhost-net) vhost_net="no"
   ;;
   --enable-vhost-net) vhost_net="yes"
@@ -1015,34 +963,6 @@ for opt do
   ;;
   --disable-zlib-test)
   ;;
-  --enable-guest-agent) guest_agent="yes"
-  ;;
-  --disable-guest-agent) guest_agent="no"
-  ;;
-  --with-vss-sdk) vss_win32_sdk=""
-  ;;
-  --with-vss-sdk=*) vss_win32_sdk="$optarg"
-  ;;
-  --without-vss-sdk) vss_win32_sdk="no"
-  ;;
-  --with-win-sdk) win_sdk=""
-  ;;
-  --with-win-sdk=*) win_sdk="$optarg"
-  ;;
-  --without-win-sdk) win_sdk="no"
-  ;;
-  --enable-tools) want_tools="yes"
-  ;;
-  --disable-tools) want_tools="no"
-  ;;
-  --disable-avx2) avx2_opt="no"
-  ;;
-  --enable-avx2) avx2_opt="yes"
-  ;;
-  --disable-avx512f) avx512f_opt="no"
-  ;;
-  --enable-avx512f) avx512f_opt="yes"
-  ;;
   --disable-virtio-blk-data-plane|--enable-virtio-blk-data-plane)
       echo "$0: $opt is obsolete, virtio-blk data-plane is always on" >&2
   ;;
@@ -1062,54 +982,6 @@ for opt do
   ;;
   --disable-pvrdma) pvrdma="no"
   ;;
-  --disable-tpm) tpm="no"
-  ;;
-  --enable-tpm) tpm="yes"
-  ;;
-  --disable-live-block-migration) live_block_migration="no"
-  ;;
-  --enable-live-block-migration) live_block_migration="yes"
-  ;;
-  --disable-numa) numa="no"
-  ;;
-  --enable-numa) numa="yes"
-  ;;
-  --disable-replication) replication="no"
-  ;;
-  --enable-replication) replication="yes"
-  ;;
-  --disable-bochs) bochs="no"
-  ;;
-  --enable-bochs) bochs="yes"
-  ;;
-  --disable-cloop) cloop="no"
-  ;;
-  --enable-cloop) cloop="yes"
-  ;;
-  --disable-dmg) dmg="no"
-  ;;
-  --enable-dmg) dmg="yes"
-  ;;
-  --disable-qcow1) qcow1="no"
-  ;;
-  --enable-qcow1) qcow1="yes"
-  ;;
-  --disable-vdi) vdi="no"
-  ;;
-  --enable-vdi) vdi="yes"
-  ;;
-  --disable-vvfat) vvfat="no"
-  ;;
-  --enable-vvfat) vvfat="yes"
-  ;;
-  --disable-qed) qed="no"
-  ;;
-  --enable-qed) qed="yes"
-  ;;
-  --disable-parallels) parallels="no"
-  ;;
-  --enable-parallels) parallels="yes"
-  ;;
   --disable-vhost-user) vhost_user="no"
   ;;
   --enable-vhost-user) vhost_user="yes"
@@ -1135,10 +1007,6 @@ for opt do
   --with-git-submodules=*)
       git_submodules_action="$optarg"
   ;;
-  --enable-debug-mutex) debug_mutex=yes
-  ;;
-  --disable-debug-mutex) debug_mutex=no
-  ;;
   --enable-plugins) if test "$mingw32" = "yes"; then
                         error_exit "TCG plugins not currently supported on Windows platforms"
                     else
@@ -1153,10 +1021,6 @@ for opt do
   ;;
   --gdb=*) gdb_bin="$optarg"
   ;;
-  --enable-rng-none) rng_none=yes
-  ;;
-  --disable-rng-none) rng_none=no
-  ;;
   --enable-keyring) secret_keyring="yes"
   ;;
   --disable-keyring) secret_keyring="no"
@@ -1165,10 +1029,6 @@ for opt do
   ;;
   --disable-gio) gio=no
   ;;
-  --enable-slirp-smbd) slirp_smbd=yes
-  ;;
-  --disable-slirp-smbd) slirp_smbd=no
-  ;;
   # backwards compatibility options
   --enable-trace-backend=*) meson_option_parse "--enable-trace-backends=$optarg" "$optarg"
   ;;
@@ -1369,21 +1229,13 @@ Advanced options (experts only):
   --block-drv-ro-whitelist=L
                            set block driver read-only whitelist
                            (by default affects only QEMU, not tools like qemu-img)
-  --enable-block-drv-whitelist-in-tools
-                           use block whitelist also in tools instead of only QEMU
   --with-trace-file=NAME   Full PATH,NAME of file to store traces
                            Default:trace-<pid>
   --cpu=CPU                Build for host CPU [$cpu]
   --with-coroutine=BACKEND coroutine backend. Supported options:
                            ucontext, sigaltstack, windows
   --enable-gcov            enable test coverage analysis with gcov
-  --with-vss-sdk=SDK-path  enable Windows VSS support in QEMU Guest Agent
-  --with-win-sdk=SDK-path  path to Windows Platform SDK (to build VSS .tlb)
   --tls-priority           default TLS protocol/cipher priority string
-  --enable-gprof           QEMU profiling with gprof
-  --enable-profiler        profiler support
-  --enable-debug-stack-usage
-                           track the maximum stack usage of stacks created by qemu_alloc_stack
   --enable-plugins
                            enable plugins via shared library loading
   --disable-containers     don't use containers for cross-building
@@ -1395,7 +1247,6 @@ cat << EOF
   user            supported user emulation targets
   linux-user      all linux usermode emulation targets
   bsd-user        all BSD usermode emulation targets
-  guest-agent     build the QEMU Guest Agent
   pie             Position Independent Executables
   modules         modules support (non-Windows)
   module-upgrades try to load modules from alternate paths for upgrades
@@ -1404,7 +1255,6 @@ cat << EOF
   lto             Enable Link-Time Optimization.
   safe-stack      SafeStack Stack Smash Protection. Depends on
                   clang/llvm >= 3.7 and requires coroutine backend ucontext.
-  membarrier      membarrier system call (for Linux 4.14+ or Windows)
   rdma            Enable RDMA-based migration
   pvrdma          Enable PVRDMA support
   vhost-net       vhost-net kernel acceleration support
@@ -1414,29 +1264,8 @@ cat << EOF
   vhost-kernel    vhost kernel backend support
   vhost-user      vhost-user backend support
   vhost-vdpa      vhost-vdpa kernel backend support
-  live-block-migration   Block migration in the main migration stream
-  coroutine-pool  coroutine freelist (better performance)
-  tpm             TPM support
-  numa            libnuma support
-  avx2            AVX2 optimization support
-  avx512f         AVX512F optimization support
-  replication     replication support
   opengl          opengl support
-  qom-cast-debug  cast debugging support
-  tools           build qemu-io, qemu-nbd and qemu-img tools
-  bochs           bochs image format support
-  cloop           cloop image format support
-  dmg             dmg image format support
-  qcow1           qcow v1 image format support
-  vdi             vdi image format support
-  vvfat           vvfat image format support
-  qed             qed image format support
-  parallels       parallels image format support
-  crypto-afalg    Linux AF_ALG crypto backend driver
-  debug-mutex     mutex debugging support
-  rng-none        dummy RNG, avoid using /dev/(u)random and getrandom()
   gio             libgio support
-  slirp-smbd      use smbd (at path --smbd=*) in slirp networking
 
 NOTE: The object files are built at the place where configure is launched
 EOF
@@ -1838,16 +1667,6 @@ else
     exit 1
 fi
 
-##########################################
-# system tools
-if test -z "$want_tools"; then
-    if test "$softmmu" = "no"; then
-        want_tools=no
-    else
-        want_tools=yes
-    fi
-fi
-
 #########################################
 # vhost interdependencies and host support
 
@@ -2437,21 +2256,6 @@ if test "$modules" = yes; then
     fi
 fi
 
-##########################################
-# TPM emulation is only on POSIX
-
-if test "$tpm" = ""; then
-  if test "$mingw32" = "yes"; then
-    tpm=no
-  else
-    tpm=yes
-  fi
-elif test "$tpm" = "yes"; then
-  if test "$mingw32" = "yes" ; then
-    error_exit "TPM emulation only available on POSIX systems"
-  fi
-fi
-
 ##########################################
 # fdt probe
 
@@ -2491,26 +2295,6 @@ EOF
   fi
 fi
 
-##########################################
-# libnuma probe
-
-if test "$numa" != "no" ; then
-  cat > $TMPC << EOF
-#include <numa.h>
-int main(void) { return numa_available(); }
-EOF
-
-  if compile_prog "" "-lnuma" ; then
-    numa=yes
-    numa_libs="-lnuma"
-  else
-    if test "$numa" = "yes" ; then
-      feature_not_found "numa" "install numactl devel"
-    fi
-    numa=no
-  fi
-fi
-
 # check for usbfs
 have_usbfs=no
 if test "$linux_user" = "yes"; then
@@ -2535,85 +2319,6 @@ EOF
   fi
 fi
 
-##########################################
-# check if we have VSS SDK headers for win
-
-guest_agent_with_vss="no"
-if test "$mingw32" = "yes" && test "$guest_agent" != "no" && \
-        test "$vss_win32_sdk" != "no" ; then
-  case "$vss_win32_sdk" in
-    "")   vss_win32_include="-isystem $source_path" ;;
-    *\ *) # The SDK is installed in "Program Files" by default, but we cannot
-          # handle path with spaces. So we symlink the headers into ".sdk/vss".
-          vss_win32_include="-isystem $source_path/.sdk/vss"
-	  symlink "$vss_win32_sdk/inc" "$source_path/.sdk/vss/inc"
-	  ;;
-    *)    vss_win32_include="-isystem $vss_win32_sdk"
-  esac
-  cat > $TMPC << EOF
-#define __MIDL_user_allocate_free_DEFINED__
-#include <inc/win2003/vss.h>
-int main(void) { return VSS_CTX_BACKUP; }
-EOF
-  if compile_prog "$vss_win32_include" "" ; then
-    guest_agent_with_vss="yes"
-    QEMU_CFLAGS="$QEMU_CFLAGS $vss_win32_include"
-    libs_qga="-lole32 -loleaut32 -lshlwapi -lstdc++ -Wl,--enable-stdcall-fixup $libs_qga"
-    qga_vss_provider="qga/vss-win32/qga-vss.dll qga/vss-win32/qga-vss.tlb"
-  else
-    if test "$vss_win32_sdk" != "" ; then
-      echo "ERROR: Please download and install Microsoft VSS SDK:"
-      echo "ERROR:   http://www.microsoft.com/en-us/download/details.aspx?id=23490"
-      echo "ERROR: On POSIX-systems, you can extract the SDK headers by:"
-      echo "ERROR:   scripts/extract-vsssdk-headers setup.exe"
-      echo "ERROR: The headers are extracted in the directory \`inc'."
-      feature_not_found "VSS support"
-    fi
-  fi
-fi
-
-##########################################
-# lookup Windows platform SDK (if not specified)
-# The SDK is needed only to build .tlb (type library) file of guest agent
-# VSS provider from the source. It is usually unnecessary because the
-# pre-compiled .tlb file is included.
-
-if test "$mingw32" = "yes" && test "$guest_agent" != "no" && \
-        test "$guest_agent_with_vss" = "yes" ; then
-  if test -z "$win_sdk"; then
-    programfiles="$PROGRAMFILES"
-    test -n "$PROGRAMW6432" && programfiles="$PROGRAMW6432"
-    if test -n "$programfiles"; then
-      win_sdk=$(ls -d "$programfiles/Microsoft SDKs/Windows/v"* | tail -1) 2>/dev/null
-    else
-      feature_not_found "Windows SDK"
-    fi
-  elif test "$win_sdk" = "no"; then
-    win_sdk=""
-  fi
-fi
-
-##########################################
-# check if mingw environment provides a recent ntddscsi.h
-guest_agent_ntddscsi="no"
-if test "$mingw32" = "yes" && test "$guest_agent" != "no"; then
-  cat > $TMPC << EOF
-#include <windows.h>
-#include <ntddscsi.h>
-int main(void) {
-#if !defined(IOCTL_SCSI_GET_ADDRESS)
-#error Missing required ioctl definitions
-#endif
-  SCSI_ADDRESS addr = { .Lun = 0, .TargetId = 0, .PathId = 0 };
-  return addr.Lun;
-}
-EOF
-  if compile_prog "" "" ; then
-    guest_agent_ntddscsi=yes
-    libs_qga="-lsetupapi -lcfgmgr32 $libs_qga"
-  fi
-fi
-
 ##########################################
 # capstone
 
@@ -2679,17 +2384,6 @@ else
   esac
 fi
 
-if test "$coroutine_pool" = ""; then
-  coroutine_pool=yes
-fi
-
-if test "$debug_stack_usage" = "yes"; then
-  if test "$coroutine_pool" = "yes"; then
-    echo "WARN: disabling coroutine pool for stack usage debugging"
-    coroutine_pool=no
-  fi
-fi
-
 ##################################################
 # SafeStack
 
@@ -2752,85 +2446,6 @@ else # "$safe_stack" = ""
 fi
 fi
 
-########################################
-# check if cpuid.h is usable.
-
-cat > $TMPC << EOF
-#include <cpuid.h>
-int main(void) {
-    unsigned a, b, c, d;
-    unsigned max = __get_cpuid_max(0, 0);
-
-    if (max >= 1) {
-        __cpuid(1, a, b, c, d);
-    }
-
-    if (max >= 7) {
-        __cpuid_count(7, 0, a, b, c, d);
-    }
-
-    return 0;
-}
-EOF
-if compile_prog "" "" ; then
-    cpuid_h=yes
-fi
-
-##########################################
-# avx2 optimization requirement check
-#
-# There is no point enabling this if cpuid.h is not usable,
-# since we won't be able to select the new routines.
-
-if test "$cpuid_h" = "yes" && test "$avx2_opt" != "no"; then
-  cat > $TMPC << EOF
-#pragma GCC push_options
-#pragma GCC target("avx2")
-#include <cpuid.h>
-#include <immintrin.h>
-static int bar(void *a) {
-    __m256i x = *(__m256i *)a;
-    return _mm256_testz_si256(x, x);
-}
-int main(int argc, char *argv[]) { return bar(argv[0]); }
-EOF
-  if compile_object "-Werror" ; then
-    avx2_opt="yes"
-  else
-    avx2_opt="no"
-  fi
-fi
-
-##########################################
-# avx512f optimization requirement check
-#
-# There is no point enabling this if cpuid.h is not usable,
-# since we won't be able to select the new routines.
-# by default, it is turned off.
-# if user explicitly want to enable it, check environment
-
-if test "$cpuid_h" = "yes" && test "$avx512f_opt" = "yes"; then
-  cat > $TMPC << EOF
-#pragma GCC push_options
-#pragma GCC target("avx512f")
-#include <cpuid.h>
-#include <immintrin.h>
-static int bar(void *a) {
-    __m512i x = *(__m512i *)a;
-    return _mm512_test_epi64_mask(x, x);
-}
-int main(int argc, char *argv[])
-{
-	return bar(argv[0]);
-}
-EOF
-  if ! compile_object "-Werror" ; then
-    avx512f_opt="no"
-  fi
-else
-  avx512f_opt="no"
-fi
-
 ########################################
 # check if __[u]int128_t is usable.
 
@@ -2926,63 +2541,6 @@ if test "$fortify_source" != "no"; then
   fi
 fi
 
-##########################################
-# check for usable membarrier system call
-if test "$membarrier" = "yes"; then
-    have_membarrier=no
-    if test "$mingw32" = "yes" ; then
-        have_membarrier=yes
-    elif test "$linux" = "yes" ; then
-        cat > $TMPC << EOF
-    #include <linux/membarrier.h>
-    #include <sys/syscall.h>
-    #include <unistd.h>
-    #include <stdlib.h>
-    int main(void) {
-        syscall(__NR_membarrier, MEMBARRIER_CMD_QUERY, 0);
-        syscall(__NR_membarrier, MEMBARRIER_CMD_SHARED, 0);
-	exit(0);
-    }
-EOF
-        if compile_prog "" "" ; then
-            have_membarrier=yes
-        fi
-    fi
-    if test "$have_membarrier" = "no"; then
-      feature_not_found "membarrier" "membarrier system call not available"
-    fi
-else
-    # Do not enable it by default even for Mingw32, because it doesn't
-    # work on Wine.
-    membarrier=no
-fi
-
-##########################################
-# check for usable AF_ALG environment
-have_afalg=no
-cat > $TMPC << EOF
-#include <errno.h>
-#include <sys/types.h>
-#include <sys/socket.h>
-#include <linux/if_alg.h>
-int main(void) {
-    int sock;
-    sock = socket(AF_ALG, SOCK_SEQPACKET, 0);
-    return sock;
-}
-EOF
-if compile_prog "" "" ; then
-    have_afalg=yes
-fi
-if test "$crypto_afalg" = "yes"
-then
-    if test "$have_afalg" != "yes"
-    then
-	error_exit "AF_ALG requested but could not be detected"
-    fi
-fi
-
-
 ##########################################
 # checks for sanitizers
 
@@ -3064,19 +2622,6 @@ case "$slirp" in
     ;;
 esac
 
-# Check for slirp smbd dupport
-: ${smbd=${SMBD-/usr/sbin/smbd}}
-if test "$slirp_smbd" != "no" ; then
-  if test "$mingw32" = "yes" ; then
-    if test "$slirp_smbd" = "yes" ; then
-      error_exit "Host smbd not supported on this platform."
-    fi
-    slirp_smbd=no
-  else
-    slirp_smbd=yes
-  fi
-fi
-
 ##########################################
 # check for usable __NR_keyctl syscall
 
@@ -3132,11 +2677,6 @@ alpha)
 ;;
 esac
 
-if test "$gprof" = "yes" ; then
-  QEMU_CFLAGS="-p $QEMU_CFLAGS"
-  QEMU_LDFLAGS="-p $QEMU_LDFLAGS"
-fi
-
 if test "$have_asan" = "yes"; then
   QEMU_CFLAGS="-fsanitize=address $QEMU_CFLAGS"
   QEMU_LDFLAGS="-fsanitize=address $QEMU_LDFLAGS"
@@ -3188,20 +2728,6 @@ if test "$mingw32" = "yes" ; then
     done
 fi
 
-# Probe for guest agent support/options
-
-if [ "$guest_agent" != "no" ]; then
-  if [ "$softmmu" = no -a "$want_tools" = no ] ; then
-      guest_agent=no
-  elif [ "$linux" = "yes" -o "$bsd" = "yes" -o "$solaris" = "yes" -o "$mingw32" = "yes" ] ; then
-      guest_agent=yes
-  elif [ "$guest_agent" != yes ]; then
-      guest_agent=no
-  else
-      error_exit "Guest agent is not supported on this platform"
-  fi
-fi
-
 # Guest agent Windows MSI package
 
 if test "$QEMU_GA_MANUFACTURER" = ""; then
@@ -3302,14 +2828,6 @@ if test "$debug_tcg" = "yes" ; then
 fi
 if test "$mingw32" = "yes" ; then
   echo "CONFIG_WIN32=y" >> $config_host_mak
-  if test "$guest_agent_with_vss" = "yes" ; then
-    echo "CONFIG_QGA_VSS=y" >> $config_host_mak
-    echo "QGA_VSS_PROVIDER=$qga_vss_provider" >> $config_host_mak
-    echo "WIN_SDK=\"$win_sdk\"" >> $config_host_mak
-  fi
-  if test "$guest_agent_ntddscsi" = "yes" ; then
-    echo "CONFIG_QGA_NTDDSCSI=y" >> $config_host_mak
-  fi
   echo "QEMU_GA_MSI_MINGW_DLL_PATH=${QEMU_GA_MSI_MINGW_DLL_PATH}" >> $config_host_mak
   echo "QEMU_GA_MANUFACTURER=${QEMU_GA_MANUFACTURER}" >> $config_host_mak
   echo "QEMU_GA_DISTRO=${QEMU_GA_DISTRO}" >> $config_host_mak
@@ -3332,27 +2850,8 @@ fi
 if test "$static" = "yes" ; then
   echo "CONFIG_STATIC=y" >> $config_host_mak
 fi
-if test "$profiler" = "yes" ; then
-  echo "CONFIG_PROFILER=y" >> $config_host_mak
-fi
-if test "$want_tools" = "yes" ; then
-  echo "CONFIG_TOOLS=y" >> $config_host_mak
-fi
-if test "$guest_agent" = "yes" ; then
-  echo "CONFIG_GUEST_AGENT=y" >> $config_host_mak
-fi
-if test "$slirp_smbd" = "yes" ; then
-  echo "CONFIG_SLIRP_SMBD=y" >> $config_host_mak
-  echo "CONFIG_SMBD_COMMAND=\"$smbd\"" >> $config_host_mak
-fi
-if test "$gprof" = "yes" ; then
-  echo "CONFIG_GPROF=y" >> $config_host_mak
-fi
 echo "CONFIG_BDRV_RW_WHITELIST=$block_drv_rw_whitelist" >> $config_host_mak
 echo "CONFIG_BDRV_RO_WHITELIST=$block_drv_ro_whitelist" >> $config_host_mak
-if test "$block_drv_whitelist_tools" = "yes" ; then
-  echo "CONFIG_BDRV_WHITELIST_TOOLS=y" >> $config_host_mak
-fi
 qemu_version=$(head $source_path/VERSION)
 echo "PKGVERSION=$pkgversion" >>$config_host_mak
 echo "SRC_PATH=$source_path" >> $config_host_mak
@@ -3418,9 +2917,6 @@ fi
 if test "$vhost_user_fs" = "yes" ; then
   echo "CONFIG_VHOST_USER_FS=y" >> $config_host_mak
 fi
-if test "$membarrier" = "yes" ; then
-  echo "CONFIG_MEMBARRIER=y" >> $config_host_mak
-fi
 if test "$tcg" = "enabled" -a "$tcg_interpreter" = "true" ; then
   echo "CONFIG_TCG_INTERPRETER=y" >> $config_host_mak
 fi
@@ -3431,37 +2927,12 @@ if test "$opengl" = "yes" ; then
   echo "OPENGL_LIBS=$opengl_libs" >> $config_host_mak
 fi
 
-if test "$avx2_opt" = "yes" ; then
-  echo "CONFIG_AVX2_OPT=y" >> $config_host_mak
-fi
-
-if test "$avx512f_opt" = "yes" ; then
-  echo "CONFIG_AVX512F_OPT=y" >> $config_host_mak
-fi
-
 # XXX: suppress that
 if [ "$bsd" = "yes" ] ; then
   echo "CONFIG_BSD=y" >> $config_host_mak
 fi
 
-if test "$qom_cast_debug" = "yes" ; then
-  echo "CONFIG_QOM_CAST_DEBUG=y" >> $config_host_mak
-fi
-
 echo "CONFIG_COROUTINE_BACKEND=$coroutine" >> $config_host_mak
-if test "$coroutine_pool" = "yes" ; then
-  echo "CONFIG_COROUTINE_POOL=1" >> $config_host_mak
-else
-  echo "CONFIG_COROUTINE_POOL=0" >> $config_host_mak
-fi
-
-if test "$debug_stack_usage" = "yes" ; then
-  echo "CONFIG_DEBUG_STACK_USAGE=y" >> $config_host_mak
-fi
-
-if test "$crypto_afalg" = "yes" ; then
-  echo "CONFIG_AF_ALG=y" >> $config_host_mak
-fi
 
 if test "$have_asan_iface_fiber" = "yes" ; then
     echo "CONFIG_ASAN_IFACE_FIBER=y" >> $config_host_mak
@@ -3471,10 +2942,6 @@ if test "$have_tsan" = "yes" && test "$have_tsan_iface_fiber" = "yes" ; then
     echo "CONFIG_TSAN=y" >> $config_host_mak
 fi
 
-if test "$cpuid_h" = "yes" ; then
-  echo "CONFIG_CPUID_H=y" >> $config_host_mak
-fi
-
 if test "$int128" = "yes" ; then
   echo "CONFIG_INT128=y" >> $config_host_mak
 fi
@@ -3487,14 +2954,6 @@ if test "$cmpxchg128" = "yes" ; then
   echo "CONFIG_CMPXCHG128=y" >> $config_host_mak
 fi
 
-if test "$live_block_migration" = "yes" ; then
-  echo "CONFIG_LIVE_BLOCK_MIGRATION=y" >> $config_host_mak
-fi
-
-if test "$tpm" = "yes"; then
-  echo 'CONFIG_TPM=y' >> $config_host_mak
-fi
-
 if test "$rdma" = "yes" ; then
   echo "CONFIG_RDMA=y" >> $config_host_mak
   echo "RDMA_LIBS=$rdma_libs" >> $config_host_mak
@@ -3504,39 +2963,6 @@ if test "$pvrdma" = "yes" ; then
   echo "CONFIG_PVRDMA=y" >> $config_host_mak
 fi
 
-if test "$replication" = "yes" ; then
-  echo "CONFIG_REPLICATION=y" >> $config_host_mak
-fi
-
-if test "$debug_mutex" = "yes" ; then
-  echo "CONFIG_DEBUG_MUTEX=y" >> $config_host_mak
-fi
-
-if test "$bochs" = "yes" ; then
-  echo "CONFIG_BOCHS=y" >> $config_host_mak
-fi
-if test "$cloop" = "yes" ; then
-  echo "CONFIG_CLOOP=y" >> $config_host_mak
-fi
-if test "$dmg" = "yes" ; then
-  echo "CONFIG_DMG=y" >> $config_host_mak
-fi
-if test "$qcow1" = "yes" ; then
-  echo "CONFIG_QCOW1=y" >> $config_host_mak
-fi
-if test "$vdi" = "yes" ; then
-  echo "CONFIG_VDI=y" >> $config_host_mak
-fi
-if test "$vvfat" = "yes" ; then
-  echo "CONFIG_VVFAT=y" >> $config_host_mak
-fi
-if test "$qed" = "yes" ; then
-  echo "CONFIG_QED=y" >> $config_host_mak
-fi
-if test "$parallels" = "yes" ; then
-  echo "CONFIG_PARALLELS=y" >> $config_host_mak
-fi
-
 if test "$plugins" = "yes" ; then
     echo "CONFIG_PLUGIN=y" >> $config_host_mak
 fi
@@ -3567,9 +2993,6 @@ echo "MESON=$meson" >> $config_host_mak
 echo "NINJA=$ninja" >> $config_host_mak
 echo "CC=$cc" >> $config_host_mak
 echo "HOST_CC=$host_cc" >> $config_host_mak
-if $iasl -h > /dev/null 2>&1; then
-  echo "CONFIG_IASL=$iasl" >> $config_host_mak
-fi
 echo "AR=$ar" >> $config_host_mak
 echo "AS=$as" >> $config_host_mak
 echo "CCAS=$ccas" >> $config_host_mak
@@ -3586,11 +3009,6 @@ echo "QEMU_LDFLAGS=$QEMU_LDFLAGS" >> $config_host_mak
 echo "LD_I386_EMULATION=$ld_i386_emulation" >> $config_host_mak
 echo "STRIP=$strip" >> $config_host_mak
 echo "EXESUF=$EXESUF" >> $config_host_mak
-echo "LIBS_QGA=$libs_qga" >> $config_host_mak
-
-if test "$rng_none" = "yes"; then
-  echo "CONFIG_RNG_NONE=y" >> $config_host_mak
-fi
 
 # use included Linux headers
 if test "$linux" = "yes" ; then
@@ -3640,11 +3058,6 @@ if test "$default_targets" = "yes"; then
   echo "CONFIG_DEFAULT_TARGETS=y" >> $config_host_mak
 fi
 
-if test "$numa" = "yes"; then
-  echo "CONFIG_NUMA=y" >> $config_host_mak
-  echo "NUMA_LIBS=$numa_libs" >> $config_host_mak
-fi
-
 if test "$ccache_cpp2" = "yes"; then
   echo "export CCACHE_CPP2=y" >> $config_host_mak
 fi
@@ -3797,8 +3210,10 @@ if test "$skip_meson" = no; then
         -Daudio_drv_list=$audio_drv_list \
         -Ddefault_devices=$default_devices \
         -Ddocdir="$docdir" \
+        -Diasl="$($iasl -h >/dev/null 2>&1 && printf %s "$iasl")" \
         -Dqemu_firmwarepath="$firmwarepath" \
         -Dqemu_suffix="$qemu_suffix" \
+        -Dsmbd="$smbd" \
         -Dsphinx_build="$sphinx_build" \
         -Dtrace_file="$trace_file" \
         -Doptimization=$(if test "$debug" = yes; then echo 0; else echo 2; fi) \

contrib/vhost-user-gpu/meson.build

@@ -1,5 +1,4 @@
-if 'CONFIG_TOOLS' in config_host and virgl.found() and gbm.found() \
+if have_vhost_user_gpu
-    and 'CONFIG_LINUX' in config_host and pixman.found()
   executable('vhost-user-gpu', files('vhost-user-gpu.c', 'virgl.c', 'vugbm.c'),
              dependencies: [qemuutil, pixman, gbm, virgl, vhost_user, opengl],
              install: true,

crypto/meson.build

@@ -35,7 +35,9 @@ else
 endif
 
 crypto_ss.add(when: 'CONFIG_SECRET_KEYRING', if_true: files('secret_keyring.c'))
-crypto_ss.add(when: 'CONFIG_AF_ALG', if_true: files('afalg.c', 'cipher-afalg.c', 'hash-afalg.c'))
+if have_afalg
+  crypto_ss.add(if_true: files('afalg.c', 'cipher-afalg.c', 'hash-afalg.c'))
+endif
 crypto_ss.add(when: gnutls, if_true: files('tls-cipher-suites.c'))
 
 util_ss.add(files('aes.c'))
@@ -48,7 +50,7 @@ if gcrypt.found()
   util_ss.add(gcrypt, files('random-gcrypt.c'))
 elif gnutls.found()
   util_ss.add(gnutls, files('random-gnutls.c'))
-elif 'CONFIG_RNG_NONE' in config_host
+elif get_option('rng_none')
   util_ss.add(files('random-none.c'))
 else
   util_ss.add(files('random-platform.c'))

docs/devel/kconfig.rst

@@ -192,11 +192,15 @@ declares its dependencies in different ways:
   no directive and are not used in the Makefile either; they only appear
   as conditions for ``default y`` directives.
 
-  QEMU currently has two device groups, ``PCI_DEVICES`` and
+  QEMU currently has three device groups, ``PCI_DEVICES``, ``I2C_DEVICES``,
-  ``TEST_DEVICES``.  PCI devices usually have a ``default y if
+  and ``TEST_DEVICES``.  PCI devices usually have a ``default y if
   PCI_DEVICES`` directive rather than just ``default y``.  This lets
   some boards (notably s390) easily support a subset of PCI devices,
   for example only VFIO (passthrough) and virtio-pci devices.
+  ``I2C_DEVICES`` is similar to ``PCI_DEVICES``. It contains i2c devices
+  that users might reasonably want to plug in to an i2c bus on any
+  board (and not ones which are very board-specific or that need
+  to be wired up in a way that can't be done on the command line).
   ``TEST_DEVICES`` instead is used for devices that are rarely used on
   production virtual machines, but provide useful hooks to test QEMU
   or KVM.
@@ -301,7 +305,7 @@ and also listed as follows in the top-level meson.build's host_kconfig
 variable::
 
     host_kconfig = \
-      ('CONFIG_TPM' in config_host ? ['CONFIG_TPM=y'] : []) + \
+      (have_tpm ? ['CONFIG_TPM=y'] : []) + \
       ('CONFIG_SPICE' in config_host ? ['CONFIG_SPICE=y'] : []) + \
       (have_ivshmem ? ['CONFIG_IVSHMEM=y'] : []) + \
       ...

docs/interop/firmware.json

@@ -210,24 +210,61 @@
   'data'   : { 'filename' : 'str',
                'format'   : 'BlockdevDriver' } }
 
+
+##
+# @FirmwareFlashType:
+#
+# Describes how the firmware build handles code versus variable
+# persistence.
+#
+# @split: the executable file contains code while the NVRAM
+#         template provides variable storage. The executable
+#         must be configured read-only and can be shared between
+#         multiple guests. The NVRAM template must be cloned
+#         for each new guest and configured read-write.
+#
+# @combined: the executable file contains both code and
+#            variable storage. The executable must be cloned
+#            for each new guest and configured read-write.
+#            No NVRAM template will be specified.
+#
+# @stateless: the executable file contains code and variable
+#             storage is not persisted. The executable must
+#             be configured read-only and can be shared
+#             between multiple guests. No NVRAM template
+#             will be specified.
+#
+# Since: 7.0.0
+##
+{ 'enum': 'FirmwareFlashMode',
+  'data': [ 'split', 'combined', 'stateless' ] }
+
 ##
 # @FirmwareMappingFlash:
 #
 # Describes loading and mapping properties for the firmware executable
 # and its accompanying NVRAM file, when @FirmwareDevice is @flash.
 #
-# @executable: Identifies the firmware executable. The firmware
+# @mode: Describes how the firmware build handles code versus variable
-#              executable may be shared by multiple virtual machine
+#        storage. If not present, it must be treated as if it was
-#              definitions. The preferred corresponding QEMU command
+#        configured with value ``split``. Since: 7.0.0
-#              line options are
+#
+# @executable: Identifies the firmware executable. The @mode
+#              indicates whether there will be an associated
+#              NVRAM template present. The preferred
+#              corresponding QEMU command line options are
 #                  -drive if=none,id=pflash0,readonly=on,file=@executable.@filename,format=@executable.@format
 #                  -machine pflash0=pflash0
-#              or equivalent -blockdev instead of -drive.
+#              or equivalent -blockdev instead of -drive. When
+#              @mode is ``combined`` the executable must be
+#              cloned before use and configured with readonly=off.
 #              With QEMU versions older than 4.0, you have to use
 #                  -drive if=pflash,unit=0,readonly=on,file=@executable.@filename,format=@executable.@format
 #
 # @nvram-template: Identifies the NVRAM template compatible with
-#                  @executable. Management software instantiates an
+#                  @executable, when @mode is set to ``split``,
+#                  otherwise it should not be present.
+#                  Management software instantiates an
 #                  individual copy -- a specific NVRAM file -- from
 #                  @nvram-template.@filename for each new virtual
 #                  machine definition created. @nvram-template.@filename
@@ -246,8 +283,9 @@
 # Since: 3.0
 ##
 { 'struct' : 'FirmwareMappingFlash',
-  'data'   : { 'executable'     : 'FirmwareFlashFile',
+  'data'   : { '*mode': 'FirmwareFlashMode',
-               'nvram-template' : 'FirmwareFlashFile' } }
+               'executable'     : 'FirmwareFlashFile',
+               '*nvram-template' : 'FirmwareFlashFile' } }
 
 ##
 # @FirmwareMappingKernel:

docs/meson.build

@@ -37,8 +37,6 @@ endif
 if build_docs
   SPHINX_ARGS += ['-Dversion=' + meson.project_version(), '-Drelease=' + config_host['PKGVERSION']]
 
-  have_ga = have_tools and config_host.has_key('CONFIG_GUEST_AGENT')
-
   man_pages = {
         'qemu-ga.8': (have_ga ? 'man8' : ''),
         'qemu-ga-ref.7': (have_ga ? 'man7' : ''),

docs/system/arm/nuvoton.rst

@@ -21,6 +21,7 @@ Hyperscale applications. The following machines are based on this chip :
 - ``quanta-gbs-bmc``    Quanta GBS server BMC
 - ``quanta-gsj``        Quanta GSJ server BMC
 - ``kudo-bmc``          Fii USA Kudo server BMC
+- ``mori-bmc``          Fii USA Mori server BMC
 
 There are also two more SoCs, NPCM710 and NPCM705, which are single-core
 variants of NPCM750 and NPCM730, respectively. These are currently not

docs/system/qemu-block-drivers.rst.inc

@@ -778,10 +778,32 @@ The optional *HOST_KEY_CHECK* parameter controls how the remote
 host's key is checked.  The default is ``yes`` which means to use
 the local ``.ssh/known_hosts`` file.  Setting this to ``no``
 turns off known-hosts checking.  Or you can check that the host key
-matches a specific fingerprint:
+matches a specific fingerprint. The fingerprint can be provided in
-``host_key_check=md5:78:45:8e:14:57:4f:d5:45:83:0a:0e:f3:49:82:c9:c8``
+``md5``, ``sha1``, or ``sha256`` format, however, it is strongly
-(``sha1:`` can also be used as a prefix, but note that OpenSSH
+recommended to only use ``sha256``, since the other options are
-tools only use MD5 to print fingerprints).
+considered insecure by modern standards. The fingerprint value
+must be given as a hex encoded string::
+
+  host_key_check=sha256:04ce2ae89ff4295a6b9c4111640bdcb3297858ee55cb434d9dd88796e93aa795
+
+The key string may optionally contain ":" separators between
+each pair of hex digits.
+
+The ``$HOME/.ssh/known_hosts`` file contains the base64 encoded
+host keys. These can be converted into the format needed for
+QEMU using a command such as::
+
+   $ for key in `grep 10.33.8.112 known_hosts | awk '{print $3}'`
+     do
+       echo $key | base64 -d | sha256sum
+     done
+     6c3aa525beda9dc83eadfbd7e5ba7d976ecb59575d1633c87cd06ed2ed6e366f  -
+     12214fd9ea5b408086f98ecccd9958609bd9ac7c0ea316734006bc7818b45dc8  -
+     d36420137bcbd101209ef70c3b15dc07362fbe0fa53c5b135eba6e6afa82f0ce  -
+
+Note that there can be multiple keys present per host, each with
+different key ciphers. Care is needed to pick the key fingerprint
+that matches the cipher QEMU will negotiate with the remote server.
 
 Currently authentication must be done using ssh-agent.  Other
 authentication methods may be supported in future.

docs/tools/virtiofsd.rst

@@ -104,6 +104,13 @@ Options
   * posix_acl|no_posix_acl -
     Enable/disable posix acl support.  Posix ACLs are disabled by default.
 
+  * security_label|no_security_label -
+    Enable/disable security label support. Security labels are disabled by
+    default. This will allow client to send a MAC label of file during
+    file creation. Typically this is expected to be SELinux security
+    label. Server will try to set that label on newly created file
+    atomically wherever possible.
+
 .. option:: --socket-path=PATH
 
   Listen on vhost-user UNIX domain socket at PATH.
@@ -348,6 +355,31 @@ client arguments or lists returned from the host.  This stops
 the client seeing any 'security.' attributes on the server and
 stops it setting any.
 
+SELinux support
+---------------
+One can enable support for SELinux by running virtiofsd with option
+"-o security_label". But this will try to save guest's security context
+in xattr security.selinux on host and it might fail if host's SELinux
+policy does not permit virtiofsd to do this operation.
+
+Hence, it is preferred to remap guest's "security.selinux" xattr to say
+"trusted.virtiofs.security.selinux" on host.
+
+"-o xattrmap=:map:security.selinux:trusted.virtiofs.:"
+
+This will make sure that guest and host's SELinux xattrs on same file
+remain separate and not interfere with each other. And will allow both
+host and guest to implement their own separate SELinux policies.
+
+Setting trusted xattr on host requires CAP_SYS_ADMIN. So one will need
+add this capability to daemon.
+
+"-o modcaps=+sys_admin"
+
+Giving CAP_SYS_ADMIN increases the risk on system. Now virtiofsd is more
+powerful and if gets compromised, it can do lot of damage to host system.
+So keep this trade-off in my mind while making a decision.
+
 Examples
 --------
 

hw/9pfs/9p-synth.c

@@ -182,7 +182,12 @@ static int synth_opendir(FsContext *ctx,
     V9fsSynthOpenState *synth_open;
     V9fsSynthNode *node = *(V9fsSynthNode **)fs_path->data;
 
-    synth_open = g_malloc(sizeof(*synth_open));
+    /*
+     * V9fsSynthOpenState contains 'struct dirent' which have OS-specific
+     * properties, thus it's zero cleared on allocation here and below
+     * in synth_open.
+     */
+    synth_open = g_new0(V9fsSynthOpenState, 1);
     synth_open->node = node;
     node->open_count++;
     fs->private = synth_open;
@@ -220,7 +225,14 @@ static void synth_rewinddir(FsContext *ctx, V9fsFidOpenState *fs)
 static void synth_direntry(V9fsSynthNode *node,
                                 struct dirent *entry, off_t off)
 {
-    strcpy(entry->d_name, node->name);
+    size_t sz = strlen(node->name) + 1;
+    /*
+     * 'entry' is always inside of V9fsSynthOpenState which have NAME_MAX
+     * back padding. Ensure we do not overflow it.
+     */
+    g_assert(sizeof(struct dirent) + NAME_MAX >=
+             offsetof(struct dirent, d_name) + sz);
+    memcpy(entry->d_name, node->name, sz);
     entry->d_ino = node->attr->inode;
     entry->d_off = off + 1;
 }
@@ -266,7 +278,7 @@ static int synth_open(FsContext *ctx, V9fsPath *fs_path,
     V9fsSynthOpenState *synth_open;
     V9fsSynthNode *node = *(V9fsSynthNode **)fs_path->data;
 
-    synth_open = g_malloc(sizeof(*synth_open));
+    synth_open = g_new0(V9fsSynthOpenState, 1);
     synth_open->node = node;
     node->open_count++;
     fs->private = synth_open;

hw/9pfs/9p-synth.h

@@ -41,6 +41,11 @@ typedef struct V9fsSynthOpenState {
     off_t offset;
     V9fsSynthNode *node;
     struct dirent dent;
+    /*
+     * Ensure there is enough space for 'dent' above, some systems have a
+     * d_name size of just 1, which would cause a buffer overrun.
+     */
+    char dent_trailing_space[NAME_MAX];
 } V9fsSynthOpenState;
 
 int qemu_v9fs_synth_mkdir(V9fsSynthNode *parent, int mode,

hw/9pfs/codir.c

@@ -143,8 +143,7 @@ static int do_readdir_many(V9fsPDU *pdu, V9fsFidState *fidp,
         } else {
             e = e->next = g_malloc0(sizeof(V9fsDirEnt));
         }
-        e->dent = g_malloc0(sizeof(struct dirent));
+        e->dent = qemu_dirent_dup(dent);
-        memcpy(e->dent, dent, sizeof(struct dirent));
 
         /* perform a full stat() for directory entry if requested by caller */
         if (dostat) {

hw/acpi/memory_hotplug.c

@@ -1,6 +1,5 @@
 #include "qemu/osdep.h"
 #include "hw/acpi/memory_hotplug.h"
-#include "hw/acpi/pc-hotplug.h"
 #include "hw/mem/pc-dimm.h"
 #include "hw/qdev-core.h"
 #include "migration/vmstate.h"

hw/acpi/meson.build

@@ -25,7 +25,9 @@ acpi_ss.add(when: 'CONFIG_ACPI_X86_ICH', if_true: files('ich9.c', 'tco.c'))
 acpi_ss.add(when: 'CONFIG_ACPI_ERST', if_true: files('erst.c'))
 acpi_ss.add(when: 'CONFIG_IPMI', if_true: files('ipmi.c'), if_false: files('ipmi-stub.c'))
 acpi_ss.add(when: 'CONFIG_PC', if_false: files('acpi-x86-stub.c'))
-acpi_ss.add(when: 'CONFIG_TPM', if_true: files('tpm.c'))
+if have_tpm
+  acpi_ss.add(files('tpm.c'))
+endif
 softmmu_ss.add(when: 'CONFIG_ACPI', if_false: files('acpi-stub.c', 'aml-build-stub.c', 'ghes-stub.c'))
 softmmu_ss.add_all(when: 'CONFIG_ACPI', if_true: acpi_ss)
 softmmu_ss.add(when: 'CONFIG_ALL', if_true: files('acpi-stub.c', 'aml-build-stub.c',

hw/arm/Kconfig

@@ -46,6 +46,7 @@ config DIGIC
 
 config EXYNOS4
     bool
+    imply I2C_DEVICES
     select A9MPCORE
     select I2C
     select LAN9118
@@ -184,6 +185,7 @@ config REALVIEW
     bool
     imply PCI_DEVICES
     imply PCI_TESTDEV
+    imply I2C_DEVICES
     select SMC91C111
     select LAN9118
     select A9MPCORE
@@ -229,6 +231,7 @@ config SABRELITE
 
 config STELLARIS
     bool
+    imply I2C_DEVICES
     select ARM_V7M
     select CMSDK_APB_WATCHDOG
     select I2C
@@ -406,6 +409,7 @@ config NPCM7XX
 
 config FSL_IMX25
     bool
+    imply I2C_DEVICES
     select IMX
     select IMX_FEC
     select IMX_I2C
@@ -414,6 +418,7 @@ config FSL_IMX25
 
 config FSL_IMX31
     bool
+    imply I2C_DEVICES
     select SERIAL
     select IMX
     select IMX_I2C
@@ -422,6 +427,7 @@ config FSL_IMX31
 
 config FSL_IMX6
     bool
+    imply I2C_DEVICES
     select A9MPCORE
     select IMX
     select IMX_FEC
@@ -450,6 +456,7 @@ config ASPEED_SOC
 
 config MPS2
     bool
+    imply I2C_DEVICES
     select ARMSSE
     select LAN9118
     select MPS2_FPGAIO
@@ -466,6 +473,7 @@ config FSL_IMX7
     bool
     imply PCI_DEVICES
     imply TEST_DEVICES
+    imply I2C_DEVICES
     select A15MPCORE
     select PCI
     select IMX
@@ -481,6 +489,7 @@ config ARM_SMMUV3
 
 config FSL_IMX6UL
     bool
+    imply I2C_DEVICES
     select A15MPCORE
     select IMX
     select IMX_FEC
@@ -495,6 +504,7 @@ config MICROBIT
 
 config NRF51_SOC
     bool
+    imply I2C_DEVICES
     select I2C
     select ARM_V7M
     select UNIMP

hw/arm/armv7m.c

@@ -284,6 +284,12 @@ static void armv7m_realize(DeviceState *dev, Error **errp)
         return;
     }
 
+    /* cpuclk must be connected; refclk is optional */
+    if (!clock_has_source(s->cpuclk)) {
+        error_setg(errp, "armv7m: cpuclk must be connected");
+        return;
+    }
+
     memory_region_add_subregion_overlap(&s->container, 0, s->board_memory, -1);
 
     s->cpu = ARM_CPU(object_new_with_props(s->cpu_type, OBJECT(s), "cpu",
@@ -420,8 +426,18 @@ static void armv7m_realize(DeviceState *dev, Error **errp)
                                     &s->sysreg_ns_mem);
     }
 
-    /* Create and map the systick devices */
+    /*
-    qdev_connect_clock_in(DEVICE(&s->systick[M_REG_NS]), "refclk", s->refclk);
+     * Create and map the systick devices. Note that we only connect
+     * refclk if it has been connected to us; otherwise the systick
+     * device gets the wrong answer for clock_has_source(refclk), because
+     * it has an immediate source (the ARMv7M's clock object) but not
+     * an ultimate source, and then it won't correctly auto-select the
+     * CPU clock as its only possible clock source.
+     */
+    if (clock_has_source(s->refclk)) {
+        qdev_connect_clock_in(DEVICE(&s->systick[M_REG_NS]), "refclk",
+                              s->refclk);
+    }
     qdev_connect_clock_in(DEVICE(&s->systick[M_REG_NS]), "cpuclk", s->cpuclk);
     if (!sysbus_realize(SYS_BUS_DEVICE(&s->systick[M_REG_NS]), errp)) {
         return;
@@ -438,8 +454,10 @@ static void armv7m_realize(DeviceState *dev, Error **errp)
          */
         object_initialize_child(OBJECT(dev), "systick-reg-s",
                                 &s->systick[M_REG_S], TYPE_SYSTICK);
+        if (clock_has_source(s->refclk)) {
             qdev_connect_clock_in(DEVICE(&s->systick[M_REG_S]), "refclk",
                                   s->refclk);
+        }
         qdev_connect_clock_in(DEVICE(&s->systick[M_REG_S]), "cpuclk",
                               s->cpuclk);
 

hw/arm/npcm7xx_boards.c

@@ -34,6 +34,7 @@
 #define QUANTA_GSJ_POWER_ON_STRAPS 0x00001fff
 #define QUANTA_GBS_POWER_ON_STRAPS 0x000017ff
 #define KUDO_BMC_POWER_ON_STRAPS 0x00001fff
+#define MORI_BMC_POWER_ON_STRAPS 0x00001fff
 
 static const char npcm7xx_default_bootrom[] = "npcm7xx_bootrom.bin";
 
@@ -429,6 +430,21 @@ static void kudo_bmc_init(MachineState *machine)
     npcm7xx_load_kernel(machine, soc);
 }
 
+static void mori_bmc_init(MachineState *machine)
+{
+    NPCM7xxState *soc;
+
+    soc = npcm7xx_create_soc(machine, MORI_BMC_POWER_ON_STRAPS);
+    npcm7xx_connect_dram(soc, machine->ram);
+    qdev_realize(DEVICE(soc), NULL, &error_fatal);
+
+    npcm7xx_load_bootrom(machine, soc);
+    npcm7xx_connect_flash(&soc->fiu[1], 0, "mx66u51235f",
+                          drive_get(IF_MTD, 3, 0));
+
+    npcm7xx_load_kernel(machine, soc);
+}
+
 static void npcm7xx_set_soc_type(NPCM7xxMachineClass *nmc, const char *type)
 {
     NPCM7xxClass *sc = NPCM7XX_CLASS(object_class_by_name(type));
@@ -501,6 +517,18 @@ static void kudo_bmc_machine_class_init(ObjectClass *oc, void *data)
     mc->default_ram_size = 1 * GiB;
 };
 
+static void mori_bmc_machine_class_init(ObjectClass *oc, void *data)
+{
+    NPCM7xxMachineClass *nmc = NPCM7XX_MACHINE_CLASS(oc);
+    MachineClass *mc = MACHINE_CLASS(oc);
+
+    npcm7xx_set_soc_type(nmc, TYPE_NPCM730);
+
+    mc->desc = "Mori BMC (Cortex-A9)";
+    mc->init = mori_bmc_init;
+    mc->default_ram_size = 1 * GiB;
+}
+
 static const TypeInfo npcm7xx_machine_types[] = {
     {
         .name           = TYPE_NPCM7XX_MACHINE,
@@ -525,6 +553,10 @@ static const TypeInfo npcm7xx_machine_types[] = {
         .name           = MACHINE_TYPE_NAME("kudo-bmc"),
         .parent         = TYPE_NPCM7XX_MACHINE,
         .class_init     = kudo_bmc_machine_class_init,
+    }, {
+        .name           = MACHINE_TYPE_NAME("mori-bmc"),
+        .parent         = TYPE_NPCM7XX_MACHINE,
+        .class_init     = mori_bmc_machine_class_init,
     },
 };
 

hw/arm/nseries.c

@@ -24,6 +24,7 @@
 #include "chardev/char.h"
 #include "qemu/cutils.h"
 #include "qemu/bswap.h"
+#include "qemu/hw-version.h"
 #include "sysemu/reset.h"
 #include "sysemu/runstate.h"
 #include "sysemu/sysemu.h"

hw/arm/omap1.c

@@ -18,6 +18,7 @@
  */
 
 #include "qemu/osdep.h"
+#include "qemu/log.h"
 #include "qemu/error-report.h"
 #include "qemu/main-loop.h"
 #include "qapi/error.h"

hw/core/generic-loader.c

@@ -207,7 +207,7 @@ static void generic_loader_class_init(ObjectClass *klass, void *data)
     set_bit(DEVICE_CATEGORY_MISC, dc->categories);
 }
 
-static TypeInfo generic_loader_info = {
+static const TypeInfo generic_loader_info = {
     .name = TYPE_GENERIC_LOADER,
     .parent = TYPE_DEVICE,
     .instance_size = sizeof(GenericLoaderState),

hw/core/guest-loader.c

@@ -129,7 +129,7 @@ static void guest_loader_class_init(ObjectClass *klass, void *data)
     set_bit(DEVICE_CATEGORY_MISC, dc->categories);
 }
 
-static TypeInfo guest_loader_info = {
+static const TypeInfo guest_loader_info = {
     .name = TYPE_GUEST_LOADER,
     .parent = TYPE_DEVICE,
     .instance_size = sizeof(GuestLoaderState),

hw/core/ptimer.c

@@ -14,7 +14,6 @@
 #include "sysemu/cpu-timers.h"
 #include "sysemu/qtest.h"
 #include "block/aio.h"
-#include "sysemu/cpus.h"
 #include "hw/clock.h"
 
 #define DELTA_ADJUST     1

hw/display/bcm2835_fb.c

@@ -454,7 +454,7 @@ static void bcm2835_fb_class_init(ObjectClass *klass, void *data)
     dc->vmsd = &vmstate_bcm2835_fb;
 }
 
-static TypeInfo bcm2835_fb_info = {
+static const TypeInfo bcm2835_fb_info = {
     .name          = TYPE_BCM2835_FB,
     .parent        = TYPE_SYS_BUS_DEVICE,
     .instance_size = sizeof(BCM2835FBState),

hw/display/i2c-ddc.c

@@ -113,7 +113,7 @@ static void i2c_ddc_class_init(ObjectClass *oc, void *data)
     isc->send = i2c_ddc_tx;
 }
 
-static TypeInfo i2c_ddc_info = {
+static const TypeInfo i2c_ddc_info = {
     .name = TYPE_I2CDDC,
     .parent = TYPE_I2C_SLAVE,
     .instance_size = sizeof(I2CDDCState),

hw/display/macfb.c

@@ -782,14 +782,14 @@ static void macfb_nubus_class_init(ObjectClass *klass, void *data)
     device_class_set_props(dc, macfb_nubus_properties);
 }
 
-static TypeInfo macfb_sysbus_info = {
+static const TypeInfo macfb_sysbus_info = {
     .name          = TYPE_MACFB,
     .parent        = TYPE_SYS_BUS_DEVICE,
     .instance_size = sizeof(MacfbSysBusState),
     .class_init    = macfb_sysbus_class_init,
 };
 
-static TypeInfo macfb_nubus_info = {
+static const TypeInfo macfb_nubus_info = {
     .name          = TYPE_NUBUS_MACFB,
     .parent        = TYPE_NUBUS_DEVICE,
     .instance_size = sizeof(MacfbNubusState),

hw/display/omap_dss.c

@@ -19,6 +19,7 @@
  */
 
 #include "qemu/osdep.h"
+#include "qemu/log.h"
 #include "hw/hw.h"
 #include "hw/irq.h"
 #include "ui/console.h"

hw/display/virtio-vga.c

@@ -220,7 +220,7 @@ static void virtio_vga_base_class_init(ObjectClass *klass, void *data)
                                    virtio_vga_set_big_endian_fb);
 }
 
-static TypeInfo virtio_vga_base_info = {
+static const TypeInfo virtio_vga_base_info = {
     .name          = TYPE_VIRTIO_VGA_BASE,
     .parent        = TYPE_VIRTIO_PCI,
     .instance_size = sizeof(VirtIOVGABase),

hw/dma/bcm2835_dma.c

@@ -394,7 +394,7 @@ static void bcm2835_dma_class_init(ObjectClass *klass, void *data)
     dc->vmsd = &vmstate_bcm2835_dma;
 }
 
-static TypeInfo bcm2835_dma_info = {
+static const TypeInfo bcm2835_dma_info = {
     .name          = TYPE_BCM2835_DMA,
     .parent        = TYPE_SYS_BUS_DEVICE,
     .instance_size = sizeof(BCM2835DMAState),

hw/gpio/omap_gpio.c

@@ -19,6 +19,7 @@
  */
 
 #include "qemu/osdep.h"
+#include "qemu/log.h"
 #include "hw/irq.h"
 #include "hw/qdev-properties.h"
 #include "hw/arm/omap.h"

hw/i2c/Kconfig

@@ -1,6 +1,11 @@
 config I2C
     bool
 
+config I2C_DEVICES
+    # Device group for i2c devices which can reasonably be user-plugged
+    # to any board's i2c bus
+    bool
+
 config SMBUS
     bool
     select I2C

hw/i386/pc_piix.c

@@ -867,7 +867,7 @@ static void isa_bridge_class_init(ObjectClass *klass, void *data)
     k->class_id     = PCI_CLASS_BRIDGE_ISA;
 };
 
-static TypeInfo isa_bridge_info = {
+static const TypeInfo isa_bridge_info = {
     .name          = "igd-passthrough-isa-bridge",
     .parent        = TYPE_PCI_DEVICE,
     .instance_size = sizeof(PCIDevice),

hw/i386/sgx-epc.c

@@ -167,7 +167,7 @@ static void sgx_epc_class_init(ObjectClass *oc, void *data)
     mdc->fill_device_info = sgx_epc_md_fill_device_info;
 }
 
-static TypeInfo sgx_epc_info = {
+static const TypeInfo sgx_epc_info = {
     .name          = TYPE_SGX_EPC,
     .parent        = TYPE_DEVICE,
     .instance_size = sizeof(SGXEPCDevice),

hw/ide/core.c

@@ -29,6 +29,7 @@
 #include "qemu/error-report.h"
 #include "qemu/main-loop.h"
 #include "qemu/timer.h"
+#include "qemu/hw-version.h"
 #include "sysemu/sysemu.h"
 #include "sysemu/blockdev.h"
 #include "sysemu/dma.h"

hw/input/hid.c

@@ -114,6 +114,8 @@ static void hid_pointer_event(DeviceState *dev, QemuConsole *src,
         [INPUT_BUTTON_LEFT]   = 0x01,
         [INPUT_BUTTON_RIGHT]  = 0x02,
         [INPUT_BUTTON_MIDDLE] = 0x04,
+        [INPUT_BUTTON_SIDE] = 0x08,
+        [INPUT_BUTTON_EXTRA] = 0x10,
     };
     HIDState *hs = (HIDState *)dev;
     HIDPointerEvent *e;

hw/input/tsc210x.c

@@ -20,6 +20,7 @@
  */
 
 #include "qemu/osdep.h"
+#include "qemu/log.h"
 #include "hw/hw.h"
 #include "audio/audio.h"
 #include "qemu/timer.h"

hw/intc/bcm2835_ic.c

@@ -227,7 +227,7 @@ static void bcm2835_ic_class_init(ObjectClass *klass, void *data)
     dc->vmsd = &vmstate_bcm2835_ic;
 }
 
-static TypeInfo bcm2835_ic_info = {
+static const TypeInfo bcm2835_ic_info = {
     .name          = TYPE_BCM2835_IC,
     .parent        = TYPE_SYS_BUS_DEVICE,
     .instance_size = sizeof(BCM2835ICState),

hw/intc/bcm2836_control.c

@@ -392,7 +392,7 @@ static void bcm2836_control_class_init(ObjectClass *klass, void *data)
     dc->vmsd = &vmstate_bcm2836_control;
 }
 
-static TypeInfo bcm2836_control_info = {
+static const TypeInfo bcm2836_control_info = {
     .name          = TYPE_BCM2836_CONTROL,
     .parent        = TYPE_SYS_BUS_DEVICE,
     .instance_size = sizeof(BCM2836ControlState),

hw/ipmi/ipmi.c

@@ -85,7 +85,7 @@ static void ipmi_interface_class_init(ObjectClass *class, void *data)
     ik->do_hw_op = ipmi_do_hw_op;
 }
 
-static TypeInfo ipmi_interface_type_info = {
+static const TypeInfo ipmi_interface_type_info = {
     .name = TYPE_IPMI_INTERFACE,
     .parent = TYPE_INTERFACE,
     .class_size = sizeof(IPMIInterfaceClass),
@@ -120,7 +120,7 @@ static void bmc_class_init(ObjectClass *oc, void *data)
     device_class_set_props(dc, ipmi_bmc_properties);
 }
 
-static TypeInfo ipmi_bmc_type_info = {
+static const TypeInfo ipmi_bmc_type_info = {
     .name = TYPE_IPMI_BMC,
     .parent = TYPE_DEVICE,
     .instance_size = sizeof(IPMIBmc),

hw/mem/nvdimm.c

@@ -181,10 +181,25 @@ static MemoryRegion *nvdimm_md_get_memory_region(MemoryDeviceState *md,
 static void nvdimm_realize(PCDIMMDevice *dimm, Error **errp)
 {
     NVDIMMDevice *nvdimm = NVDIMM(dimm);
+    NVDIMMClass *ndc = NVDIMM_GET_CLASS(nvdimm);
 
     if (!nvdimm->nvdimm_mr) {
         nvdimm_prepare_memory_region(nvdimm, errp);
     }
+
+    if (ndc->realize) {
+        ndc->realize(nvdimm, errp);
+    }
+}
+
+static void nvdimm_unrealize(PCDIMMDevice *dimm)
+{
+    NVDIMMDevice *nvdimm = NVDIMM(dimm);
+    NVDIMMClass *ndc = NVDIMM_GET_CLASS(nvdimm);
+
+    if (ndc->unrealize) {
+        ndc->unrealize(nvdimm);
+    }
 }
 
 /*
@@ -240,6 +255,7 @@ static void nvdimm_class_init(ObjectClass *oc, void *data)
     DeviceClass *dc = DEVICE_CLASS(oc);
 
     ddc->realize = nvdimm_realize;
+    ddc->unrealize = nvdimm_unrealize;
     mdc->get_memory_region = nvdimm_md_get_memory_region;
     device_class_set_props(dc, nvdimm_properties);
 
@@ -248,7 +264,7 @@ static void nvdimm_class_init(ObjectClass *oc, void *data)
     set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
 }
 
-static TypeInfo nvdimm_info = {
+static const TypeInfo nvdimm_info = {
     .name          = TYPE_NVDIMM,
     .parent        = TYPE_PC_DIMM,
     .class_size    = sizeof(NVDIMMClass),

hw/mem/pc-dimm.c

@@ -216,6 +216,11 @@ static void pc_dimm_realize(DeviceState *dev, Error **errp)
 static void pc_dimm_unrealize(DeviceState *dev)
 {
     PCDIMMDevice *dimm = PC_DIMM(dev);
+    PCDIMMDeviceClass *ddc = PC_DIMM_GET_CLASS(dimm);
+
+    if (ddc->unrealize) {
+        ddc->unrealize(dimm);
+    }
 
     host_memory_backend_set_mapped(dimm->hostmem, false);
 }
@@ -286,7 +291,7 @@ static void pc_dimm_class_init(ObjectClass *oc, void *data)
     mdc->fill_device_info = pc_dimm_md_fill_device_info;
 }
 
-static TypeInfo pc_dimm_info = {
+static const TypeInfo pc_dimm_info = {
     .name          = TYPE_PC_DIMM,
     .parent        = TYPE_DEVICE,
     .instance_size = sizeof(PCDIMMDevice),

hw/misc/bcm2835_mbox.c

@@ -323,7 +323,7 @@ static void bcm2835_mbox_class_init(ObjectClass *klass, void *data)
     dc->vmsd = &vmstate_bcm2835_mbox;
 }
 
-static TypeInfo bcm2835_mbox_info = {
+static const TypeInfo bcm2835_mbox_info = {
     .name          = TYPE_BCM2835_MBOX,
     .parent        = TYPE_SYS_BUS_DEVICE,
     .instance_size = sizeof(BCM2835MboxState),

hw/misc/bcm2835_powermgt.c

@@ -144,7 +144,7 @@ static void bcm2835_powermgt_class_init(ObjectClass *klass, void *data)
     dc->vmsd = &vmstate_bcm2835_powermgt;
 }
 
-static TypeInfo bcm2835_powermgt_info = {
+static const TypeInfo bcm2835_powermgt_info = {
     .name          = TYPE_BCM2835_POWERMGT,
     .parent        = TYPE_SYS_BUS_DEVICE,
     .instance_size = sizeof(BCM2835PowerMgtState),

hw/misc/bcm2835_property.c

@@ -421,7 +421,7 @@ static void bcm2835_property_class_init(ObjectClass *klass, void *data)
     dc->vmsd = &vmstate_bcm2835_property;
 }
 
-static TypeInfo bcm2835_property_info = {
+static const TypeInfo bcm2835_property_info = {
     .name          = TYPE_BCM2835_PROPERTY,
     .parent        = TYPE_SYS_BUS_DEVICE,
     .instance_size = sizeof(BCM2835PropertyState),

hw/misc/bcm2835_rng.c

@@ -131,7 +131,7 @@ static void bcm2835_rng_class_init(ObjectClass *klass, void *data)
     dc->vmsd = &vmstate_bcm2835_rng;
 }
 
-static TypeInfo bcm2835_rng_info = {
+static const TypeInfo bcm2835_rng_info = {
     .name          = TYPE_BCM2835_RNG,
     .parent        = TYPE_SYS_BUS_DEVICE,
     .instance_size = sizeof(BCM2835RngState),

hw/misc/pvpanic-isa.c

@@ -77,7 +77,7 @@ static void pvpanic_isa_class_init(ObjectClass *klass, void *data)
     set_bit(DEVICE_CATEGORY_MISC, dc->categories);
 }
 
-static TypeInfo pvpanic_isa_info = {
+static const TypeInfo pvpanic_isa_info = {
     .name          = TYPE_PVPANIC_ISA_DEVICE,
     .parent        = TYPE_ISA_DEVICE,
     .instance_size = sizeof(PVPanicISAState),

hw/misc/pvpanic-pci.c

@@ -74,7 +74,7 @@ static void pvpanic_pci_class_init(ObjectClass *klass, void *data)
     set_bit(DEVICE_CATEGORY_MISC, dc->categories);
 }
 
-static TypeInfo pvpanic_pci_info = {
+static const TypeInfo pvpanic_pci_info = {
     .name          = TYPE_PVPANIC_PCI_DEVICE,
     .parent        = TYPE_PCI_DEVICE,
     .instance_size = sizeof(PVPanicPCIState),

hw/net/fsl_etsec/etsec.c

@@ -430,7 +430,7 @@ static void etsec_class_init(ObjectClass *klass, void *data)
     dc->user_creatable = true;
 }
 
-static TypeInfo etsec_info = {
+static const TypeInfo etsec_info = {
     .name                  = TYPE_ETSEC_COMMON,
     .parent                = TYPE_SYS_BUS_DEVICE,
     .instance_size         = sizeof(eTSEC),

hw/nvram/eeprom_at24c.c

@@ -54,7 +54,7 @@ struct EEPROMState {
 static
 int at24c_eeprom_event(I2CSlave *s, enum i2c_event event)
 {
-    EEPROMState *ee = container_of(s, EEPROMState, parent_obj);
+    EEPROMState *ee = AT24C_EE(s);
 
     switch (event) {
     case I2C_START_SEND:

hw/ppc/pegasos2.c

@@ -449,6 +449,11 @@ static target_ulong pegasos2_rtas(PowerPCCPU *cpu, Pegasos2MachineState *pm,
     }
 }
 
+static bool pegasos2_cpu_in_nested(PowerPCCPU *cpu)
+{
+    return false;
+}
+
 static void pegasos2_hypercall(PPCVirtualHypervisor *vhyp, PowerPCCPU *cpu)
 {
     Pegasos2MachineState *pm = PEGASOS2_MACHINE(vhyp);
@@ -504,6 +509,7 @@ static void pegasos2_machine_class_init(ObjectClass *oc, void *data)
     mc->default_ram_id = "pegasos2.ram";
     mc->default_ram_size = 512 * MiB;
 
+    vhc->cpu_in_nested = pegasos2_cpu_in_nested;
     vhc->hypercall = pegasos2_hypercall;
     vhc->cpu_exec_enter = vhyp_nop;
     vhc->cpu_exec_exit = vhyp_nop;

hw/ppc/ppc.c

@@ -1072,7 +1072,7 @@ clk_setup_cb cpu_ppc_tb_init (CPUPPCState *env, uint32_t freq)
     }
     /* Create new timer */
     tb_env->decr_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, &cpu_ppc_decr_cb, cpu);
-    if (env->has_hv_mode) {
+    if (env->has_hv_mode && !cpu->vhyp) {
         tb_env->hdecr_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, &cpu_ppc_hdecr_cb,
                                                 cpu);
     } else {
@@ -1083,6 +1083,27 @@ clk_setup_cb cpu_ppc_tb_init (CPUPPCState *env, uint32_t freq)
     return &cpu_ppc_set_tb_clk;
 }
 
+/* cpu_ppc_hdecr_init may be used if the timer is not used by HDEC emulation */
+void cpu_ppc_hdecr_init(CPUPPCState *env)
+{
+    PowerPCCPU *cpu = env_archcpu(env);
+
+    assert(env->tb_env->hdecr_timer == NULL);
+
+    env->tb_env->hdecr_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL,
+                                            &cpu_ppc_hdecr_cb, cpu);
+}
+
+void cpu_ppc_hdecr_exit(CPUPPCState *env)
+{
+    PowerPCCPU *cpu = env_archcpu(env);
+
+    timer_free(env->tb_env->hdecr_timer);
+    env->tb_env->hdecr_timer = NULL;
+
+    cpu_ppc_hdecr_lower(cpu);
+}
+
 /*****************************************************************************/
 /* PowerPC 40x timers */
 

hw/ppc/prep_systemio.c

@@ -300,7 +300,7 @@ static void prep_systemio_class_initfn(ObjectClass *klass, void *data)
     device_class_set_props(dc, prep_systemio_properties);
 }
 
-static TypeInfo prep_systemio800_info = {
+static const TypeInfo prep_systemio800_info = {
     .name          = TYPE_PREP_SYSTEMIO,
     .parent        = TYPE_ISA_DEVICE,
     .instance_size = sizeof(PrepSystemIoState),

hw/ppc/spapr.c

@@ -1270,6 +1270,8 @@ static void emulate_spapr_hypercall(PPCVirtualHypervisor *vhyp,
     /* The TCG path should also be holding the BQL at this point */
     g_assert(qemu_mutex_iothread_locked());
 
+    g_assert(!vhyp_cpu_in_nested(cpu));
+
     if (msr_pr) {
         hcall_dprintf("Hypercall made with MSR[PR]=1\n");
         env->gpr[3] = H_PRIVILEGE;
@@ -1309,13 +1311,40 @@ void spapr_set_all_lpcrs(target_ulong value, target_ulong mask)
     }
 }
 
-static void spapr_get_pate(PPCVirtualHypervisor *vhyp, ppc_v3_pate_t *entry)
+static bool spapr_get_pate(PPCVirtualHypervisor *vhyp, PowerPCCPU *cpu,
+                           target_ulong lpid, ppc_v3_pate_t *entry)
 {
     SpaprMachineState *spapr = SPAPR_MACHINE(vhyp);
+    SpaprCpuState *spapr_cpu = spapr_cpu_state(cpu);
+
+    if (!spapr_cpu->in_nested) {
+        assert(lpid == 0);
 
         /* Copy PATE1:GR into PATE0:HR */
         entry->dw0 = spapr->patb_entry & PATE0_HR;
         entry->dw1 = spapr->patb_entry;
+
+    } else {
+        uint64_t patb, pats;
+
+        assert(lpid != 0);
+
+        patb = spapr->nested_ptcr & PTCR_PATB;
+        pats = spapr->nested_ptcr & PTCR_PATS;
+
+        /* Calculate number of entries */
+        pats = 1ull << (pats + 12 - 4);
+        if (pats <= lpid) {
+            return false;
+        }
+
+        /* Grab entry */
+        patb += 16 * lpid;
+        entry->dw0 = ldq_phys(CPU(cpu)->as, patb);
+        entry->dw1 = ldq_phys(CPU(cpu)->as, patb + 8);
+    }
+
+    return true;
 }
 
 #define HPTE(_table, _i)   (void *)(((uint64_t *)(_table)) + ((_i) * 2))
@@ -1634,6 +1663,8 @@ static void spapr_machine_reset(MachineState *machine)
         spapr->ov5_cas = spapr_ovec_clone(spapr->ov5);
     }
 
+    spapr_nvdimm_finish_flushes();
+
     /* DRC reset may cause a device to be unplugged. This will cause troubles
      * if this device is used by another device (eg, a running vhost backend
      * will crash QEMU if the DIMM holding the vring goes away). To avoid such
@@ -4465,6 +4496,13 @@ PowerPCCPU *spapr_find_cpu(int vcpu_id)
     return NULL;
 }
 
+static bool spapr_cpu_in_nested(PowerPCCPU *cpu)
+{
+    SpaprCpuState *spapr_cpu = spapr_cpu_state(cpu);
+
+    return spapr_cpu->in_nested;
+}
+
 static void spapr_cpu_exec_enter(PPCVirtualHypervisor *vhyp, PowerPCCPU *cpu)
 {
     SpaprCpuState *spapr_cpu = spapr_cpu_state(cpu);
@@ -4573,6 +4611,8 @@ static void spapr_machine_class_init(ObjectClass *oc, void *data)
     fwc->get_dev_path = spapr_get_fw_dev_path;
     nc->nmi_monitor_handler = spapr_nmi;
     smc->phb_placement = spapr_phb_placement;
+    vhc->cpu_in_nested = spapr_cpu_in_nested;
+    vhc->deliver_hv_excp = spapr_exit_nested;
     vhc->hypercall = emulate_spapr_hypercall;
     vhc->hpt_mask = spapr_hpt_mask;
     vhc->map_hptes = spapr_map_hptes;

hw/ppc/spapr_caps.c

@@ -444,19 +444,23 @@ static void cap_nested_kvm_hv_apply(SpaprMachineState *spapr,
 {
     ERRP_GUARD();
     PowerPCCPU *cpu = POWERPC_CPU(first_cpu);
+    CPUPPCState *env = &cpu->env;
 
     if (!val) {
         /* capability disabled by default */
         return;
     }
 
-    if (tcg_enabled()) {
+    if (!(env->insns_flags2 & PPC2_ISA300)) {
-        error_setg(errp, "No Nested KVM-HV support in TCG");
+        error_setg(errp, "Nested-HV only supported on POWER9 and later");
         error_append_hint(errp, "Try appending -machine cap-nested-hv=off\n");
-    } else if (kvm_enabled()) {
+        return;
+    }
+
+    if (kvm_enabled()) {
         if (!ppc_check_compat(cpu, CPU_POWERPC_LOGICAL_3_00, 0,
                               spapr->max_compat_pvr)) {
-            error_setg(errp, "Nested KVM-HV only supported on POWER9");
+            error_setg(errp, "Nested-HV only supported on POWER9 and later");
             error_append_hint(errp,
                               "Try appending -machine max-cpu-compat=power9\n");
             return;
@@ -464,7 +468,7 @@ static void cap_nested_kvm_hv_apply(SpaprMachineState *spapr,
 
         if (!kvmppc_has_cap_nested_kvm_hv()) {
             error_setg(errp,
-                       "KVM implementation does not support Nested KVM-HV");
+                       "KVM implementation does not support Nested-HV");
             error_append_hint(errp,
                               "Try appending -machine cap-nested-hv=off\n");
         } else if (kvmppc_set_cap_nested_kvm_hv(val) < 0) {

hw/ppc/spapr_cpu_core.c

@@ -261,12 +261,12 @@ static bool spapr_realize_vcpu(PowerPCCPU *cpu, SpaprMachineState *spapr,
         return false;
     }
 
-    /* Set time-base frequency to 512 MHz */
-    cpu_ppc_tb_init(env, SPAPR_TIMEBASE_FREQ);
-
     cpu_ppc_set_vhyp(cpu, PPC_VIRTUAL_HYPERVISOR(spapr));
     kvmppc_set_papr(cpu);
 
+    /* Set time-base frequency to 512 MHz. vhyp must be set first. */
+    cpu_ppc_tb_init(env, SPAPR_TIMEBASE_FREQ);
+
     if (spapr_irq_cpu_intc_create(spapr, cpu, errp) < 0) {
         qdev_unrealize(DEVICE(cpu));
         return false;

hw/ppc/spapr_hcall.c

@@ -9,6 +9,7 @@
 #include "qemu/error-report.h"
 #include "exec/exec-all.h"
 #include "helper_regs.h"
+#include "hw/ppc/ppc.h"
 #include "hw/ppc/spapr.h"
 #include "hw/ppc/spapr_cpu_core.h"
 #include "mmu-hash64.h"
@@ -1497,6 +1498,333 @@ static void hypercall_register_softmmu(void)
 }
 #endif
 
+/* TCG only */
+#define PRTS_MASK      0x1f
+
+static target_ulong h_set_ptbl(PowerPCCPU *cpu,
+                               SpaprMachineState *spapr,
+                               target_ulong opcode,
+                               target_ulong *args)
+{
+    target_ulong ptcr = args[0];
+
+    if (!spapr_get_cap(spapr, SPAPR_CAP_NESTED_KVM_HV)) {
+        return H_FUNCTION;
+    }
+
+    if ((ptcr & PRTS_MASK) + 12 - 4 > 12) {
+        return H_PARAMETER;
+    }
+
+    spapr->nested_ptcr = ptcr; /* Save new partition table */
+
+    return H_SUCCESS;
+}
+
+static target_ulong h_tlb_invalidate(PowerPCCPU *cpu,
+                                     SpaprMachineState *spapr,
+                                     target_ulong opcode,
+                                     target_ulong *args)
+{
+    /*
+     * The spapr virtual hypervisor nested HV implementation retains no L2
+     * translation state except for TLB. And the TLB is always invalidated
+     * across L1<->L2 transitions, so nothing is required here.
+     */
+
+    return H_SUCCESS;
+}
+
+static target_ulong h_copy_tofrom_guest(PowerPCCPU *cpu,
+                                        SpaprMachineState *spapr,
+                                        target_ulong opcode,
+                                        target_ulong *args)
+{
+    /*
+     * This HCALL is not required, L1 KVM will take a slow path and walk the
+     * page tables manually to do the data copy.
+     */
+    return H_FUNCTION;
+}
+
+/*
+ * When this handler returns, the environment is switched to the L2 guest
+ * and TCG begins running that. spapr_exit_nested() performs the switch from
+ * L2 back to L1 and returns from the H_ENTER_NESTED hcall.
+ */
+static target_ulong h_enter_nested(PowerPCCPU *cpu,
+                                   SpaprMachineState *spapr,
+                                   target_ulong opcode,
+                                   target_ulong *args)
+{
+    PowerPCCPUClass *pcc = POWERPC_CPU_GET_CLASS(cpu);
+    CPUState *cs = CPU(cpu);
+    CPUPPCState *env = &cpu->env;
+    SpaprCpuState *spapr_cpu = spapr_cpu_state(cpu);
+    target_ulong hv_ptr = args[0];
+    target_ulong regs_ptr = args[1];
+    target_ulong hdec, now = cpu_ppc_load_tbl(env);
+    target_ulong lpcr, lpcr_mask;
+    struct kvmppc_hv_guest_state *hvstate;
+    struct kvmppc_hv_guest_state hv_state;
+    struct kvmppc_pt_regs *regs;
+    hwaddr len;
+    uint64_t cr;
+    int i;
+
+    if (spapr->nested_ptcr == 0) {
+        return H_NOT_AVAILABLE;
+    }
+
+    len = sizeof(*hvstate);
+    hvstate = address_space_map(CPU(cpu)->as, hv_ptr, &len, false,
+                                MEMTXATTRS_UNSPECIFIED);
+    if (len != sizeof(*hvstate)) {
+        address_space_unmap(CPU(cpu)->as, hvstate, len, 0, false);
+        return H_PARAMETER;
+    }
+
+    memcpy(&hv_state, hvstate, len);
+
+    address_space_unmap(CPU(cpu)->as, hvstate, len, len, false);
+
+    /*
+     * We accept versions 1 and 2. Version 2 fields are unused because TCG
+     * does not implement DAWR*.
+     */
+    if (hv_state.version > HV_GUEST_STATE_VERSION) {
+        return H_PARAMETER;
+    }
+
+    spapr_cpu->nested_host_state = g_try_malloc(sizeof(CPUPPCState));
+    if (!spapr_cpu->nested_host_state) {
+        return H_NO_MEM;
+    }
+
+    memcpy(spapr_cpu->nested_host_state, env, sizeof(CPUPPCState));
+
+    len = sizeof(*regs);
+    regs = address_space_map(CPU(cpu)->as, regs_ptr, &len, false,
+                                MEMTXATTRS_UNSPECIFIED);
+    if (!regs || len != sizeof(*regs)) {
+        address_space_unmap(CPU(cpu)->as, regs, len, 0, false);
+        g_free(spapr_cpu->nested_host_state);
+        return H_P2;
+    }
+
+    len = sizeof(env->gpr);
+    assert(len == sizeof(regs->gpr));
+    memcpy(env->gpr, regs->gpr, len);
+
+    env->lr = regs->link;
+    env->ctr = regs->ctr;
+    cpu_write_xer(env, regs->xer);
+
+    cr = regs->ccr;
+    for (i = 7; i >= 0; i--) {
+        env->crf[i] = cr & 15;
+        cr >>= 4;
+    }
+
+    env->msr = regs->msr;
+    env->nip = regs->nip;
+
+    address_space_unmap(CPU(cpu)->as, regs, len, len, false);
+
+    env->cfar = hv_state.cfar;
+
+    assert(env->spr[SPR_LPIDR] == 0);
+    env->spr[SPR_LPIDR] = hv_state.lpid;
+
+    lpcr_mask = LPCR_DPFD | LPCR_ILE | LPCR_AIL | LPCR_LD | LPCR_MER;
+    lpcr = (env->spr[SPR_LPCR] & ~lpcr_mask) | (hv_state.lpcr & lpcr_mask);
+    lpcr |= LPCR_HR | LPCR_UPRT | LPCR_GTSE | LPCR_HVICE | LPCR_HDICE;
+    lpcr &= ~LPCR_LPES0;
+    env->spr[SPR_LPCR] = lpcr & pcc->lpcr_mask;
+
+    env->spr[SPR_PCR] = hv_state.pcr;
+    /* hv_state.amor is not used */
+    env->spr[SPR_DPDES] = hv_state.dpdes;
+    env->spr[SPR_HFSCR] = hv_state.hfscr;
+    hdec = hv_state.hdec_expiry - now;
+    spapr_cpu->nested_tb_offset = hv_state.tb_offset;
+    /* TCG does not implement DAWR*, CIABR, PURR, SPURR, IC, VTB, HEIR SPRs*/
+    env->spr[SPR_SRR0] = hv_state.srr0;
+    env->spr[SPR_SRR1] = hv_state.srr1;
+    env->spr[SPR_SPRG0] = hv_state.sprg[0];
+    env->spr[SPR_SPRG1] = hv_state.sprg[1];
+    env->spr[SPR_SPRG2] = hv_state.sprg[2];
+    env->spr[SPR_SPRG3] = hv_state.sprg[3];
+    env->spr[SPR_BOOKS_PID] = hv_state.pidr;
+    env->spr[SPR_PPR] = hv_state.ppr;
+
+    cpu_ppc_hdecr_init(env);
+    cpu_ppc_store_hdecr(env, hdec);
+
+    /*
+     * The hv_state.vcpu_token is not needed. It is used by the KVM
+     * implementation to remember which L2 vCPU last ran on which physical
+     * CPU so as to invalidate process scope translations if it is moved
+     * between physical CPUs. For now TLBs are always flushed on L1<->L2
+     * transitions so this is not a problem.
+     *
+     * Could validate that the same vcpu_token does not attempt to run on
+     * different L1 vCPUs at the same time, but that would be a L1 KVM bug
+     * and it's not obviously worth a new data structure to do it.
+     */
+
+    env->tb_env->tb_offset += spapr_cpu->nested_tb_offset;
+    spapr_cpu->in_nested = true;
+
+    hreg_compute_hflags(env);
+    tlb_flush(cs);
+    env->reserve_addr = -1; /* Reset the reservation */
+
+    /*
+     * The spapr hcall helper sets env->gpr[3] to the return value, but at
+     * this point the L1 is not returning from the hcall but rather we
+     * start running the L2, so r3 must not be clobbered, so return env->gpr[3]
+     * to leave it unchanged.
+     */
+    return env->gpr[3];
+}
+
+void spapr_exit_nested(PowerPCCPU *cpu, int excp)
+{
+    CPUState *cs = CPU(cpu);
+    CPUPPCState *env = &cpu->env;
+    SpaprCpuState *spapr_cpu = spapr_cpu_state(cpu);
+    target_ulong r3_return = env->excp_vectors[excp]; /* hcall return value */
+    target_ulong hv_ptr = spapr_cpu->nested_host_state->gpr[4];
+    target_ulong regs_ptr = spapr_cpu->nested_host_state->gpr[5];
+    struct kvmppc_hv_guest_state *hvstate;
+    struct kvmppc_pt_regs *regs;
+    hwaddr len;
+    uint64_t cr;
+    int i;
+
+    assert(spapr_cpu->in_nested);
+
+    cpu_ppc_hdecr_exit(env);
+
+    len = sizeof(*hvstate);
+    hvstate = address_space_map(CPU(cpu)->as, hv_ptr, &len, true,
+                                MEMTXATTRS_UNSPECIFIED);
+    if (len != sizeof(*hvstate)) {
+        address_space_unmap(CPU(cpu)->as, hvstate, len, 0, true);
+        r3_return = H_PARAMETER;
+        goto out_restore_l1;
+    }
+
+    hvstate->cfar = env->cfar;
+    hvstate->lpcr = env->spr[SPR_LPCR];
+    hvstate->pcr = env->spr[SPR_PCR];
+    hvstate->dpdes = env->spr[SPR_DPDES];
+    hvstate->hfscr = env->spr[SPR_HFSCR];
+
+    if (excp == POWERPC_EXCP_HDSI) {
+        hvstate->hdar = env->spr[SPR_HDAR];
+        hvstate->hdsisr = env->spr[SPR_HDSISR];
+        hvstate->asdr = env->spr[SPR_ASDR];
+    } else if (excp == POWERPC_EXCP_HISI) {
+        hvstate->asdr = env->spr[SPR_ASDR];
+    }
+
+    /* HEIR should be implemented for HV mode and saved here. */
+    hvstate->srr0 = env->spr[SPR_SRR0];
+    hvstate->srr1 = env->spr[SPR_SRR1];
+    hvstate->sprg[0] = env->spr[SPR_SPRG0];
+    hvstate->sprg[1] = env->spr[SPR_SPRG1];
+    hvstate->sprg[2] = env->spr[SPR_SPRG2];
+    hvstate->sprg[3] = env->spr[SPR_SPRG3];
+    hvstate->pidr = env->spr[SPR_BOOKS_PID];
+    hvstate->ppr = env->spr[SPR_PPR];
+
+    /* Is it okay to specify write length larger than actual data written? */
+    address_space_unmap(CPU(cpu)->as, hvstate, len, len, true);
+
+    len = sizeof(*regs);
+    regs = address_space_map(CPU(cpu)->as, regs_ptr, &len, true,
+                                MEMTXATTRS_UNSPECIFIED);
+    if (!regs || len != sizeof(*regs)) {
+        address_space_unmap(CPU(cpu)->as, regs, len, 0, true);
+        r3_return = H_P2;
+        goto out_restore_l1;
+    }
+
+    len = sizeof(env->gpr);
+    assert(len == sizeof(regs->gpr));
+    memcpy(regs->gpr, env->gpr, len);
+
+    regs->link = env->lr;
+    regs->ctr = env->ctr;
+    regs->xer = cpu_read_xer(env);
+
+    cr = 0;
+    for (i = 0; i < 8; i++) {
+        cr |= (env->crf[i] & 15) << (4 * (7 - i));
+    }
+    regs->ccr = cr;
+
+    if (excp == POWERPC_EXCP_MCHECK ||
+        excp == POWERPC_EXCP_RESET ||
+        excp == POWERPC_EXCP_SYSCALL) {
+        regs->nip = env->spr[SPR_SRR0];
+        regs->msr = env->spr[SPR_SRR1] & env->msr_mask;
+    } else {
+        regs->nip = env->spr[SPR_HSRR0];
+        regs->msr = env->spr[SPR_HSRR1] & env->msr_mask;
+    }
+
+    /* Is it okay to specify write length larger than actual data written? */
+    address_space_unmap(CPU(cpu)->as, regs, len, len, true);
+
+out_restore_l1:
+    memcpy(env->gpr, spapr_cpu->nested_host_state->gpr, sizeof(env->gpr));
+    env->lr = spapr_cpu->nested_host_state->lr;
+    env->ctr = spapr_cpu->nested_host_state->ctr;
+    memcpy(env->crf, spapr_cpu->nested_host_state->crf, sizeof(env->crf));
+    env->cfar = spapr_cpu->nested_host_state->cfar;
+    env->xer = spapr_cpu->nested_host_state->xer;
+    env->so = spapr_cpu->nested_host_state->so;
+    env->ov = spapr_cpu->nested_host_state->ov;
+    env->ov32 = spapr_cpu->nested_host_state->ov32;
+    env->ca32 = spapr_cpu->nested_host_state->ca32;
+    env->msr = spapr_cpu->nested_host_state->msr;
+    env->nip = spapr_cpu->nested_host_state->nip;
+
+    assert(env->spr[SPR_LPIDR] != 0);
+    env->spr[SPR_LPCR] = spapr_cpu->nested_host_state->spr[SPR_LPCR];
+    env->spr[SPR_LPIDR] = spapr_cpu->nested_host_state->spr[SPR_LPIDR];
+    env->spr[SPR_PCR] = spapr_cpu->nested_host_state->spr[SPR_PCR];
+    env->spr[SPR_DPDES] = 0;
+    env->spr[SPR_HFSCR] = spapr_cpu->nested_host_state->spr[SPR_HFSCR];
+    env->spr[SPR_SRR0] = spapr_cpu->nested_host_state->spr[SPR_SRR0];
+    env->spr[SPR_SRR1] = spapr_cpu->nested_host_state->spr[SPR_SRR1];
+    env->spr[SPR_SPRG0] = spapr_cpu->nested_host_state->spr[SPR_SPRG0];
+    env->spr[SPR_SPRG1] = spapr_cpu->nested_host_state->spr[SPR_SPRG1];
+    env->spr[SPR_SPRG2] = spapr_cpu->nested_host_state->spr[SPR_SPRG2];
+    env->spr[SPR_SPRG3] = spapr_cpu->nested_host_state->spr[SPR_SPRG3];
+    env->spr[SPR_BOOKS_PID] = spapr_cpu->nested_host_state->spr[SPR_BOOKS_PID];
+    env->spr[SPR_PPR] = spapr_cpu->nested_host_state->spr[SPR_PPR];
+
+    /*
+     * Return the interrupt vector address from H_ENTER_NESTED to the L1
+     * (or error code).
+     */
+    env->gpr[3] = r3_return;
+
+    env->tb_env->tb_offset -= spapr_cpu->nested_tb_offset;
+    spapr_cpu->in_nested = false;
+
+    hreg_compute_hflags(env);
+    tlb_flush(cs);
+    env->reserve_addr = -1; /* Reset the reservation */
+
+    g_free(spapr_cpu->nested_host_state);
+    spapr_cpu->nested_host_state = NULL;
+}
+
 static void hypercall_register_types(void)
 {
     hypercall_register_softmmu();
@@ -1552,6 +1880,11 @@ static void hypercall_register_types(void)
     spapr_register_hypercall(KVMPPC_H_CAS, h_client_architecture_support);
 
     spapr_register_hypercall(KVMPPC_H_UPDATE_DT, h_update_dt);
+
+    spapr_register_hypercall(KVMPPC_H_SET_PARTITION_TABLE, h_set_ptbl);
+    spapr_register_hypercall(KVMPPC_H_ENTER_NESTED, h_enter_nested);
+    spapr_register_hypercall(KVMPPC_H_TLB_INVALIDATE, h_tlb_invalidate);
+    spapr_register_hypercall(KVMPPC_H_COPY_TOFROM_GUEST, h_copy_tofrom_guest);
 }
 
 type_init(hypercall_register_types)

hw/ppc/spapr_iommu.c

@@ -685,7 +685,7 @@ static void spapr_tce_table_class_init(ObjectClass *klass, void *data)
     spapr_register_hypercall(H_STUFF_TCE, h_stuff_tce);
 }
 
-static TypeInfo spapr_tce_table_info = {
+static const TypeInfo spapr_tce_table_info = {
     .name = TYPE_SPAPR_TCE_TABLE,
     .parent = TYPE_DEVICE,
     .instance_size = sizeof(SpaprTceTable),

hw/ppc/spapr_nvdimm.c

@@ -22,6 +22,7 @@
  * THE SOFTWARE.
  */
 #include "qemu/osdep.h"
+#include "qemu/cutils.h"
 #include "qapi/error.h"
 #include "hw/ppc/spapr_drc.h"
 #include "hw/ppc/spapr_nvdimm.h"
@@ -30,6 +31,10 @@
 #include "hw/ppc/fdt.h"
 #include "qemu/range.h"
 #include "hw/ppc/spapr_numa.h"
+#include "block/thread-pool.h"
+#include "migration/vmstate.h"
+#include "qemu/pmem.h"
+#include "hw/qdev-properties.h"
 
 /* DIMM health bitmap bitmap indicators. Taken from kernel's papr_scm.c */
 /* SCM device is unable to persist memory contents */
@@ -47,11 +52,25 @@
 /* Have an explicit check for alignment */
 QEMU_BUILD_BUG_ON(SPAPR_MINIMUM_SCM_BLOCK_SIZE % SPAPR_MEMORY_BLOCK_SIZE);
 
+#define TYPE_SPAPR_NVDIMM "spapr-nvdimm"
+OBJECT_DECLARE_TYPE(SpaprNVDIMMDevice, SPAPRNVDIMMClass, SPAPR_NVDIMM)
+
+struct SPAPRNVDIMMClass {
+    /* private */
+    NVDIMMClass parent_class;
+
+    /* public */
+    void (*realize)(NVDIMMDevice *dimm, Error **errp);
+    void (*unrealize)(NVDIMMDevice *dimm, Error **errp);
+};
+
 bool spapr_nvdimm_validate(HotplugHandler *hotplug_dev, NVDIMMDevice *nvdimm,
                            uint64_t size, Error **errp)
 {
     const MachineClass *mc = MACHINE_GET_CLASS(hotplug_dev);
     const MachineState *ms = MACHINE(hotplug_dev);
+    PCDIMMDevice *dimm = PC_DIMM(nvdimm);
+    MemoryRegion *mr = host_memory_backend_get_memory(dimm->hostmem);
     g_autofree char *uuidstr = NULL;
     QemuUUID uuid;
     int ret;
@@ -89,6 +108,14 @@ bool spapr_nvdimm_validate(HotplugHandler *hotplug_dev, NVDIMMDevice *nvdimm,
         return false;
     }
 
+    if (object_dynamic_cast(OBJECT(nvdimm), TYPE_SPAPR_NVDIMM) &&
+        (memory_region_get_fd(mr) < 0)) {
+        error_setg(errp, "spapr-nvdimm device requires the "
+                   "memdev %s to be of memory-backend-file type",
+                   object_get_canonical_path_component(OBJECT(dimm->hostmem)));
+        return false;
+    }
+
     return true;
 }
 
@@ -160,6 +187,20 @@ static int spapr_dt_nvdimm(SpaprMachineState *spapr, void *fdt,
                              "operating-system")));
     _FDT(fdt_setprop(fdt, child_offset, "ibm,cache-flush-required", NULL, 0));
 
+    if (object_dynamic_cast(OBJECT(nvdimm), TYPE_SPAPR_NVDIMM)) {
+        bool is_pmem = false, pmem_override = false;
+        PCDIMMDevice *dimm = PC_DIMM(nvdimm);
+        HostMemoryBackend *hostmem = dimm->hostmem;
+
+        is_pmem = object_property_get_bool(OBJECT(hostmem), "pmem", NULL);
+        pmem_override = object_property_get_bool(OBJECT(nvdimm),
+                                                 "pmem-override", NULL);
+        if (!is_pmem || pmem_override) {
+            _FDT(fdt_setprop(fdt, child_offset, "ibm,hcall-flush-required",
+                             NULL, 0));
+        }
+    }
+
     return child_offset;
 }
 
@@ -375,6 +416,293 @@ static target_ulong h_scm_bind_mem(PowerPCCPU *cpu, SpaprMachineState *spapr,
     return H_SUCCESS;
 }
 
+typedef struct SpaprNVDIMMDeviceFlushState {
+    uint64_t continue_token;
+    int64_t hcall_ret;
+    uint32_t drcidx;
+
+    QLIST_ENTRY(SpaprNVDIMMDeviceFlushState) node;
+} SpaprNVDIMMDeviceFlushState;
+
+typedef struct SpaprNVDIMMDevice SpaprNVDIMMDevice;
+struct SpaprNVDIMMDevice {
+    /* private */
+    NVDIMMDevice parent_obj;
+
+    bool hcall_flush_required;
+    uint64_t nvdimm_flush_token;
+    QLIST_HEAD(, SpaprNVDIMMDeviceFlushState) pending_nvdimm_flush_states;
+    QLIST_HEAD(, SpaprNVDIMMDeviceFlushState) completed_nvdimm_flush_states;
+
+    /* public */
+
+    /*
+     * The 'on' value for this property forced the qemu to enable the hcall
+     * flush for the nvdimm device even if the backend is a pmem
+     */
+    bool pmem_override;
+};
+
+static int flush_worker_cb(void *opaque)
+{
+    SpaprNVDIMMDeviceFlushState *state = opaque;
+    SpaprDrc *drc = spapr_drc_by_index(state->drcidx);
+    PCDIMMDevice *dimm = PC_DIMM(drc->dev);
+    HostMemoryBackend *backend = MEMORY_BACKEND(dimm->hostmem);
+    int backend_fd = memory_region_get_fd(&backend->mr);
+
+    if (object_property_get_bool(OBJECT(backend), "pmem", NULL)) {
+        MemoryRegion *mr = host_memory_backend_get_memory(dimm->hostmem);
+        void *ptr = memory_region_get_ram_ptr(mr);
+        size_t size = object_property_get_uint(OBJECT(dimm), PC_DIMM_SIZE_PROP,
+                                               NULL);
+
+        /* flush pmem backend */
+        pmem_persist(ptr, size);
+    } else {
+        /* flush raw backing image */
+        if (qemu_fdatasync(backend_fd) < 0) {
+            error_report("papr_scm: Could not sync nvdimm to backend file: %s",
+                         strerror(errno));
+            return H_HARDWARE;
+        }
+    }
+
+    return H_SUCCESS;
+}
+
+static void spapr_nvdimm_flush_completion_cb(void *opaque, int hcall_ret)
+{
+    SpaprNVDIMMDeviceFlushState *state = opaque;
+    SpaprDrc *drc = spapr_drc_by_index(state->drcidx);
+    SpaprNVDIMMDevice *s_nvdimm = SPAPR_NVDIMM(drc->dev);
+
+    state->hcall_ret = hcall_ret;
+    QLIST_REMOVE(state, node);
+    QLIST_INSERT_HEAD(&s_nvdimm->completed_nvdimm_flush_states, state, node);
+}
+
+static int spapr_nvdimm_flush_post_load(void *opaque, int version_id)
+{
+    SpaprNVDIMMDevice *s_nvdimm = (SpaprNVDIMMDevice *)opaque;
+    SpaprNVDIMMDeviceFlushState *state;
+    ThreadPool *pool = aio_get_thread_pool(qemu_get_aio_context());
+    HostMemoryBackend *backend = MEMORY_BACKEND(PC_DIMM(s_nvdimm)->hostmem);
+    bool is_pmem = object_property_get_bool(OBJECT(backend), "pmem", NULL);
+    bool pmem_override = object_property_get_bool(OBJECT(s_nvdimm),
+                                                  "pmem-override", NULL);
+    bool dest_hcall_flush_required = pmem_override || !is_pmem;
+
+    if (!s_nvdimm->hcall_flush_required && dest_hcall_flush_required) {
+        error_report("The file backend for the spapr-nvdimm device %s at "
+                     "source is a pmem, use pmem=on and pmem-override=off to "
+                     "continue.", DEVICE(s_nvdimm)->id);
+        return -EINVAL;
+    }
+    if (s_nvdimm->hcall_flush_required && !dest_hcall_flush_required) {
+        error_report("The guest expects hcall-flush support for the "
+                     "spapr-nvdimm device %s, use pmem_override=on to "
+                     "continue.", DEVICE(s_nvdimm)->id);
+        return -EINVAL;
+    }
+
+    QLIST_FOREACH(state, &s_nvdimm->pending_nvdimm_flush_states, node) {
+        thread_pool_submit_aio(pool, flush_worker_cb, state,
+                               spapr_nvdimm_flush_completion_cb, state);
+    }
+
+    return 0;
+}
+
+static const VMStateDescription vmstate_spapr_nvdimm_flush_state = {
+     .name = "spapr_nvdimm_flush_state",
+     .version_id = 1,
+     .minimum_version_id = 1,
+     .fields = (VMStateField[]) {
+         VMSTATE_UINT64(continue_token, SpaprNVDIMMDeviceFlushState),
+         VMSTATE_INT64(hcall_ret, SpaprNVDIMMDeviceFlushState),
+         VMSTATE_UINT32(drcidx, SpaprNVDIMMDeviceFlushState),
+         VMSTATE_END_OF_LIST()
+     },
+};
+
+const VMStateDescription vmstate_spapr_nvdimm_states = {
+    .name = "spapr_nvdimm_states",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .post_load = spapr_nvdimm_flush_post_load,
+    .fields = (VMStateField[]) {
+        VMSTATE_BOOL(hcall_flush_required, SpaprNVDIMMDevice),
+        VMSTATE_UINT64(nvdimm_flush_token, SpaprNVDIMMDevice),
+        VMSTATE_QLIST_V(completed_nvdimm_flush_states, SpaprNVDIMMDevice, 1,
+                        vmstate_spapr_nvdimm_flush_state,
+                        SpaprNVDIMMDeviceFlushState, node),
+        VMSTATE_QLIST_V(pending_nvdimm_flush_states, SpaprNVDIMMDevice, 1,
+                        vmstate_spapr_nvdimm_flush_state,
+                        SpaprNVDIMMDeviceFlushState, node),
+        VMSTATE_END_OF_LIST()
+    },
+};
+
+/*
+ * Assign a token and reserve it for the new flush state.
+ */
+static SpaprNVDIMMDeviceFlushState *spapr_nvdimm_init_new_flush_state(
+                                                SpaprNVDIMMDevice *spapr_nvdimm)
+{
+    SpaprNVDIMMDeviceFlushState *state;
+
+    state = g_malloc0(sizeof(*state));
+
+    spapr_nvdimm->nvdimm_flush_token++;
+    /* Token zero is presumed as no job pending. Assert on overflow to zero */
+    g_assert(spapr_nvdimm->nvdimm_flush_token != 0);
+
+    state->continue_token = spapr_nvdimm->nvdimm_flush_token;
+
+    QLIST_INSERT_HEAD(&spapr_nvdimm->pending_nvdimm_flush_states, state, node);
+
+    return state;
+}
+
+/*
+ * spapr_nvdimm_finish_flushes
+ *      Waits for all pending flush requests to complete
+ *      their execution and free the states
+ */
+void spapr_nvdimm_finish_flushes(void)
+{
+    SpaprNVDIMMDeviceFlushState *state, *next;
+    GSList *list, *nvdimms;
+
+    /*
+     * Called on reset path, the main loop thread which calls
+     * the pending BHs has gotten out running in the reset path,
+     * finally reaching here. Other code path being guest
+     * h_client_architecture_support, thats early boot up.
+     */
+    nvdimms = nvdimm_get_device_list();
+    for (list = nvdimms; list; list = list->next) {
+        NVDIMMDevice *nvdimm = list->data;
+        if (object_dynamic_cast(OBJECT(nvdimm), TYPE_SPAPR_NVDIMM)) {
+            SpaprNVDIMMDevice *s_nvdimm = SPAPR_NVDIMM(nvdimm);
+            while (!QLIST_EMPTY(&s_nvdimm->pending_nvdimm_flush_states)) {
+                aio_poll(qemu_get_aio_context(), true);
+            }
+
+            QLIST_FOREACH_SAFE(state, &s_nvdimm->completed_nvdimm_flush_states,
+                               node, next) {
+                QLIST_REMOVE(state, node);
+                g_free(state);
+            }
+        }
+    }
+    g_slist_free(nvdimms);
+}
+
+/*
+ * spapr_nvdimm_get_flush_status
+ *      Fetches the status of the hcall worker and returns
+ *      H_LONG_BUSY_ORDER_10_MSEC if the worker is still running.
+ */
+static int spapr_nvdimm_get_flush_status(SpaprNVDIMMDevice *s_nvdimm,
+                                         uint64_t token)
+{
+    SpaprNVDIMMDeviceFlushState *state, *node;
+
+    QLIST_FOREACH(state, &s_nvdimm->pending_nvdimm_flush_states, node) {
+        if (state->continue_token == token) {
+            return H_LONG_BUSY_ORDER_10_MSEC;
+        }
+    }
+
+    QLIST_FOREACH_SAFE(state, &s_nvdimm->completed_nvdimm_flush_states,
+                       node, node) {
+        if (state->continue_token == token) {
+            int ret = state->hcall_ret;
+            QLIST_REMOVE(state, node);
+            g_free(state);
+            return ret;
+        }
+    }
+
+    /* If not found in complete list too, invalid token */
+    return H_P2;
+}
+
+/*
+ * H_SCM_FLUSH
+ * Input: drc_index, continue-token
+ * Out: continue-token
+ * Return Value: H_SUCCESS, H_Parameter, H_P2, H_LONG_BUSY_ORDER_10_MSEC,
+ *               H_UNSUPPORTED
+ *
+ * Given a DRC Index Flush the data to backend NVDIMM device. The hcall returns
+ * H_LONG_BUSY_ORDER_10_MSEC when the flush takes longer time and the hcall
+ * needs to be issued multiple times in order to be completely serviced. The
+ * continue-token from the output to be passed in the argument list of
+ * subsequent hcalls until the hcall is completely serviced at which point
+ * H_SUCCESS or other error is returned.
+ */
+static target_ulong h_scm_flush(PowerPCCPU *cpu, SpaprMachineState *spapr,
+                                target_ulong opcode, target_ulong *args)
+{
+    int ret;
+    uint32_t drc_index = args[0];
+    uint64_t continue_token = args[1];
+    SpaprDrc *drc = spapr_drc_by_index(drc_index);
+    PCDIMMDevice *dimm;
+    HostMemoryBackend *backend = NULL;
+    SpaprNVDIMMDeviceFlushState *state;
+    ThreadPool *pool = aio_get_thread_pool(qemu_get_aio_context());
+    int fd;
+
+    if (!drc || !drc->dev ||
+        spapr_drc_type(drc) != SPAPR_DR_CONNECTOR_TYPE_PMEM) {
+        return H_PARAMETER;
+    }
+
+    dimm = PC_DIMM(drc->dev);
+    if (!object_dynamic_cast(OBJECT(dimm), TYPE_SPAPR_NVDIMM)) {
+        return H_PARAMETER;
+    }
+    if (continue_token == 0) {
+        bool is_pmem = false, pmem_override = false;
+        backend = MEMORY_BACKEND(dimm->hostmem);
+        fd = memory_region_get_fd(&backend->mr);
+
+        if (fd < 0) {
+            return H_UNSUPPORTED;
+        }
+
+        is_pmem = object_property_get_bool(OBJECT(backend), "pmem", NULL);
+        pmem_override = object_property_get_bool(OBJECT(dimm),
+                                                "pmem-override", NULL);
+        if (is_pmem && !pmem_override) {
+            return H_UNSUPPORTED;
+        }
+
+        state = spapr_nvdimm_init_new_flush_state(SPAPR_NVDIMM(dimm));
+        if (!state) {
+            return H_HARDWARE;
+        }
+
+        state->drcidx = drc_index;
+
+        thread_pool_submit_aio(pool, flush_worker_cb, state,
+                               spapr_nvdimm_flush_completion_cb, state);
+
+        continue_token = state->continue_token;
+    }
+
+    ret = spapr_nvdimm_get_flush_status(SPAPR_NVDIMM(dimm), continue_token);
+    if (H_IS_LONG_BUSY(ret)) {
+        args[0] = continue_token;
+    }
+
+    return ret;
+}
+
 static target_ulong h_scm_unbind_mem(PowerPCCPU *cpu, SpaprMachineState *spapr,
                                      target_ulong opcode, target_ulong *args)
 {
@@ -523,6 +851,70 @@ static void spapr_scm_register_types(void)
     spapr_register_hypercall(H_SCM_UNBIND_MEM, h_scm_unbind_mem);
     spapr_register_hypercall(H_SCM_UNBIND_ALL, h_scm_unbind_all);
     spapr_register_hypercall(H_SCM_HEALTH, h_scm_health);
+    spapr_register_hypercall(H_SCM_FLUSH, h_scm_flush);
 }
 
 type_init(spapr_scm_register_types)
+
+static void spapr_nvdimm_realize(NVDIMMDevice *dimm, Error **errp)
+{
+    SpaprNVDIMMDevice *s_nvdimm = SPAPR_NVDIMM(dimm);
+    HostMemoryBackend *backend = MEMORY_BACKEND(PC_DIMM(dimm)->hostmem);
+    bool is_pmem = object_property_get_bool(OBJECT(backend),  "pmem", NULL);
+    bool pmem_override = object_property_get_bool(OBJECT(dimm), "pmem-override",
+                                             NULL);
+    if (!is_pmem || pmem_override) {
+        s_nvdimm->hcall_flush_required = true;
+    }
+
+    vmstate_register(NULL, VMSTATE_INSTANCE_ID_ANY,
+                     &vmstate_spapr_nvdimm_states, dimm);
+}
+
+static void spapr_nvdimm_unrealize(NVDIMMDevice *dimm)
+{
+    vmstate_unregister(NULL, &vmstate_spapr_nvdimm_states, dimm);
+}
+
+static Property spapr_nvdimm_properties[] = {
+#ifdef CONFIG_LIBPMEM
+    DEFINE_PROP_BOOL("pmem-override", SpaprNVDIMMDevice, pmem_override, false),
+#endif
+    DEFINE_PROP_END_OF_LIST(),
+};
+
+static void spapr_nvdimm_class_init(ObjectClass *oc, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(oc);
+    NVDIMMClass *nvc = NVDIMM_CLASS(oc);
+
+    nvc->realize = spapr_nvdimm_realize;
+    nvc->unrealize = spapr_nvdimm_unrealize;
+
+    device_class_set_props(dc, spapr_nvdimm_properties);
+}
+
+static void spapr_nvdimm_init(Object *obj)
+{
+    SpaprNVDIMMDevice *s_nvdimm = SPAPR_NVDIMM(obj);
+
+    s_nvdimm->hcall_flush_required = false;
+    QLIST_INIT(&s_nvdimm->pending_nvdimm_flush_states);
+    QLIST_INIT(&s_nvdimm->completed_nvdimm_flush_states);
+}
+
+static TypeInfo spapr_nvdimm_info = {
+    .name          = TYPE_SPAPR_NVDIMM,
+    .parent        = TYPE_NVDIMM,
+    .class_init    = spapr_nvdimm_class_init,
+    .class_size    = sizeof(SPAPRNVDIMMClass),
+    .instance_size = sizeof(SpaprNVDIMMDevice),
+    .instance_init = spapr_nvdimm_init,
+};
+
+static void spapr_nvdimm_register_types(void)
+{
+    type_register_static(&spapr_nvdimm_info);
+}
+
+type_init(spapr_nvdimm_register_types)

hw/remote/proxy-memory-listener.c

@@ -16,6 +16,7 @@
 #include "exec/cpu-common.h"
 #include "exec/ram_addr.h"
 #include "qapi/error.h"
+#include "qemu/error-report.h"
 #include "hw/remote/mpqemu-link.h"
 #include "hw/remote/proxy-memory-listener.h"
 

hw/rtc/Kconfig

@@ -1,10 +1,12 @@
 config DS1338
     bool
     depends on I2C
+    default y if I2C_DEVICES
 
 config M41T80
     bool
     depends on I2C
+    default y if I2C_DEVICES
 
 config M48T59
     bool

hw/s390x/s390-pci-bus.c

@@ -1392,7 +1392,7 @@ static const TypeInfo s390_pci_device_info = {
     .class_init = s390_pci_device_class_init,
 };
 
-static TypeInfo s390_pci_iommu_info = {
+static const TypeInfo s390_pci_iommu_info = {
     .name = TYPE_S390_PCI_IOMMU,
     .parent = TYPE_OBJECT,
     .instance_size = sizeof(S390PCIIOMMU),

hw/s390x/sclp.c

@@ -460,7 +460,7 @@ static void sclp_class_init(ObjectClass *oc, void *data)
     sc->service_interrupt = service_interrupt;
 }
 
-static TypeInfo sclp_info = {
+static const TypeInfo sclp_info = {
     .name = TYPE_SCLP,
     .parent = TYPE_DEVICE,
     .instance_init = sclp_init,

hw/s390x/tod-kvm.c

@@ -147,7 +147,7 @@ static void kvm_s390_tod_init(Object *obj)
     td->stopped = false;
 }
 
-static TypeInfo kvm_s390_tod_info = {
+static const TypeInfo kvm_s390_tod_info = {
     .name = TYPE_KVM_S390_TOD,
     .parent = TYPE_S390_TOD,
     .instance_size = sizeof(S390TODState),

hw/s390x/tod-tcg.c

@@ -73,7 +73,7 @@ static void qemu_s390_tod_init(Object *obj)
     }
 }
 
-static TypeInfo qemu_s390_tod_info = {
+static const TypeInfo qemu_s390_tod_info = {
     .name = TYPE_QEMU_S390_TOD,
     .parent = TYPE_S390_TOD,
     .instance_size = sizeof(S390TODState),

hw/s390x/tod.c

@@ -123,7 +123,7 @@ static void s390_tod_class_init(ObjectClass *oc, void *data)
     dc->user_creatable = false;
 }
 
-static TypeInfo s390_tod_info = {
+static const TypeInfo s390_tod_info = {
     .name = TYPE_S390_TOD,
     .parent = TYPE_DEVICE,
     .instance_size = sizeof(S390TODState),

hw/scsi/lsi53c895a.c

@@ -2352,7 +2352,7 @@ static void lsi53c810_class_init(ObjectClass *klass, void *data)
     k->device_id = PCI_DEVICE_ID_LSI_53C810;
 }
 
-static TypeInfo lsi53c810_info = {
+static const TypeInfo lsi53c810_info = {
     .name          = TYPE_LSI53C810,
     .parent        = TYPE_LSI53C895A,
     .class_init    = lsi53c810_class_init,

hw/scsi/megasas.c

@@ -28,6 +28,7 @@
 #include "hw/pci/msix.h"
 #include "qemu/iov.h"
 #include "qemu/module.h"
+#include "qemu/hw-version.h"
 #include "hw/scsi/scsi.h"
 #include "scsi/constants.h"
 #include "trace.h"

hw/scsi/scsi-bus.c

@@ -3,6 +3,7 @@
 #include "qemu/error-report.h"
 #include "qemu/module.h"
 #include "qemu/option.h"
+#include "qemu/hw-version.h"
 #include "hw/qdev-properties.h"
 #include "hw/scsi/scsi.h"
 #include "migration/qemu-file-types.h"

hw/scsi/scsi-disk.c

@@ -25,6 +25,7 @@
 #include "qemu/error-report.h"
 #include "qemu/main-loop.h"
 #include "qemu/module.h"
+#include "qemu/hw-version.h"
 #include "hw/scsi/scsi.h"
 #include "migration/qemu-file-types.h"
 #include "migration/vmstate.h"

hw/sd/allwinner-sdhost.c

@@ -835,7 +835,7 @@ static void allwinner_sdhost_sun5i_class_init(ObjectClass *klass, void *data)
     sc->max_desc_size = 64 * KiB;
 }
 
-static TypeInfo allwinner_sdhost_info = {
+static const TypeInfo allwinner_sdhost_info = {
     .name          = TYPE_AW_SDHOST,
     .parent        = TYPE_SYS_BUS_DEVICE,
     .instance_init = allwinner_sdhost_init,

hw/sd/aspeed_sdhci.c

@@ -198,7 +198,7 @@ static void aspeed_sdhci_class_init(ObjectClass *classp, void *data)
     device_class_set_props(dc, aspeed_sdhci_properties);
 }
 
-static TypeInfo aspeed_sdhci_info = {
+static const TypeInfo aspeed_sdhci_info = {
     .name          = TYPE_ASPEED_SDHCI,
     .parent        = TYPE_SYS_BUS_DEVICE,
     .instance_size = sizeof(AspeedSDHCIState),

hw/sd/bcm2835_sdhost.c

@@ -436,7 +436,7 @@ static void bcm2835_sdhost_class_init(ObjectClass *klass, void *data)
     dc->vmsd = &vmstate_bcm2835_sdhost;
 }
 
-static TypeInfo bcm2835_sdhost_info = {
+static const TypeInfo bcm2835_sdhost_info = {
     .name          = TYPE_BCM2835_SDHOST,
     .parent        = TYPE_SYS_BUS_DEVICE,
     .instance_size = sizeof(BCM2835SDHostState),

hw/sd/cadence_sdhci.c

@@ -175,7 +175,7 @@ static void cadence_sdhci_class_init(ObjectClass *classp, void *data)
     dc->vmsd = &vmstate_cadence_sdhci;
 }
 
-static TypeInfo cadence_sdhci_info = {
+static const TypeInfo cadence_sdhci_info = {
     .name          = TYPE_CADENCE_SDHCI,
     .parent        = TYPE_SYS_BUS_DEVICE,
     .instance_size = sizeof(CadenceSDHCIState),

hw/sd/npcm7xx_sdhci.c

@@ -166,7 +166,7 @@ static void npcm7xx_sdhci_instance_init(Object *obj)
                             TYPE_SYSBUS_SDHCI);
 }
 
-static TypeInfo npcm7xx_sdhci_info = {
+static const TypeInfo npcm7xx_sdhci_info = {
     .name = TYPE_NPCM7XX_SDHCI,
     .parent = TYPE_SYS_BUS_DEVICE,
     .instance_size = sizeof(NPCM7xxSDHCIState),

hw/sensor/Kconfig

@@ -1,18 +1,22 @@
 config TMP105
     bool
     depends on I2C
+    default y if I2C_DEVICES
 
 config TMP421
     bool
     depends on I2C
+    default y if I2C_DEVICES
 
 config DPS310
     bool
     depends on I2C
+    default y if I2C_DEVICES
 
 config EMC141X
     bool
     depends on I2C
+    default y if I2C_DEVICES
 
 config ADM1272
     bool
@@ -25,3 +29,4 @@ config MAX34451
 config LSM303DLHC_MAG
     bool
     depends on I2C
+    default y if I2C_DEVICES

hw/timer/a9gtimer.c

@@ -318,6 +318,12 @@ static void a9_gtimer_realize(DeviceState *dev, Error **errp)
     }
 }
 
+static bool vmstate_a9_gtimer_control_needed(void *opaque)
+{
+    A9GTimerState *s = opaque;
+    return s->control != 0;
+}
+
 static const VMStateDescription vmstate_a9_gtimer_per_cpu = {
     .name = "arm.cortex-a9-global-timer.percpu",
     .version_id = 1,
@@ -331,6 +337,17 @@ static const VMStateDescription vmstate_a9_gtimer_per_cpu = {
     }
 };
 
+static const VMStateDescription vmstate_a9_gtimer_control = {
+    .name = "arm.cortex-a9-global-timer.control",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .needed = vmstate_a9_gtimer_control_needed,
+    .fields = (VMStateField[]) {
+        VMSTATE_UINT32(control, A9GTimerState),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
 static const VMStateDescription vmstate_a9_gtimer = {
     .name = "arm.cortex-a9-global-timer",
     .version_id = 1,
@@ -344,6 +361,10 @@ static const VMStateDescription vmstate_a9_gtimer = {
                                      1, vmstate_a9_gtimer_per_cpu,
                                      A9GTimerPerCPU),
         VMSTATE_END_OF_LIST()
+    },
+    .subsections = (const VMStateDescription*[]) {
+        &vmstate_a9_gtimer_control,
+        NULL
     }
 };
 

hw/tpm/tpm_crb.c

@@ -18,6 +18,7 @@
 
 #include "qemu/module.h"
 #include "qapi/error.h"
+#include "exec/address-spaces.h"
 #include "hw/qdev-properties.h"
 #include "hw/pci/pci_ids.h"
 #include "hw/acpi/tpm.h"

hw/tpm/tpm_ppi.c

@@ -14,9 +14,9 @@
 #include "qemu/osdep.h"
 
 #include "qapi/error.h"
-#include "cpu.h"
 #include "sysemu/memory_mapping.h"
 #include "migration/vmstate.h"
+#include "hw/qdev-core.h"
 #include "hw/acpi/tpm.h"
 #include "tpm_ppi.h"
 #include "trace.h"
@@ -44,7 +44,7 @@ void tpm_ppi_reset(TPMPPI *tpmppi)
     }
 }
 
-void tpm_ppi_init(TPMPPI *tpmppi, struct MemoryRegion *m,
+void tpm_ppi_init(TPMPPI *tpmppi, MemoryRegion *m,
                   hwaddr addr, Object *obj)
 {
     tpmppi->buf = qemu_memalign(qemu_real_host_page_size,

hw/tpm/tpm_ppi.h

@@ -12,7 +12,7 @@
 #ifndef TPM_TPM_PPI_H
 #define TPM_TPM_PPI_H
 
-#include "exec/address-spaces.h"
+#include "exec/memory.h"
 
 typedef struct TPMPPI {
     MemoryRegion ram;
@@ -29,7 +29,7 @@ typedef struct TPMPPI {
  * Register the TPM PPI memory region at @addr on the given address
  * space for the object @obj.
  **/
-void tpm_ppi_init(TPMPPI *tpmppi, struct MemoryRegion *m,
+void tpm_ppi_init(TPMPPI *tpmppi, MemoryRegion *m,
                   hwaddr addr, Object *obj);
 
 /**

hw/usb/dev-hid.c

@@ -461,14 +461,14 @@ static const uint8_t qemu_mouse_hid_report_descriptor[] = {
     0xa1, 0x00,		/*   Collection (Physical) */
     0x05, 0x09,		/*     Usage Page (Button) */
     0x19, 0x01,		/*     Usage Minimum (1) */
-    0x29, 0x03,		/*     Usage Maximum (3) */
+    0x29, 0x05,		/*     Usage Maximum (5) */
     0x15, 0x00,		/*     Logical Minimum (0) */
     0x25, 0x01,		/*     Logical Maximum (1) */
-    0x95, 0x03,		/*     Report Count (3) */
+    0x95, 0x05,		/*     Report Count (5) */
     0x75, 0x01,		/*     Report Size (1) */
     0x81, 0x02,		/*     Input (Data, Variable, Absolute) */
     0x95, 0x01,		/*     Report Count (1) */
-    0x75, 0x05,		/*     Report Size (5) */
+    0x75, 0x03,		/*     Report Size (3) */
     0x81, 0x01,		/*     Input (Constant) */
     0x05, 0x01,		/*     Usage Page (Generic Desktop) */
     0x09, 0x30,		/*     Usage (X) */

hw/usb/dev-mtp.c

@@ -2106,7 +2106,7 @@ static void usb_mtp_class_initfn(ObjectClass *klass, void *data)
     device_class_set_props(dc, mtp_properties);
 }
 
-static TypeInfo mtp_info = {
+static const TypeInfo mtp_info = {
     .name          = TYPE_USB_MTP,
     .parent        = TYPE_USB_DEVICE,
     .instance_size = sizeof(MTPState),

hw/usb/host-libusb.c

@@ -1801,7 +1801,7 @@ static void usb_host_class_initfn(ObjectClass *klass, void *data)
     set_bit(DEVICE_CATEGORY_BRIDGE, dc->categories);
 }
 
-static TypeInfo usb_host_dev_info = {
+static const TypeInfo usb_host_dev_info = {
     .name          = TYPE_USB_HOST_DEVICE,
     .parent        = TYPE_USB_DEVICE,
     .instance_size = sizeof(USBHostDevice),

hw/vfio/igd.c

@@ -199,7 +199,7 @@ static void vfio_pci_igd_lpc_bridge_class_init(ObjectClass *klass, void *data)
     k->class_id = PCI_CLASS_BRIDGE_ISA;
 }
 
-static TypeInfo vfio_pci_igd_lpc_bridge_info = {
+static const TypeInfo vfio_pci_igd_lpc_bridge_info = {
     .name = "vfio-pci-igd-lpc-bridge",
     .parent = TYPE_PCI_DEVICE,
     .class_init = vfio_pci_igd_lpc_bridge_class_init,

hw/virtio/virtio-balloon.c

@@ -17,6 +17,7 @@
 #include "qemu/iov.h"
 #include "qemu/module.h"
 #include "qemu/timer.h"
+#include "qemu/madvise.h"
 #include "hw/virtio/virtio.h"
 #include "hw/mem/pc-dimm.h"
 #include "hw/qdev-properties.h"

hw/virtio/virtio-pmem.c

@@ -182,7 +182,7 @@ static void virtio_pmem_class_init(ObjectClass *klass, void *data)
     set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
 }
 
-static TypeInfo virtio_pmem_info = {
+static const TypeInfo virtio_pmem_info = {
     .name          = TYPE_VIRTIO_PMEM,
     .parent        = TYPE_VIRTIO_DEVICE,
     .class_size    = sizeof(VirtIOPMEMClass),

include/exec/exec-all.h

@@ -40,8 +40,6 @@ typedef ram_addr_t tb_page_addr_t;
 #define TB_PAGE_ADDR_FMT RAM_ADDR_FMT
 #endif
 
-#include "qemu/log.h"
-
 void gen_intermediate_code(CPUState *cpu, TranslationBlock *tb, int max_insns);
 void restore_state_to_opc(CPUArchState *env, TranslationBlock *tb,
                           target_ulong *data);

include/exec/ramblock.h

@@ -21,6 +21,8 @@
 
 #ifndef CONFIG_USER_ONLY
 #include "cpu-common.h"
+#include "qemu/rcu.h"
+#include "exec/ramlist.h"
 
 struct RAMBlock {
     struct rcu_head rcu;

include/hw/m68k/mcf.h

@@ -2,6 +2,7 @@
 #define HW_MCF_H
 /* Motorola ColdFire device prototypes.  */
 
+#include "exec/hwaddr.h"
 #include "target/m68k/cpu-qom.h"
 
 /* mcf_uart.c */

include/hw/mem/nvdimm.h

@@ -103,6 +103,8 @@ struct NVDIMMClass {
     /* write @size bytes from @buf to NVDIMM label data at @offset. */
     void (*write_label_data)(NVDIMMDevice *nvdimm, const void *buf,
                              uint64_t size, uint64_t offset);
+    void (*realize)(NVDIMMDevice *nvdimm, Error **errp);
+    void (*unrealize)(NVDIMMDevice *nvdimm);
 };
 
 #define NVDIMM_DSM_MEM_FILE     "etc/acpi/nvdimm-mem"

include/hw/mem/pc-dimm.h

@@ -63,6 +63,7 @@ struct PCDIMMDeviceClass {
 
     /* public */
     void (*realize)(PCDIMMDevice *dimm, Error **errp);
+    void (*unrealize)(PCDIMMDevice *dimm);
 };
 
 void pc_dimm_pre_plug(PCDIMMDevice *dimm, MachineState *machine,

include/hw/ppc/ppc.h

@@ -54,6 +54,9 @@ struct ppc_tb_t {
 
 uint64_t cpu_ppc_get_tb(ppc_tb_t *tb_env, uint64_t vmclk, int64_t tb_offset);
 clk_setup_cb cpu_ppc_tb_init (CPUPPCState *env, uint32_t freq);
+void cpu_ppc_hdecr_init(CPUPPCState *env);
+void cpu_ppc_hdecr_exit(CPUPPCState *env);
+
 /* Embedded PowerPC DCR management */
 typedef uint32_t (*dcr_read_cb)(void *opaque, int dcrn);
 typedef void (*dcr_write_cb)(void *opaque, int dcrn, uint32_t val);

include/hw/ppc/spapr.h

@@ -197,6 +197,9 @@ struct SpaprMachineState {
     bool has_graphics;
     uint32_t vsmt;       /* Virtual SMT mode (KVM's "core stride") */
 
+    /* Nested HV support (TCG only) */
+    uint64_t nested_ptcr;
+
     Notifier epow_notifier;
     QTAILQ_HEAD(, SpaprEventLogEntry) pending_events;
     bool use_hotplug_event_source;
@@ -341,6 +344,7 @@ struct SpaprMachineState {
 #define H_P7              -60
 #define H_P8              -61
 #define H_P9              -62
+#define H_UNSUPPORTED     -67
 #define H_OVERLAP         -68
 #define H_UNSUPPORTED_FLAG -256
 #define H_MULTI_THREADS_ACTIVE -9005
@@ -559,8 +563,9 @@ struct SpaprMachineState {
 #define H_SCM_UNBIND_ALL        0x3FC
 #define H_SCM_HEALTH            0x400
 #define H_RPT_INVALIDATE        0x448
+#define H_SCM_FLUSH             0x44C
 
-#define MAX_HCALL_OPCODE        H_RPT_INVALIDATE
+#define MAX_HCALL_OPCODE        H_SCM_FLUSH
 
 /* The hcalls above are standardized in PAPR and implemented by pHyp
  * as well.
@@ -577,7 +582,14 @@ struct SpaprMachineState {
 #define KVMPPC_H_UPDATE_DT      (KVMPPC_HCALL_BASE + 0x3)
 /* 0x4 was used for KVMPPC_H_UPDATE_PHANDLE in SLOF */
 #define KVMPPC_H_VOF_CLIENT     (KVMPPC_HCALL_BASE + 0x5)
-#define KVMPPC_HCALL_MAX        KVMPPC_H_VOF_CLIENT
+
+/* Platform-specific hcalls used for nested HV KVM */
+#define KVMPPC_H_SET_PARTITION_TABLE   (KVMPPC_HCALL_BASE + 0x800)
+#define KVMPPC_H_ENTER_NESTED          (KVMPPC_HCALL_BASE + 0x804)
+#define KVMPPC_H_TLB_INVALIDATE        (KVMPPC_HCALL_BASE + 0x808)
+#define KVMPPC_H_COPY_TOFROM_GUEST     (KVMPPC_HCALL_BASE + 0x80C)
+
+#define KVMPPC_HCALL_MAX        KVMPPC_H_COPY_TOFROM_GUEST
 
 /*
  * The hcall range 0xEF00 to 0xEF80 is reserved for use in facilitating
@@ -587,6 +599,65 @@ struct SpaprMachineState {
 #define SVM_H_TPM_COMM              0xEF10
 #define SVM_HCALL_MAX               SVM_H_TPM_COMM
 
+/*
+ * Register state for entering a nested guest with H_ENTER_NESTED.
+ * New member must be added at the end.
+ */
+struct kvmppc_hv_guest_state {
+    uint64_t version;      /* version of this structure layout, must be first */
+    uint32_t lpid;
+    uint32_t vcpu_token;
+    /* These registers are hypervisor privileged (at least for writing) */
+    uint64_t lpcr;
+    uint64_t pcr;
+    uint64_t amor;
+    uint64_t dpdes;
+    uint64_t hfscr;
+    int64_t tb_offset;
+    uint64_t dawr0;
+    uint64_t dawrx0;
+    uint64_t ciabr;
+    uint64_t hdec_expiry;
+    uint64_t purr;
+    uint64_t spurr;
+    uint64_t ic;
+    uint64_t vtb;
+    uint64_t hdar;
+    uint64_t hdsisr;
+    uint64_t heir;
+    uint64_t asdr;
+    /* These are OS privileged but need to be set late in guest entry */
+    uint64_t srr0;
+    uint64_t srr1;
+    uint64_t sprg[4];
+    uint64_t pidr;
+    uint64_t cfar;
+    uint64_t ppr;
+    /* Version 1 ends here */
+    uint64_t dawr1;
+    uint64_t dawrx1;
+    /* Version 2 ends here */
+};
+
+/* Latest version of hv_guest_state structure */
+#define HV_GUEST_STATE_VERSION  2
+
+/* Linux 64-bit powerpc pt_regs struct, used by nested HV */
+struct kvmppc_pt_regs {
+    uint64_t gpr[32];
+    uint64_t nip;
+    uint64_t msr;
+    uint64_t orig_gpr3;    /* Used for restarting system calls */
+    uint64_t ctr;
+    uint64_t link;
+    uint64_t xer;
+    uint64_t ccr;
+    uint64_t softe;        /* Soft enabled/disabled */
+    uint64_t trap;         /* Reason for being here */
+    uint64_t dar;          /* Fault registers */
+    uint64_t dsisr;        /* on 4xx/Book-E used for ESR */
+    uint64_t result;       /* Result of a system call */
+};
 
 typedef struct SpaprDeviceTreeUpdateHeader {
     uint32_t version_id;
@@ -604,6 +675,9 @@ typedef target_ulong (*spapr_hcall_fn)(PowerPCCPU *cpu, SpaprMachineState *sm,
 void spapr_register_hypercall(target_ulong opcode, spapr_hcall_fn fn);
 target_ulong spapr_hypercall(PowerPCCPU *cpu, target_ulong opcode,
                              target_ulong *args);
+
+void spapr_exit_nested(PowerPCCPU *cpu, int excp);
+
 target_ulong softmmu_resize_hpt_prepare(PowerPCCPU *cpu, SpaprMachineState *spapr,
                                          target_ulong shift);
 target_ulong softmmu_resize_hpt_commit(PowerPCCPU *cpu, SpaprMachineState *spapr,

include/hw/ppc/spapr_cpu_core.h

@@ -48,6 +48,11 @@ typedef struct SpaprCpuState {
     bool prod; /* not migrated, only used to improve dispatch latencies */
     struct ICPState *icp;
     struct XiveTCTX *tctx;
+
+    /* Fields for nested-HV support */
+    bool in_nested; /* true while the L2 is executing */
+    CPUPPCState *nested_host_state; /* holds the L1 state while L2 executes */
+    int64_t nested_tb_offset; /* L1->L2 TB offset */
 } SpaprCpuState;
 
 static inline SpaprCpuState *spapr_cpu_state(PowerPCCPU *cpu)