Merge tag 'edk2-20240320-pull-request' of https://gitlab.com/kraxel/qemu into staging
edk2: cleanup fix, update build config, rebuild binaries.
# -----BEGIN PGP SIGNATURE-----
#
# iQIzBAABCgAdFiEEoDKM/7k6F6eZAf59TLbY7tPocTgFAmX6i2UACgkQTLbY7tPo
# cTgZpw/9GR+9LMdZJF7OoXB2t3zRvURMg79BYI2hXVXLd2OnoNGA1obM7pu2ecpo
# 1ny2VoijagpcQFJpIDOblyiqa5/CTnCek5tt6L60TwSHNeUfnsD2qowXl2VTQ+IX
# Fk/XT+LtLhohmq3zvNi6nxTf9Mc/HqvbVTU1DHm5yXNRAG/glCWiVoQAqGiaBLrm
# pR2rjHVU5C3BmHW+c9GAQlb9L8ZoMtqNB4865K0IradXmdFcCO+0xcKFDMKpUF+a
# RuC1Mmq/MaxjU8cq/tMqUbE7lk/qZgQgw4h2g4ozT5JGFErf+sV9AYkb6UIoeZ69
# t+KRuYc9I4Bbgb2YL85jezGAmNxGSDLfRnaMdOGlA579cjHjhWLX50FHP5dDM5xB
# hL3qQ8H5NPIYdHuWCg4RfZLeIGKTWA8dsi0QIQ81KN1yLMogEVb3v2QI0dWCEnv+
# 6OJK8A8T7eQs74hcGqm8psX9n8KcwppsfSDdSAv11sdHSGGoyhoXALXEYqZ12kvW
# TXE1YwL1UBbr9d/1uhoVolQ8gwIW+DOsawG55xBF8FeII5HcUX/925NR7jYNWjJC
# SwzVWMXhAzEijoSDGoMjDpdKUSxA/bfaOuAuBy00mmNEp/YrlPcU1KxDMPywFyDe
# D7TRtJmoGVA3/gCRdfhE7Hmi5xrb8u3MLgtJpNWZTbcTO+ODv48=
# =pJEG
# -----END PGP SIGNATURE-----
# gpg: Signature made Wed 20 Mar 2024 07:08:21 GMT
# gpg: using RSA key A0328CFFB93A17A79901FE7D4CB6D8EED3E87138
# gpg: Good signature from "Gerd Hoffmann (work) <kraxel@redhat.com>" [full]
# gpg: aka "Gerd Hoffmann <gerd@kraxel.org>" [full]
# gpg: aka "Gerd Hoffmann (private) <kraxel@gmail.com>" [full]
# Primary key fingerprint: A032 8CFF B93A 17A7 9901 FE7D 4CB6 D8EE D3E8 7138
* tag 'edk2-20240320-pull-request' of https://gitlab.com/kraxel/qemu:
update edk2 binaries for arm, risc-v and x86 secure boot.
roms/efi: use pure 64-bit build for edk2-x86_64-secure-code.fd
roms/efi: exclude efi shell from secure boot builds
roms/efi: drop workaround for edk2-stable202308
roms/efi: clean up edk2 build config
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
diff --git a/.travis.yml b/.travis.yml
index 76859d4..597d151 100644
--- a/.travis.yml
+++ b/.travis.yml
@@ -35,7 +35,7 @@
- TEST_BUILD_CMD=""
- TEST_CMD="make check V=1"
# This is broadly a list of "mainline" system targets which have support across the major distros
- - MAIN_SOFTMMU_TARGETS="aarch64-softmmu,mips64-softmmu,ppc64-softmmu,riscv64-softmmu,s390x-softmmu,x86_64-softmmu"
+ - MAIN_SYSTEM_TARGETS="aarch64-softmmu,mips64-softmmu,ppc64-softmmu,riscv64-softmmu,s390x-softmmu,x86_64-softmmu"
- CCACHE_SLOPPINESS="include_file_ctime,include_file_mtime"
- CCACHE_MAXSIZE=1G
- G_MESSAGES_DEBUG=error
@@ -114,7 +114,7 @@
env:
- TEST_CMD="make check check-tcg V=1"
- CONFIG="--disable-containers --enable-fdt=system
- --target-list=${MAIN_SOFTMMU_TARGETS} --cxx=/bin/false"
+ --target-list=${MAIN_SYSTEM_TARGETS} --cxx=/bin/false"
- UNRELIABLE=true
- name: "[ppc64] GCC check-tcg"
@@ -185,7 +185,7 @@
env:
- TEST_CMD="make check check-tcg V=1"
- CONFIG="--disable-containers --enable-fdt=system
- --target-list=${MAIN_SOFTMMU_TARGETS},s390x-linux-user"
+ --target-list=${MAIN_SYSTEM_TARGETS},s390x-linux-user"
- UNRELIABLE=true
script:
- BUILD_RC=0 && make -j${JOBS} || BUILD_RC=$?
@@ -226,7 +226,7 @@
- genisoimage
env:
- CONFIG="--disable-containers --enable-fdt=system --audio-drv-list=sdl
- --disable-user --target-list-exclude=${MAIN_SOFTMMU_TARGETS}"
+ --disable-user --target-list-exclude=${MAIN_SYSTEM_TARGETS}"
- name: "[s390x] GCC (user)"
arch: s390x
diff --git a/VERSION b/VERSION
index 11ff3cd..07e31fc 100644
--- a/VERSION
+++ b/VERSION
@@ -1 +1 @@
-8.2.50
+8.2.90
diff --git a/block/mirror.c b/block/mirror.c
index 5145eb5..1bdce3b 100644
--- a/block/mirror.c
+++ b/block/mirror.c
@@ -479,9 +479,9 @@
return bytes_handled;
}
-static void coroutine_fn GRAPH_RDLOCK mirror_iteration(MirrorBlockJob *s)
+static void coroutine_fn GRAPH_UNLOCKED mirror_iteration(MirrorBlockJob *s)
{
- BlockDriverState *source = s->mirror_top_bs->backing->bs;
+ BlockDriverState *source;
MirrorOp *pseudo_op;
int64_t offset;
/* At least the first dirty chunk is mirrored in one iteration. */
@@ -489,6 +489,10 @@
bool write_zeroes_ok = bdrv_can_write_zeroes_with_unmap(blk_bs(s->target));
int max_io_bytes = MAX(s->buf_size / MAX_IN_FLIGHT, MAX_IO_BYTES);
+ bdrv_graph_co_rdlock();
+ source = s->mirror_top_bs->backing->bs;
+ bdrv_graph_co_rdunlock();
+
bdrv_dirty_bitmap_lock(s->dirty_bitmap);
offset = bdrv_dirty_iter_next(s->dbi);
if (offset < 0) {
@@ -1066,9 +1070,7 @@
mirror_wait_for_free_in_flight_slot(s);
continue;
} else if (cnt != 0) {
- bdrv_graph_co_rdlock();
mirror_iteration(s);
- bdrv_graph_co_rdunlock();
}
}
diff --git a/block/qapi.c b/block/qapi.c
index 31183d4..2b5793f 100644
--- a/block/qapi.c
+++ b/block/qapi.c
@@ -742,15 +742,15 @@
char *sizing = NULL;
if (!sn) {
- qemu_printf("%-10s%-17s%8s%20s%13s%11s",
- "ID", "TAG", "VM SIZE", "DATE", "VM CLOCK", "ICOUNT");
+ qemu_printf("%-7s %-16s %8s %19s %15s %10s",
+ "ID", "TAG", "VM_SIZE", "DATE", "VM_CLOCK", "ICOUNT");
} else {
g_autoptr(GDateTime) date = g_date_time_new_from_unix_local(sn->date_sec);
g_autofree char *date_buf = g_date_time_format(date, "%Y-%m-%d %H:%M:%S");
secs = sn->vm_clock_nsec / 1000000000;
snprintf(clock_buf, sizeof(clock_buf),
- "%02d:%02d:%02d.%03d",
+ "%04d:%02d:%02d.%03d",
(int)(secs / 3600),
(int)((secs / 60) % 60),
(int)(secs % 60),
@@ -759,8 +759,10 @@
if (sn->icount != -1ULL) {
snprintf(icount_buf, sizeof(icount_buf),
"%"PRId64, sn->icount);
+ } else {
+ snprintf(icount_buf, sizeof(icount_buf), "--");
}
- qemu_printf("%-9s %-16s %8s%20s%13s%11s",
+ qemu_printf("%-7s %-16s %8s %19s %15s %10s",
sn->id_str, sn->name,
sizing,
date_buf,
diff --git a/blockdev.c b/blockdev.c
index d8fb339..057601d 100644
--- a/blockdev.c
+++ b/blockdev.c
@@ -1395,7 +1395,8 @@
bdrv_drained_begin(state->old_bs);
if (!bdrv_is_inserted(state->old_bs)) {
- error_setg(errp, QERR_DEVICE_HAS_NO_MEDIUM, device);
+ error_setg(errp, QERR_DEVICE_HAS_NO_MEDIUM,
+ bdrv_get_device_or_node_name(state->old_bs));
return;
}
diff --git a/chardev/char-io.c b/chardev/char-io.c
index 4451128..dab77b1 100644
--- a/chardev/char-io.c
+++ b/chardev/char-io.c
@@ -33,6 +33,7 @@
IOCanReadHandler *fd_can_read;
GSourceFunc fd_read;
void *opaque;
+ GMainContext *context;
} IOWatchPoll;
static IOWatchPoll *io_watch_poll_from_source(GSource *source)
@@ -50,28 +51,59 @@
return FALSE;
}
+ /*
+ * We do not register the QIOChannel watch as a child GSource.
+ * The 'prepare' function on the parent GSource will be
+ * skipped if a child GSource's 'prepare' function indicates
+ * readiness. We need this prepare function be guaranteed
+ * to run on *every* iteration of the main loop, because
+ * it is critical to ensure we remove the QIOChannel watch
+ * if 'fd_can_read' indicates the frontend cannot receive
+ * more data.
+ */
if (now_active) {
iwp->src = qio_channel_create_watch(
iwp->ioc, G_IO_IN | G_IO_ERR | G_IO_HUP | G_IO_NVAL);
g_source_set_callback(iwp->src, iwp->fd_read, iwp->opaque, NULL);
- g_source_add_child_source(source, iwp->src);
- g_source_unref(iwp->src);
+ g_source_attach(iwp->src, iwp->context);
} else {
- g_source_remove_child_source(source, iwp->src);
+ g_source_destroy(iwp->src);
+ g_source_unref(iwp->src);
iwp->src = NULL;
}
return FALSE;
}
+static gboolean io_watch_poll_check(GSource *source)
+{
+ return FALSE;
+}
+
static gboolean io_watch_poll_dispatch(GSource *source, GSourceFunc callback,
gpointer user_data)
{
- return G_SOURCE_CONTINUE;
+ abort();
+}
+
+static void io_watch_poll_finalize(GSource *source)
+{
+ /*
+ * Due to a glib bug, removing the last reference to a source
+ * inside a finalize callback causes recursive locking (and a
+ * deadlock). This is not a problem inside other callbacks,
+ * including dispatch callbacks, so we call io_remove_watch_poll
+ * to remove this source. At this point, iwp->src must
+ * be NULL, or we would leak it.
+ */
+ IOWatchPoll *iwp = io_watch_poll_from_source(source);
+ assert(iwp->src == NULL);
}
static GSourceFuncs io_watch_poll_funcs = {
.prepare = io_watch_poll_prepare,
+ .check = io_watch_poll_check,
.dispatch = io_watch_poll_dispatch,
+ .finalize = io_watch_poll_finalize,
};
GSource *io_add_watch_poll(Chardev *chr,
@@ -91,6 +123,7 @@
iwp->ioc = ioc;
iwp->fd_read = (GSourceFunc) fd_read;
iwp->src = NULL;
+ iwp->context = context;
name = g_strdup_printf("chardev-iowatch-%s", chr->label);
g_source_set_name((GSource *)iwp, name);
@@ -101,10 +134,23 @@
return (GSource *)iwp;
}
+static void io_remove_watch_poll(GSource *source)
+{
+ IOWatchPoll *iwp;
+
+ iwp = io_watch_poll_from_source(source);
+ if (iwp->src) {
+ g_source_destroy(iwp->src);
+ g_source_unref(iwp->src);
+ iwp->src = NULL;
+ }
+ g_source_destroy(&iwp->parent);
+}
+
void remove_fd_in_watch(Chardev *chr)
{
if (chr->gsource) {
- g_source_destroy(chr->gsource);
+ io_remove_watch_poll(chr->gsource);
chr->gsource = NULL;
}
}
diff --git a/chardev/char-socket.c b/chardev/char-socket.c
index 8a0406c..812d7aa 100644
--- a/chardev/char-socket.c
+++ b/chardev/char-socket.c
@@ -496,9 +496,9 @@
s->max_size <= 0) {
return TRUE;
}
- len = tcp_chr_read_poll(opaque);
- if (len > sizeof(buf)) {
- len = sizeof(buf);
+ len = sizeof(buf);
+ if (len > s->max_size) {
+ len = s->max_size;
}
size = tcp_chr_recv(chr, (void *)buf, len);
if (size == 0 || (size == -1 && errno != EAGAIN)) {
@@ -601,6 +601,22 @@
remove_hup_source(s);
s->hup_source = qio_channel_create_watch(s->ioc, G_IO_HUP);
+ /*
+ * poll() is liable to return POLLHUP even when there is
+ * still incoming data available to read on the FD. If
+ * we have the hup_source at the same priority as the
+ * main io_add_watch_poll GSource, then we might end up
+ * processing the POLLHUP event first, closing the FD,
+ * and as a result silently discard data we should have
+ * read.
+ *
+ * By setting the hup_source to G_PRIORITY_DEFAULT + 1,
+ * we ensure that io_add_watch_poll GSource will always
+ * be dispatched first, thus guaranteeing we will be
+ * able to process all incoming data before closing the
+ * FD
+ */
+ g_source_set_priority(s->hup_source, G_PRIORITY_DEFAULT + 1);
g_source_set_callback(s->hup_source, (GSourceFunc)tcp_chr_hup,
chr, NULL);
g_source_attach(s->hup_source, chr->gcontext);
diff --git a/crypto/cipher-gcrypt.c.inc b/crypto/cipher-gcrypt.c.inc
index 1377cba..4a83147 100644
--- a/crypto/cipher-gcrypt.c.inc
+++ b/crypto/cipher-gcrypt.c.inc
@@ -20,6 +20,56 @@
#include <gcrypt.h>
+static int qcrypto_cipher_alg_to_gcry_alg(QCryptoCipherAlgorithm alg)
+{
+ switch (alg) {
+ case QCRYPTO_CIPHER_ALG_DES:
+ return GCRY_CIPHER_DES;
+ case QCRYPTO_CIPHER_ALG_3DES:
+ return GCRY_CIPHER_3DES;
+ case QCRYPTO_CIPHER_ALG_AES_128:
+ return GCRY_CIPHER_AES128;
+ case QCRYPTO_CIPHER_ALG_AES_192:
+ return GCRY_CIPHER_AES192;
+ case QCRYPTO_CIPHER_ALG_AES_256:
+ return GCRY_CIPHER_AES256;
+ case QCRYPTO_CIPHER_ALG_CAST5_128:
+ return GCRY_CIPHER_CAST5;
+ case QCRYPTO_CIPHER_ALG_SERPENT_128:
+ return GCRY_CIPHER_SERPENT128;
+ case QCRYPTO_CIPHER_ALG_SERPENT_192:
+ return GCRY_CIPHER_SERPENT192;
+ case QCRYPTO_CIPHER_ALG_SERPENT_256:
+ return GCRY_CIPHER_SERPENT256;
+ case QCRYPTO_CIPHER_ALG_TWOFISH_128:
+ return GCRY_CIPHER_TWOFISH128;
+ case QCRYPTO_CIPHER_ALG_TWOFISH_256:
+ return GCRY_CIPHER_TWOFISH;
+#ifdef CONFIG_CRYPTO_SM4
+ case QCRYPTO_CIPHER_ALG_SM4:
+ return GCRY_CIPHER_SM4;
+#endif
+ default:
+ return GCRY_CIPHER_NONE;
+ }
+}
+
+static int qcrypto_cipher_mode_to_gcry_mode(QCryptoCipherMode mode)
+{
+ switch (mode) {
+ case QCRYPTO_CIPHER_MODE_ECB:
+ return GCRY_CIPHER_MODE_ECB;
+ case QCRYPTO_CIPHER_MODE_XTS:
+ return GCRY_CIPHER_MODE_XTS;
+ case QCRYPTO_CIPHER_MODE_CBC:
+ return GCRY_CIPHER_MODE_CBC;
+ case QCRYPTO_CIPHER_MODE_CTR:
+ return GCRY_CIPHER_MODE_CTR;
+ default:
+ return GCRY_CIPHER_MODE_NONE;
+ }
+}
+
bool qcrypto_cipher_supports(QCryptoCipherAlgorithm alg,
QCryptoCipherMode mode)
{
@@ -43,6 +93,11 @@
return false;
}
+ if (gcry_cipher_algo_info(qcrypto_cipher_alg_to_gcry_alg(alg),
+ GCRYCTL_TEST_ALGO, NULL, NULL) != 0) {
+ return false;
+ }
+
switch (mode) {
case QCRYPTO_CIPHER_MODE_ECB:
case QCRYPTO_CIPHER_MODE_CBC:
@@ -188,72 +243,26 @@
return NULL;
}
- switch (alg) {
- case QCRYPTO_CIPHER_ALG_DES:
- gcryalg = GCRY_CIPHER_DES;
- break;
- case QCRYPTO_CIPHER_ALG_3DES:
- gcryalg = GCRY_CIPHER_3DES;
- break;
- case QCRYPTO_CIPHER_ALG_AES_128:
- gcryalg = GCRY_CIPHER_AES128;
- break;
- case QCRYPTO_CIPHER_ALG_AES_192:
- gcryalg = GCRY_CIPHER_AES192;
- break;
- case QCRYPTO_CIPHER_ALG_AES_256:
- gcryalg = GCRY_CIPHER_AES256;
- break;
- case QCRYPTO_CIPHER_ALG_CAST5_128:
- gcryalg = GCRY_CIPHER_CAST5;
- break;
- case QCRYPTO_CIPHER_ALG_SERPENT_128:
- gcryalg = GCRY_CIPHER_SERPENT128;
- break;
- case QCRYPTO_CIPHER_ALG_SERPENT_192:
- gcryalg = GCRY_CIPHER_SERPENT192;
- break;
- case QCRYPTO_CIPHER_ALG_SERPENT_256:
- gcryalg = GCRY_CIPHER_SERPENT256;
- break;
- case QCRYPTO_CIPHER_ALG_TWOFISH_128:
- gcryalg = GCRY_CIPHER_TWOFISH128;
- break;
- case QCRYPTO_CIPHER_ALG_TWOFISH_256:
- gcryalg = GCRY_CIPHER_TWOFISH;
- break;
-#ifdef CONFIG_CRYPTO_SM4
- case QCRYPTO_CIPHER_ALG_SM4:
- gcryalg = GCRY_CIPHER_SM4;
- break;
-#endif
- default:
+ gcryalg = qcrypto_cipher_alg_to_gcry_alg(alg);
+ if (gcryalg == GCRY_CIPHER_NONE) {
error_setg(errp, "Unsupported cipher algorithm %s",
QCryptoCipherAlgorithm_str(alg));
return NULL;
}
- drv = &qcrypto_gcrypt_driver;
- switch (mode) {
- case QCRYPTO_CIPHER_MODE_ECB:
- gcrymode = GCRY_CIPHER_MODE_ECB;
- break;
- case QCRYPTO_CIPHER_MODE_XTS:
- gcrymode = GCRY_CIPHER_MODE_XTS;
- break;
- case QCRYPTO_CIPHER_MODE_CBC:
- gcrymode = GCRY_CIPHER_MODE_CBC;
- break;
- case QCRYPTO_CIPHER_MODE_CTR:
- drv = &qcrypto_gcrypt_ctr_driver;
- gcrymode = GCRY_CIPHER_MODE_CTR;
- break;
- default:
+ gcrymode = qcrypto_cipher_mode_to_gcry_mode(mode);
+ if (gcrymode == GCRY_CIPHER_MODE_NONE) {
error_setg(errp, "Unsupported cipher mode %s",
QCryptoCipherMode_str(mode));
return NULL;
}
+ if (mode == QCRYPTO_CIPHER_MODE_CTR) {
+ drv = &qcrypto_gcrypt_ctr_driver;
+ } else {
+ drv = &qcrypto_gcrypt_driver;
+ }
+
ctx = g_new0(QCryptoCipherGcrypt, 1);
ctx->base.driver = drv;
diff --git a/docs/devel/migration/CPR.rst b/docs/devel/migration/CPR.rst
new file mode 100644
index 0000000..63c3647
--- /dev/null
+++ b/docs/devel/migration/CPR.rst
@@ -0,0 +1,147 @@
+CheckPoint and Restart (CPR)
+============================
+
+CPR is the umbrella name for a set of migration modes in which the
+VM is migrated to a new QEMU instance on the same host. It is
+intended for use when the goal is to update host software components
+that run the VM, such as QEMU or even the host kernel. At this time,
+cpr-reboot is the only available mode.
+
+Because QEMU is restarted on the same host, with access to the same
+local devices, CPR is allowed in certain cases where normal migration
+would be blocked. However, the user must not modify the contents of
+guest block devices between quitting old QEMU and starting new QEMU.
+
+CPR unconditionally stops VM execution before memory is saved, and
+thus does not depend on any form of dirty page tracking.
+
+cpr-reboot mode
+---------------
+
+In this mode, QEMU stops the VM, and writes VM state to the migration
+URI, which will typically be a file. After quitting QEMU, the user
+resumes by running QEMU with the ``-incoming`` option. Because the
+old and new QEMU instances are not active concurrently, the URI cannot
+be a type that streams data from one instance to the other.
+
+Guest RAM can be saved in place if backed by shared memory, or can be
+copied to a file. The former is more efficient and is therefore
+preferred.
+
+After state and memory are saved, the user may update userland host
+software before restarting QEMU and resuming the VM. Further, if
+the RAM is backed by persistent shared memory, such as a DAX device,
+then the user may reboot to a new host kernel before restarting QEMU.
+
+This mode supports VFIO devices provided the user first puts the
+guest in the suspended runstate, such as by issuing the
+``guest-suspend-ram`` command to the QEMU guest agent. The agent
+must be pre-installed in the guest, and the guest must support
+suspend to RAM. Beware that suspension can take a few seconds, so
+the user should poll to see the suspended state before proceeding
+with the CPR operation.
+
+Usage
+^^^^^
+
+It is recommended that guest RAM be backed with some type of shared
+memory, such as ``memory-backend-file,share=on``, and that the
+``x-ignore-shared`` capability be set. This combination allows memory
+to be saved in place. Otherwise, after QEMU stops the VM, all guest
+RAM is copied to the migration URI.
+
+Outgoing:
+ * Set the migration mode parameter to ``cpr-reboot``.
+ * Set the ``x-ignore-shared`` capability if desired.
+ * Issue the ``migrate`` command. It is recommended the the URI be a
+ ``file`` type, but one can use other types such as ``exec``,
+ provided the command captures all the data from the outgoing side,
+ and provides all the data to the incoming side.
+ * Quit when QEMU reaches the postmigrate state.
+
+Incoming:
+ * Start QEMU with the ``-incoming defer`` option.
+ * Set the migration mode parameter to ``cpr-reboot``.
+ * Set the ``x-ignore-shared`` capability if desired.
+ * Issue the ``migrate-incoming`` command.
+ * If the VM was running when the outgoing ``migrate`` command was
+ issued, then QEMU automatically resumes VM execution.
+
+Example 1
+^^^^^^^^^
+::
+
+ # qemu-kvm -monitor stdio
+ -object memory-backend-file,id=ram0,size=4G,mem-path=/dev/dax0.0,align=2M,share=on -m 4G
+ ...
+
+ (qemu) info status
+ VM status: running
+ (qemu) migrate_set_parameter mode cpr-reboot
+ (qemu) migrate_set_capability x-ignore-shared on
+ (qemu) migrate -d file:vm.state
+ (qemu) info status
+ VM status: paused (postmigrate)
+ (qemu) quit
+
+ ### optionally update kernel and reboot
+ # systemctl kexec
+ kexec_core: Starting new kernel
+ ...
+
+ # qemu-kvm ... -incoming defer
+ (qemu) info status
+ VM status: paused (inmigrate)
+ (qemu) migrate_set_parameter mode cpr-reboot
+ (qemu) migrate_set_capability x-ignore-shared on
+ (qemu) migrate_incoming file:vm.state
+ (qemu) info status
+ VM status: running
+
+Example 2: VFIO
+^^^^^^^^^^^^^^^
+::
+
+ # qemu-kvm -monitor stdio
+ -object memory-backend-file,id=ram0,size=4G,mem-path=/dev/dax0.0,align=2M,share=on -m 4G
+ -device vfio-pci, ...
+ -chardev socket,id=qga0,path=qga.sock,server=on,wait=off
+ -device virtserialport,chardev=qga0,name=org.qemu.guest_agent.0
+ ...
+
+ (qemu) info status
+ VM status: running
+
+ # echo '{"execute":"guest-suspend-ram"}' | ncat --send-only -U qga.sock
+
+ (qemu) info status
+ VM status: paused (suspended)
+ (qemu) migrate_set_parameter mode cpr-reboot
+ (qemu) migrate_set_capability x-ignore-shared on
+ (qemu) migrate -d file:vm.state
+ (qemu) info status
+ VM status: paused (postmigrate)
+ (qemu) quit
+
+ ### optionally update kernel and reboot
+ # systemctl kexec
+ kexec_core: Starting new kernel
+ ...
+
+ # qemu-kvm ... -incoming defer
+ (qemu) info status
+ VM status: paused (inmigrate)
+ (qemu) migrate_set_parameter mode cpr-reboot
+ (qemu) migrate_set_capability x-ignore-shared on
+ (qemu) migrate_incoming file:vm.state
+ (qemu) info status
+ VM status: paused (suspended)
+ (qemu) system_wakeup
+ (qemu) info status
+ VM status: running
+
+Caveats
+^^^^^^^
+
+cpr-reboot mode may not be used with postcopy, background-snapshot,
+or COLO.
diff --git a/docs/devel/migration/features.rst b/docs/devel/migration/features.rst
index 9d1abd2..d5ca7b8 100644
--- a/docs/devel/migration/features.rst
+++ b/docs/devel/migration/features.rst
@@ -11,3 +11,4 @@
vfio
virtio
mapped-ram
+ CPR
diff --git a/docs/specs/pvpanic.rst b/docs/specs/pvpanic.rst
index 61a8048..b0f2786 100644
--- a/docs/specs/pvpanic.rst
+++ b/docs/specs/pvpanic.rst
@@ -29,7 +29,7 @@
a guest panic has happened and will be handled by the guest;
the host should record it or report it, but should not affect
the execution of the guest.
-bit 2
+bit 2 (to be implemented)
a regular guest shutdown has happened and should be processed by the host
PCI Interface
diff --git a/docs/system/introduction.rst b/docs/system/introduction.rst
index 51ac132..746707e 100644
--- a/docs/system/introduction.rst
+++ b/docs/system/introduction.rst
@@ -1,6 +1,8 @@
Introduction
============
+.. _Accelerators:
+
Virtualisation Accelerators
---------------------------
diff --git a/docs/system/s390x/cpu-topology.rst b/docs/system/s390x/cpu-topology.rst
index 5133fdc..d5b506e 100644
--- a/docs/system/s390x/cpu-topology.rst
+++ b/docs/system/s390x/cpu-topology.rst
@@ -25,17 +25,19 @@
Prerequisites
-------------
-To use the CPU topology, you need to run with KVM on a s390x host that
-uses the Linux kernel v6.0 or newer (which provide the so-called
+To use the CPU topology, you currently need to choose the KVM accelerator.
+See :ref:`Accelerators` for more details about accelerators and how to select them.
+
+The s390x host needs to use a Linux kernel v6.0 or newer (which provides the so-called
``KVM_CAP_S390_CPU_TOPOLOGY`` capability that allows QEMU to signal the
CPU topology facility via the so-called STFLE bit 11 to the VM).
Enabling CPU topology
---------------------
-Currently, CPU topology is only enabled in the host model by default.
+Currently, CPU topology is enabled by default only in the "host" CPU model.
-Enabling CPU topology in a CPU model is done by setting the CPU flag
+Enabling CPU topology in another CPU model is done by setting the CPU flag
``ctop`` to ``on`` as in:
.. code-block:: bash
@@ -132,7 +134,7 @@
.. code-block:: bash
- $ qemu-system-s390x -m 2G \
+ $ qemu-system-s390x -accel kvm -m 2G \
-cpu gen16b,ctop=on \
-smp cpus=5,sockets=8,cores=4,maxcpus=32 \
-device host-s390x-cpu,core-id=14 \
@@ -227,7 +229,7 @@
.. code-block:: bash
- $ qemu-system-s390x -m 2G \
+ $ qemu-system-s390x -accel kvm -m 2G \
-cpu gen16b,ctop=on \
-smp cpus=1,sockets=8,cores=4,maxcpus=32 \
\
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index e5cd935..a9a913a 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -1650,14 +1650,14 @@
}
smbios_set_defaults("QEMU", product,
- vmc->smbios_old_sys_ver ? "1.0" : mc->name, false,
- true, SMBIOS_ENTRY_POINT_TYPE_64);
+ vmc->smbios_old_sys_ver ? "1.0" : mc->name,
+ true);
/* build the array of physical mem area from base_memmap */
mem_array.address = vms->memmap[VIRT_MEM].base;
mem_array.length = ms->ram_size;
- smbios_get_tables(ms, &mem_array, 1,
+ smbios_get_tables(ms, SMBIOS_ENTRY_POINT_TYPE_64, &mem_array, 1,
&smbios_tables, &smbios_tables_len,
&smbios_anchor, &smbios_anchor_len,
&error_fatal);
diff --git a/hw/arm/xlnx-versal-virt.c b/hw/arm/xlnx-versal-virt.c
index bfaed1a..962f98f 100644
--- a/hw/arm/xlnx-versal-virt.c
+++ b/hw/arm/xlnx-versal-virt.c
@@ -13,6 +13,7 @@
#include "qemu/error-report.h"
#include "qapi/error.h"
#include "sysemu/device_tree.h"
+#include "hw/block/flash.h"
#include "hw/boards.h"
#include "hw/sysbus.h"
#include "hw/arm/fdt.h"
@@ -759,7 +760,7 @@
flash_klass = object_class_by_name(s->ospi_model);
if (!flash_klass ||
object_class_is_abstract(flash_klass) ||
- !object_class_dynamic_cast(flash_klass, "m25p80-generic")) {
+ !object_class_dynamic_cast(flash_klass, TYPE_M25P80)) {
error_setg(&error_fatal, "'%s' is either abstract or"
" not a subtype of m25p80", s->ospi_model);
return;
diff --git a/hw/block/m25p80.c b/hw/block/m25p80.c
index 08a00a6..8dec134 100644
--- a/hw/block/m25p80.c
+++ b/hw/block/m25p80.c
@@ -515,7 +515,6 @@
FlashPartInfo *pi;
};
-#define TYPE_M25P80 "m25p80-generic"
OBJECT_DECLARE_TYPE(Flash, M25P80Class, M25P80)
static inline Manufacturer get_man(Flash *s)
diff --git a/hw/i386/Kconfig b/hw/i386/Kconfig
index a1846be..a6ee052 100644
--- a/hw/i386/Kconfig
+++ b/hw/i386/Kconfig
@@ -76,6 +76,7 @@
select PIIX
select DIMM
select SMBIOS
+ select SMBIOS_LEGACY
select FW_CFG_DMA
config ISAPC
diff --git a/hw/i386/fw_cfg.c b/hw/i386/fw_cfg.c
index 98a478c..d802d27 100644
--- a/hw/i386/fw_cfg.c
+++ b/hw/i386/fw_cfg.c
@@ -48,7 +48,8 @@
return NULL;
}
-void fw_cfg_build_smbios(PCMachineState *pcms, FWCfgState *fw_cfg)
+void fw_cfg_build_smbios(PCMachineState *pcms, FWCfgState *fw_cfg,
+ SmbiosEntryPointType ep_type)
{
#ifdef CONFIG_SMBIOS
uint8_t *smbios_tables, *smbios_anchor;
@@ -63,17 +64,18 @@
if (pcmc->smbios_defaults) {
/* These values are guest ABI, do not change */
smbios_set_defaults("QEMU", mc->desc, mc->name,
- pcmc->smbios_legacy_mode, pcmc->smbios_uuid_encoded,
- pcms->smbios_entry_point_type);
+ pcmc->smbios_uuid_encoded);
}
/* tell smbios about cpuid version and features */
smbios_set_cpuid(cpu->env.cpuid_version, cpu->env.features[FEAT_1_EDX]);
- smbios_tables = smbios_get_table_legacy(ms, &smbios_tables_len);
- if (smbios_tables) {
+ if (pcmc->smbios_legacy_mode) {
+ smbios_tables = smbios_get_table_legacy(&smbios_tables_len,
+ &error_fatal);
fw_cfg_add_bytes(fw_cfg, FW_CFG_SMBIOS_ENTRIES,
smbios_tables, smbios_tables_len);
+ return;
}
/* build the array of physical mem area from e820 table */
@@ -87,7 +89,7 @@
array_count++;
}
}
- smbios_get_tables(ms, mem_array, array_count,
+ smbios_get_tables(ms, ep_type, mem_array, array_count,
&smbios_tables, &smbios_tables_len,
&smbios_anchor, &smbios_anchor_len,
&error_fatal);
diff --git a/hw/i386/fw_cfg.h b/hw/i386/fw_cfg.h
index 1e1de6b..92e310f 100644
--- a/hw/i386/fw_cfg.h
+++ b/hw/i386/fw_cfg.h
@@ -23,7 +23,8 @@
FWCfgState *fw_cfg_arch_create(MachineState *ms,
uint16_t boot_cpus,
uint16_t apic_id_limit);
-void fw_cfg_build_smbios(PCMachineState *ms, FWCfgState *fw_cfg);
+void fw_cfg_build_smbios(PCMachineState *pcms, FWCfgState *fw_cfg,
+ SmbiosEntryPointType ep_type);
void fw_cfg_build_feature_control(MachineState *ms, FWCfgState *fw_cfg);
void fw_cfg_add_acpi_dsdt(Aml *scope, FWCfgState *fw_cfg);
diff --git a/hw/i386/pc.c b/hw/i386/pc.c
index feb7a93..e80f02b 100644
--- a/hw/i386/pc.c
+++ b/hw/i386/pc.c
@@ -672,7 +672,7 @@
acpi_setup();
if (x86ms->fw_cfg) {
- fw_cfg_build_smbios(pcms, x86ms->fw_cfg);
+ fw_cfg_build_smbios(pcms, x86ms->fw_cfg, pcms->smbios_entry_point_type);
fw_cfg_build_feature_control(MACHINE(pcms), x86ms->fw_cfg);
/* update FW_CFG_NB_CPUS to account for -device added CPUs */
fw_cfg_modify_i16(x86ms->fw_cfg, FW_CFG_NB_CPUS, x86ms->boot_cpus);
@@ -1832,7 +1832,7 @@
mc->nvdimm_supported = true;
mc->smp_props.dies_supported = true;
mc->default_ram_id = "pc.ram";
- pcmc->default_smbios_ep_type = SMBIOS_ENTRY_POINT_TYPE_64;
+ pcmc->default_smbios_ep_type = SMBIOS_ENTRY_POINT_TYPE_AUTO;
object_class_property_add(oc, PC_MACHINE_MAX_RAM_BELOW_4G, "size",
pc_machine_get_max_ram_below_4g, pc_machine_set_max_ram_below_4g,
diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c
index c9a6c0a..18ba076 100644
--- a/hw/i386/pc_piix.c
+++ b/hw/i386/pc_piix.c
@@ -525,12 +525,16 @@
static void pc_i440fx_8_2_machine_options(MachineClass *m)
{
+ PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
+
pc_i440fx_9_0_machine_options(m);
m->alias = NULL;
m->is_default = false;
compat_props_add(m->compat_props, hw_compat_8_2, hw_compat_8_2_len);
compat_props_add(m->compat_props, pc_compat_8_2, pc_compat_8_2_len);
+ /* For pc-i44fx-8.2 and 8.1, use SMBIOS 3.X by default */
+ pcmc->default_smbios_ep_type = SMBIOS_ENTRY_POINT_TYPE_64;
}
DEFINE_I440FX_MACHINE(v8_2, "pc-i440fx-8.2", NULL,
diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c
index 8a427c4..b5922b4 100644
--- a/hw/i386/pc_q35.c
+++ b/hw/i386/pc_q35.c
@@ -376,11 +376,14 @@
static void pc_q35_8_2_machine_options(MachineClass *m)
{
+ PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
pc_q35_9_0_machine_options(m);
m->alias = NULL;
m->max_cpus = 1024;
compat_props_add(m->compat_props, hw_compat_8_2, hw_compat_8_2_len);
compat_props_add(m->compat_props, pc_compat_8_2, pc_compat_8_2_len);
+ /* For pc-q35-8.2 and 8.1, use SMBIOS 3.X by default */
+ pcmc->default_smbios_ep_type = SMBIOS_ENTRY_POINT_TYPE_64;
}
DEFINE_Q35_MACHINE(v8_2, "pc-q35-8.2", NULL,
diff --git a/hw/intc/loongarch_extioi.c b/hw/intc/loongarch_extioi.c
index bdfa3b4..0b35854 100644
--- a/hw/intc/loongarch_extioi.c
+++ b/hw/intc/loongarch_extioi.c
@@ -151,7 +151,7 @@
continue;
}
- if (notify && test_bit(irq, (unsigned long *)s->isr)) {
+ if (notify && test_bit(irq + i, (unsigned long *)s->isr)) {
/*
* lower irq at old cpu and raise irq at new cpu
*/
diff --git a/hw/loongarch/virt.c b/hw/loongarch/virt.c
index efce112..441d764 100644
--- a/hw/loongarch/virt.c
+++ b/hw/loongarch/virt.c
@@ -355,10 +355,11 @@
return;
}
- smbios_set_defaults("QEMU", product, mc->name, false,
- true, SMBIOS_ENTRY_POINT_TYPE_64);
+ smbios_set_defaults("QEMU", product, mc->name, true);
- smbios_get_tables(ms, NULL, 0, &smbios_tables, &smbios_tables_len,
+ smbios_get_tables(ms, SMBIOS_ENTRY_POINT_TYPE_64,
+ NULL, 0,
+ &smbios_tables, &smbios_tables_len,
&smbios_anchor, &smbios_anchor_len, &error_fatal);
if (smbios_anchor) {
diff --git a/hw/ppc/pnv_i2c.c b/hw/ppc/pnv_i2c.c
index 4581cc5..eec5047 100644
--- a/hw/ppc/pnv_i2c.c
+++ b/hw/ppc/pnv_i2c.c
@@ -557,6 +557,9 @@
xscomc->dt_xscom = pnv_i2c_dt_xscom;
+ /* Reason: This device is part of the CPU and cannot be used separately */
+ dc->user_creatable = false;
+
dc->desc = "PowerNV I2C";
dc->realize = pnv_i2c_realize;
device_class_set_props(dc, pnv_i2c_properties);
diff --git a/hw/riscv/virt.c b/hw/riscv/virt.c
index a094af9..72a55b8 100644
--- a/hw/riscv/virt.c
+++ b/hw/riscv/virt.c
@@ -1275,8 +1275,7 @@
product = "KVM Virtual Machine";
}
- smbios_set_defaults("QEMU", product, mc->name, false,
- true, SMBIOS_ENTRY_POINT_TYPE_64);
+ smbios_set_defaults("QEMU", product, mc->name, true);
if (riscv_is_32bit(&s->soc[0])) {
smbios_set_default_processor_family(0x200);
@@ -1288,7 +1287,8 @@
mem_array.address = s->memmap[VIRT_DRAM].base;
mem_array.length = ms->ram_size;
- smbios_get_tables(ms, &mem_array, 1,
+ smbios_get_tables(ms, SMBIOS_ENTRY_POINT_TYPE_64,
+ &mem_array, 1,
&smbios_tables, &smbios_tables_len,
&smbios_anchor, &smbios_anchor_len,
&error_fatal);
diff --git a/hw/smbios/Kconfig b/hw/smbios/Kconfig
index 553adf4..8d989a2 100644
--- a/hw/smbios/Kconfig
+++ b/hw/smbios/Kconfig
@@ -1,2 +1,4 @@
config SMBIOS
bool
+config SMBIOS_LEGACY
+ bool
diff --git a/hw/smbios/meson.build b/hw/smbios/meson.build
index 7046967..a59039f 100644
--- a/hw/smbios/meson.build
+++ b/hw/smbios/meson.build
@@ -4,5 +4,9 @@
if_true: files('smbios_type_38.c'),
if_false: files('smbios_type_38-stub.c'))
+smbios_ss.add(when: 'CONFIG_SMBIOS_LEGACY',
+ if_true: files('smbios_legacy.c'),
+ if_false: files('smbios_legacy_stub.c'))
+
system_ss.add_all(when: 'CONFIG_SMBIOS', if_true: smbios_ss)
system_ss.add(when: 'CONFIG_SMBIOS', if_false: files('smbios-stub.c'))
diff --git a/hw/smbios/smbios.c b/hw/smbios/smbios.c
index e3d5d8f..eed5787 100644
--- a/hw/smbios/smbios.c
+++ b/hw/smbios/smbios.c
@@ -19,7 +19,6 @@
#include "qemu/units.h"
#include "qapi/error.h"
#include "qemu/config-file.h"
-#include "qemu/error-report.h"
#include "qemu/module.h"
#include "qemu/option.h"
#include "sysemu/sysemu.h"
@@ -31,60 +30,31 @@
#include "hw/pci/pci_device.h"
#include "smbios_build.h"
-/* legacy structures and constants for <= 2.0 machines */
-struct smbios_header {
- uint16_t length;
- uint8_t type;
-} QEMU_PACKED;
-
-struct smbios_field {
- struct smbios_header header;
- uint8_t type;
- uint16_t offset;
- uint8_t data[];
-} QEMU_PACKED;
-
-struct smbios_table {
- struct smbios_header header;
- uint8_t data[];
-} QEMU_PACKED;
-
-#define SMBIOS_FIELD_ENTRY 0
-#define SMBIOS_TABLE_ENTRY 1
-
-static uint8_t *smbios_entries;
-static size_t smbios_entries_len;
-static bool smbios_legacy = true;
static bool smbios_uuid_encoded = true;
-/* end: legacy structures & constants for <= 2.0 machines */
-
+/*
+ * SMBIOS tables provided by user with '-smbios file=<foo>' option
+ */
+uint8_t *usr_blobs;
+size_t usr_blobs_len;
+static unsigned usr_table_max;
+static unsigned usr_table_cnt;
uint8_t *smbios_tables;
size_t smbios_tables_len;
unsigned smbios_table_max;
unsigned smbios_table_cnt;
-static SmbiosEntryPointType smbios_ep_type = SMBIOS_ENTRY_POINT_TYPE_32;
static SmbiosEntryPoint ep;
static int smbios_type4_count = 0;
-static bool smbios_immutable;
static bool smbios_have_defaults;
-static uint32_t smbios_cpuid_version, smbios_cpuid_features, smbios_smp_sockets;
+static uint32_t smbios_cpuid_version, smbios_cpuid_features;
-static DECLARE_BITMAP(have_binfile_bitmap, SMBIOS_MAX_TYPE+1);
-static DECLARE_BITMAP(have_fields_bitmap, SMBIOS_MAX_TYPE+1);
+DECLARE_BITMAP(smbios_have_binfile_bitmap, SMBIOS_MAX_TYPE + 1);
+DECLARE_BITMAP(smbios_have_fields_bitmap, SMBIOS_MAX_TYPE + 1);
-static struct {
- const char *vendor, *version, *date;
- bool have_major_minor, uefi;
- uint8_t major, minor;
-} type0;
-
-static struct {
- const char *manufacturer, *product, *version, *serial, *sku, *family;
- /* uuid is in qemu_uuid */
-} type1;
+smbios_type0_t smbios_type0;
+smbios_type1_t smbios_type1;
static struct {
const char *manufacturer, *product, *version, *serial, *asset, *location;
@@ -539,126 +509,33 @@
*/
#define SMBIOS_21_MAX_TABLES_LEN 0xffff
-static void smbios_validate_table(MachineState *ms)
+static bool smbios_check_type4_count(uint32_t expected_t4_count, Error **errp)
{
- uint32_t expect_t4_count = smbios_legacy ?
- ms->smp.cpus : smbios_smp_sockets;
-
- if (smbios_type4_count && smbios_type4_count != expect_t4_count) {
- error_report("Expected %d SMBIOS Type 4 tables, got %d instead",
- expect_t4_count, smbios_type4_count);
- exit(1);
+ if (smbios_type4_count && smbios_type4_count != expected_t4_count) {
+ error_setg(errp, "Expected %d SMBIOS Type 4 tables, got %d instead",
+ expected_t4_count, smbios_type4_count);
+ return false;
}
+ return true;
+}
- if (smbios_ep_type == SMBIOS_ENTRY_POINT_TYPE_32 &&
+bool smbios_validate_table(SmbiosEntryPointType ep_type, Error **errp)
+{
+ if (ep_type == SMBIOS_ENTRY_POINT_TYPE_32 &&
smbios_tables_len > SMBIOS_21_MAX_TABLES_LEN) {
- error_report("SMBIOS 2.1 table length %zu exceeds %d",
- smbios_tables_len, SMBIOS_21_MAX_TABLES_LEN);
- exit(1);
+ error_setg(errp, "SMBIOS 2.1 table length %zu exceeds %d",
+ smbios_tables_len, SMBIOS_21_MAX_TABLES_LEN);
+ return false;
}
+ return true;
}
-
-/* legacy setup functions for <= 2.0 machines */
-static void smbios_add_field(int type, int offset, const void *data, size_t len)
-{
- struct smbios_field *field;
-
- if (!smbios_entries) {
- smbios_entries_len = sizeof(uint16_t);
- smbios_entries = g_malloc0(smbios_entries_len);
- }
- smbios_entries = g_realloc(smbios_entries, smbios_entries_len +
- sizeof(*field) + len);
- field = (struct smbios_field *)(smbios_entries + smbios_entries_len);
- field->header.type = SMBIOS_FIELD_ENTRY;
- field->header.length = cpu_to_le16(sizeof(*field) + len);
-
- field->type = type;
- field->offset = cpu_to_le16(offset);
- memcpy(field->data, data, len);
-
- smbios_entries_len += sizeof(*field) + len;
- (*(uint16_t *)smbios_entries) =
- cpu_to_le16(le16_to_cpu(*(uint16_t *)smbios_entries) + 1);
-}
-
-static void smbios_maybe_add_str(int type, int offset, const char *data)
-{
- if (data) {
- smbios_add_field(type, offset, data, strlen(data) + 1);
- }
-}
-
-static void smbios_build_type_0_fields(void)
-{
- smbios_maybe_add_str(0, offsetof(struct smbios_type_0, vendor_str),
- type0.vendor);
- smbios_maybe_add_str(0, offsetof(struct smbios_type_0, bios_version_str),
- type0.version);
- smbios_maybe_add_str(0, offsetof(struct smbios_type_0,
- bios_release_date_str),
- type0.date);
- if (type0.have_major_minor) {
- smbios_add_field(0, offsetof(struct smbios_type_0,
- system_bios_major_release),
- &type0.major, 1);
- smbios_add_field(0, offsetof(struct smbios_type_0,
- system_bios_minor_release),
- &type0.minor, 1);
- }
-}
-
-static void smbios_build_type_1_fields(void)
-{
- smbios_maybe_add_str(1, offsetof(struct smbios_type_1, manufacturer_str),
- type1.manufacturer);
- smbios_maybe_add_str(1, offsetof(struct smbios_type_1, product_name_str),
- type1.product);
- smbios_maybe_add_str(1, offsetof(struct smbios_type_1, version_str),
- type1.version);
- smbios_maybe_add_str(1, offsetof(struct smbios_type_1, serial_number_str),
- type1.serial);
- smbios_maybe_add_str(1, offsetof(struct smbios_type_1, sku_number_str),
- type1.sku);
- smbios_maybe_add_str(1, offsetof(struct smbios_type_1, family_str),
- type1.family);
- if (qemu_uuid_set) {
- /* We don't encode the UUID in the "wire format" here because this
- * function is for legacy mode and needs to keep the guest ABI, and
- * because we don't know what's the SMBIOS version advertised by the
- * BIOS.
- */
- smbios_add_field(1, offsetof(struct smbios_type_1, uuid),
- &qemu_uuid, 16);
- }
-}
-
-uint8_t *smbios_get_table_legacy(MachineState *ms, size_t *length)
-{
- if (!smbios_legacy) {
- *length = 0;
- return NULL;
- }
-
- if (!smbios_immutable) {
- smbios_build_type_0_fields();
- smbios_build_type_1_fields();
- smbios_validate_table(ms);
- smbios_immutable = true;
- }
- *length = smbios_entries_len;
- return smbios_entries;
-}
-/* end: legacy setup functions for <= 2.0 machines */
-
-
bool smbios_skip_table(uint8_t type, bool required_table)
{
- if (test_bit(type, have_binfile_bitmap)) {
+ if (test_bit(type, smbios_have_binfile_bitmap)) {
return true; /* user provided their own binary blob(s) */
}
- if (test_bit(type, have_fields_bitmap)) {
+ if (test_bit(type, smbios_have_fields_bitmap)) {
return false; /* user provided fields via command line */
}
if (smbios_have_defaults && required_table) {
@@ -686,25 +563,25 @@
{
SMBIOS_BUILD_TABLE_PRE(0, T0_BASE, false); /* optional, leave up to BIOS */
- SMBIOS_TABLE_SET_STR(0, vendor_str, type0.vendor);
- SMBIOS_TABLE_SET_STR(0, bios_version_str, type0.version);
+ SMBIOS_TABLE_SET_STR(0, vendor_str, smbios_type0.vendor);
+ SMBIOS_TABLE_SET_STR(0, bios_version_str, smbios_type0.version);
t->bios_starting_address_segment = cpu_to_le16(0xE800); /* from SeaBIOS */
- SMBIOS_TABLE_SET_STR(0, bios_release_date_str, type0.date);
+ SMBIOS_TABLE_SET_STR(0, bios_release_date_str, smbios_type0.date);
t->bios_rom_size = 0; /* hardcoded in SeaBIOS with FIXME comment */
t->bios_characteristics = cpu_to_le64(0x08); /* Not supported */
t->bios_characteristics_extension_bytes[0] = 0;
t->bios_characteristics_extension_bytes[1] = 0x14; /* TCD/SVVP | VM */
- if (type0.uefi) {
+ if (smbios_type0.uefi) {
t->bios_characteristics_extension_bytes[1] |= 0x08; /* |= UEFI */
}
- if (type0.have_major_minor) {
- t->system_bios_major_release = type0.major;
- t->system_bios_minor_release = type0.minor;
+ if (smbios_type0.have_major_minor) {
+ t->system_bios_major_release = smbios_type0.major;
+ t->system_bios_minor_release = smbios_type0.minor;
} else {
t->system_bios_major_release = 0;
t->system_bios_minor_release = 0;
@@ -734,18 +611,18 @@
{
SMBIOS_BUILD_TABLE_PRE(1, T1_BASE, true); /* required */
- SMBIOS_TABLE_SET_STR(1, manufacturer_str, type1.manufacturer);
- SMBIOS_TABLE_SET_STR(1, product_name_str, type1.product);
- SMBIOS_TABLE_SET_STR(1, version_str, type1.version);
- SMBIOS_TABLE_SET_STR(1, serial_number_str, type1.serial);
+ SMBIOS_TABLE_SET_STR(1, manufacturer_str, smbios_type1.manufacturer);
+ SMBIOS_TABLE_SET_STR(1, product_name_str, smbios_type1.product);
+ SMBIOS_TABLE_SET_STR(1, version_str, smbios_type1.version);
+ SMBIOS_TABLE_SET_STR(1, serial_number_str, smbios_type1.serial);
if (qemu_uuid_set) {
smbios_encode_uuid(&t->uuid, &qemu_uuid);
} else {
memset(&t->uuid, 0, 16);
}
t->wake_up_type = 0x06; /* power switch */
- SMBIOS_TABLE_SET_STR(1, sku_number_str, type1.sku);
- SMBIOS_TABLE_SET_STR(1, family_str, type1.family);
+ SMBIOS_TABLE_SET_STR(1, sku_number_str, smbios_type1.sku);
+ SMBIOS_TABLE_SET_STR(1, family_str, smbios_type1.family);
SMBIOS_BUILD_TABLE_POST;
}
@@ -791,14 +668,16 @@
SMBIOS_BUILD_TABLE_POST;
}
-static void smbios_build_type_4_table(MachineState *ms, unsigned instance)
+static void smbios_build_type_4_table(MachineState *ms, unsigned instance,
+ SmbiosEntryPointType ep_type,
+ Error **errp)
{
char sock_str[128];
size_t tbl_len = SMBIOS_TYPE_4_LEN_V28;
unsigned threads_per_socket;
unsigned cores_per_socket;
- if (smbios_ep_type == SMBIOS_ENTRY_POINT_TYPE_64) {
+ if (ep_type == SMBIOS_ENTRY_POINT_TYPE_64) {
tbl_len = SMBIOS_TYPE_4_LEN_V30;
}
@@ -845,6 +724,12 @@
if (tbl_len == SMBIOS_TYPE_4_LEN_V30) {
t->core_count2 = t->core_enabled2 = cpu_to_le16(cores_per_socket);
t->thread_count2 = cpu_to_le16(threads_per_socket);
+ } else if (t->core_count == 0xFF || t->thread_count == 0xFF) {
+ error_setg(errp, "SMBIOS 2.0 doesn't support number of processor "
+ "cores/threads more than 255, use "
+ "-machine smbios-entry-point-type=64 option to enable "
+ "SMBIOS 3.0 support");
+ return;
}
SMBIOS_BUILD_TABLE_POST;
@@ -1132,31 +1017,15 @@
}
void smbios_set_defaults(const char *manufacturer, const char *product,
- const char *version, bool legacy_mode,
- bool uuid_encoded, SmbiosEntryPointType ep_type)
+ const char *version,
+ bool uuid_encoded)
{
smbios_have_defaults = true;
- smbios_legacy = legacy_mode;
smbios_uuid_encoded = uuid_encoded;
- smbios_ep_type = ep_type;
- /* drop unwanted version of command-line file blob(s) */
- if (smbios_legacy) {
- g_free(smbios_tables);
- /* in legacy mode, also complain if fields were given for types > 1 */
- if (find_next_bit(have_fields_bitmap,
- SMBIOS_MAX_TYPE+1, 2) < SMBIOS_MAX_TYPE+1) {
- error_report("can't process fields for smbios "
- "types > 1 on machine versions < 2.1!");
- exit(1);
- }
- } else {
- g_free(smbios_entries);
- }
-
- SMBIOS_SET_DEFAULT(type1.manufacturer, manufacturer);
- SMBIOS_SET_DEFAULT(type1.product, product);
- SMBIOS_SET_DEFAULT(type1.version, version);
+ SMBIOS_SET_DEFAULT(smbios_type1.manufacturer, manufacturer);
+ SMBIOS_SET_DEFAULT(smbios_type1.product, product);
+ SMBIOS_SET_DEFAULT(smbios_type1.version, version);
SMBIOS_SET_DEFAULT(type2.manufacturer, manufacturer);
SMBIOS_SET_DEFAULT(type2.product, product);
SMBIOS_SET_DEFAULT(type2.version, version);
@@ -1169,9 +1038,9 @@
SMBIOS_SET_DEFAULT(type17.manufacturer, manufacturer);
}
-static void smbios_entry_point_setup(void)
+static void smbios_entry_point_setup(SmbiosEntryPointType ep_type)
{
- switch (smbios_ep_type) {
+ switch (ep_type) {
case SMBIOS_ENTRY_POINT_TYPE_32:
memcpy(ep.ep21.anchor_string, "_SM_", 4);
memcpy(ep.ep21.intermediate_anchor_string, "_DMI_", 5);
@@ -1220,7 +1089,8 @@
}
}
-void smbios_get_tables(MachineState *ms,
+static bool smbios_get_tables_ep(MachineState *ms,
+ SmbiosEntryPointType ep_type,
const struct smbios_phys_mem_area *mem_array,
const unsigned int mem_array_size,
uint8_t **tables, size_t *tables_len,
@@ -1228,78 +1098,87 @@
Error **errp)
{
unsigned i, dimm_cnt, offset;
+ ERRP_GUARD();
- if (smbios_legacy) {
- *tables = *anchor = NULL;
- *tables_len = *anchor_len = 0;
- return;
+ assert(ep_type == SMBIOS_ENTRY_POINT_TYPE_32 ||
+ ep_type == SMBIOS_ENTRY_POINT_TYPE_64);
+
+ g_free(smbios_tables);
+ smbios_type4_count = 0;
+ smbios_tables = g_memdup2(usr_blobs, usr_blobs_len);
+ smbios_tables_len = usr_blobs_len;
+ smbios_table_max = usr_table_max;
+ smbios_table_cnt = usr_table_cnt;
+
+ smbios_build_type_0_table();
+ smbios_build_type_1_table();
+ smbios_build_type_2_table();
+ smbios_build_type_3_table();
+
+ assert(ms->smp.sockets >= 1);
+
+ for (i = 0; i < ms->smp.sockets; i++) {
+ smbios_build_type_4_table(ms, i, ep_type, errp);
+ if (*errp) {
+ goto err_exit;
+ }
}
- if (!smbios_immutable) {
- smbios_build_type_0_table();
- smbios_build_type_1_table();
- smbios_build_type_2_table();
- smbios_build_type_3_table();
-
- smbios_smp_sockets = ms->smp.sockets;
- assert(smbios_smp_sockets >= 1);
-
- for (i = 0; i < smbios_smp_sockets; i++) {
- smbios_build_type_4_table(ms, i);
- }
-
- smbios_build_type_8_table();
- smbios_build_type_9_table(errp);
- smbios_build_type_11_table();
+ smbios_build_type_8_table();
+ smbios_build_type_9_table(errp);
+ smbios_build_type_11_table();
#define MAX_DIMM_SZ (16 * GiB)
#define GET_DIMM_SZ ((i < dimm_cnt - 1) ? MAX_DIMM_SZ \
: ((current_machine->ram_size - 1) % MAX_DIMM_SZ) + 1)
- dimm_cnt = QEMU_ALIGN_UP(current_machine->ram_size, MAX_DIMM_SZ) / MAX_DIMM_SZ;
+ dimm_cnt = QEMU_ALIGN_UP(current_machine->ram_size, MAX_DIMM_SZ) /
+ MAX_DIMM_SZ;
- /*
- * The offset determines if we need to keep additional space between
- * table 17 and table 19 header handle numbers so that they do
- * not overlap. For example, for a VM with larger than 8 TB guest
- * memory and DIMM like chunks of 16 GiB, the default space between
- * the two tables (T19_BASE - T17_BASE = 512) is not enough.
- */
- offset = (dimm_cnt > (T19_BASE - T17_BASE)) ? \
- dimm_cnt - (T19_BASE - T17_BASE) : 0;
+ /*
+ * The offset determines if we need to keep additional space between
+ * table 17 and table 19 header handle numbers so that they do
+ * not overlap. For example, for a VM with larger than 8 TB guest
+ * memory and DIMM like chunks of 16 GiB, the default space between
+ * the two tables (T19_BASE - T17_BASE = 512) is not enough.
+ */
+ offset = (dimm_cnt > (T19_BASE - T17_BASE)) ? \
+ dimm_cnt - (T19_BASE - T17_BASE) : 0;
- smbios_build_type_16_table(dimm_cnt);
+ smbios_build_type_16_table(dimm_cnt);
- for (i = 0; i < dimm_cnt; i++) {
- smbios_build_type_17_table(i, GET_DIMM_SZ);
- }
-
- for (i = 0; i < mem_array_size; i++) {
- smbios_build_type_19_table(i, offset, mem_array[i].address,
- mem_array[i].length);
- }
-
- /*
- * make sure 16 bit handle numbers in the headers of tables 19
- * and 32 do not overlap.
- */
- assert((mem_array_size + offset) < (T32_BASE - T19_BASE));
-
- smbios_build_type_32_table();
- smbios_build_type_38_table();
- smbios_build_type_41_table(errp);
- smbios_build_type_127_table();
-
- smbios_validate_table(ms);
- smbios_entry_point_setup();
- smbios_immutable = true;
+ for (i = 0; i < dimm_cnt; i++) {
+ smbios_build_type_17_table(i, GET_DIMM_SZ);
}
+ for (i = 0; i < mem_array_size; i++) {
+ smbios_build_type_19_table(i, offset, mem_array[i].address,
+ mem_array[i].length);
+ }
+
+ /*
+ * make sure 16 bit handle numbers in the headers of tables 19
+ * and 32 do not overlap.
+ */
+ assert((mem_array_size + offset) < (T32_BASE - T19_BASE));
+
+ smbios_build_type_32_table();
+ smbios_build_type_38_table();
+ smbios_build_type_41_table(errp);
+ smbios_build_type_127_table();
+
+ if (!smbios_check_type4_count(ms->smp.sockets, errp)) {
+ goto err_exit;
+ }
+ if (!smbios_validate_table(ep_type, errp)) {
+ goto err_exit;
+ }
+ smbios_entry_point_setup(ep_type);
+
/* return tables blob and entry point (anchor), and their sizes */
*tables = smbios_tables;
*tables_len = smbios_tables_len;
*anchor = (uint8_t *)&ep;
-
/* calculate length based on anchor string */
if (!strncmp((char *)&ep, "_SM_", 4)) {
*anchor_len = sizeof(struct smbios_21_entry_point);
@@ -1308,6 +1187,57 @@
} else {
abort();
}
+
+ return true;
+err_exit:
+ g_free(smbios_tables);
+ smbios_tables = NULL;
+ return false;
+}
+
+void smbios_get_tables(MachineState *ms,
+ SmbiosEntryPointType ep_type,
+ const struct smbios_phys_mem_area *mem_array,
+ const unsigned int mem_array_size,
+ uint8_t **tables, size_t *tables_len,
+ uint8_t **anchor, size_t *anchor_len,
+ Error **errp)
+{
+ Error *local_err = NULL;
+ bool is_valid;
+ ERRP_GUARD();
+
+ switch (ep_type) {
+ case SMBIOS_ENTRY_POINT_TYPE_AUTO:
+ case SMBIOS_ENTRY_POINT_TYPE_32:
+ is_valid = smbios_get_tables_ep(ms, SMBIOS_ENTRY_POINT_TYPE_32,
+ mem_array, mem_array_size,
+ tables, tables_len,
+ anchor, anchor_len,
+ &local_err);
+ if (is_valid || ep_type != SMBIOS_ENTRY_POINT_TYPE_AUTO) {
+ break;
+ }
+ /*
+ * fall through in case AUTO endpoint is selected and
+ * SMBIOS 2.x tables can't be generated, to try if SMBIOS 3.x
+ * tables would work
+ */
+ case SMBIOS_ENTRY_POINT_TYPE_64:
+ error_free(local_err);
+ local_err = NULL;
+ is_valid = smbios_get_tables_ep(ms, SMBIOS_ENTRY_POINT_TYPE_64,
+ mem_array, mem_array_size,
+ tables, tables_len,
+ anchor, anchor_len,
+ &local_err);
+ break;
+ default:
+ abort();
+ }
+ if (!is_valid) {
+ error_propagate(errp, local_err);
+ }
}
static void save_opt(const char **dest, QemuOpts *opts, const char *name)
@@ -1393,13 +1323,10 @@
{
const char *val;
- assert(!smbios_immutable);
-
val = qemu_opt_get(opts, "file");
if (val) {
struct smbios_structure_header *header;
- int size;
- struct smbios_table *table; /* legacy mode only */
+ size_t size;
if (!qemu_opts_validate(opts, qemu_smbios_file_opts, errp)) {
return;
@@ -1416,9 +1343,9 @@
* (except in legacy mode, where the second '\0' is implicit and
* will be inserted by the BIOS).
*/
- smbios_tables = g_realloc(smbios_tables, smbios_tables_len + size);
- header = (struct smbios_structure_header *)(smbios_tables +
- smbios_tables_len);
+ usr_blobs = g_realloc(usr_blobs, usr_blobs_len + size);
+ header = (struct smbios_structure_header *)(usr_blobs +
+ usr_blobs_len);
if (load_image_size(val, (uint8_t *)header, size) != size) {
error_setg(errp, "Failed to load SMBIOS file %s", val);
@@ -1426,47 +1353,30 @@
}
if (header->type <= SMBIOS_MAX_TYPE) {
- if (test_bit(header->type, have_fields_bitmap)) {
+ if (test_bit(header->type, smbios_have_fields_bitmap)) {
error_setg(errp,
"can't load type %d struct, fields already specified!",
header->type);
return;
}
- set_bit(header->type, have_binfile_bitmap);
+ set_bit(header->type, smbios_have_binfile_bitmap);
}
if (header->type == 4) {
smbios_type4_count++;
}
- smbios_tables_len += size;
- if (size > smbios_table_max) {
- smbios_table_max = size;
- }
- smbios_table_cnt++;
-
- /* add a copy of the newly loaded blob to legacy smbios_entries */
- /* NOTE: This code runs before smbios_set_defaults(), so we don't
- * yet know which mode (legacy vs. aggregate-table) will be
- * required. We therefore add the binary blob to both legacy
- * (smbios_entries) and aggregate (smbios_tables) tables, and
- * delete the one we don't need from smbios_set_defaults(),
- * once we know which machine version has been requested.
+ /*
+ * preserve blob size for legacy mode so it could build its
+ * blobs flavor from 'usr_blobs'
*/
- if (!smbios_entries) {
- smbios_entries_len = sizeof(uint16_t);
- smbios_entries = g_malloc0(smbios_entries_len);
+ smbios_add_usr_blob_size(size);
+
+ usr_blobs_len += size;
+ if (size > usr_table_max) {
+ usr_table_max = size;
}
- smbios_entries = g_realloc(smbios_entries, smbios_entries_len +
- size + sizeof(*table));
- table = (struct smbios_table *)(smbios_entries + smbios_entries_len);
- table->header.type = SMBIOS_TABLE_ENTRY;
- table->header.length = cpu_to_le16(sizeof(*table) + size);
- memcpy(table->data, header, size);
- smbios_entries_len += sizeof(*table) + size;
- (*(uint16_t *)smbios_entries) =
- cpu_to_le16(le16_to_cpu(*(uint16_t *)smbios_entries) + 1);
- /* end: add a copy of the newly loaded blob to legacy smbios_entries */
+ usr_table_cnt++;
return;
}
@@ -1480,41 +1390,42 @@
return;
}
- if (test_bit(type, have_binfile_bitmap)) {
+ if (test_bit(type, smbios_have_binfile_bitmap)) {
error_setg(errp, "can't add fields, binary file already loaded!");
return;
}
- set_bit(type, have_fields_bitmap);
+ set_bit(type, smbios_have_fields_bitmap);
switch (type) {
case 0:
if (!qemu_opts_validate(opts, qemu_smbios_type0_opts, errp)) {
return;
}
- save_opt(&type0.vendor, opts, "vendor");
- save_opt(&type0.version, opts, "version");
- save_opt(&type0.date, opts, "date");
- type0.uefi = qemu_opt_get_bool(opts, "uefi", false);
+ save_opt(&smbios_type0.vendor, opts, "vendor");
+ save_opt(&smbios_type0.version, opts, "version");
+ save_opt(&smbios_type0.date, opts, "date");
+ smbios_type0.uefi = qemu_opt_get_bool(opts, "uefi", false);
val = qemu_opt_get(opts, "release");
if (val) {
- if (sscanf(val, "%hhu.%hhu", &type0.major, &type0.minor) != 2) {
+ if (sscanf(val, "%hhu.%hhu", &smbios_type0.major,
+ &smbios_type0.minor) != 2) {
error_setg(errp, "Invalid release");
return;
}
- type0.have_major_minor = true;
+ smbios_type0.have_major_minor = true;
}
return;
case 1:
if (!qemu_opts_validate(opts, qemu_smbios_type1_opts, errp)) {
return;
}
- save_opt(&type1.manufacturer, opts, "manufacturer");
- save_opt(&type1.product, opts, "product");
- save_opt(&type1.version, opts, "version");
- save_opt(&type1.serial, opts, "serial");
- save_opt(&type1.sku, opts, "sku");
- save_opt(&type1.family, opts, "family");
+ save_opt(&smbios_type1.manufacturer, opts, "manufacturer");
+ save_opt(&smbios_type1.product, opts, "product");
+ save_opt(&smbios_type1.version, opts, "version");
+ save_opt(&smbios_type1.serial, opts, "serial");
+ save_opt(&smbios_type1.sku, opts, "sku");
+ save_opt(&smbios_type1.family, opts, "family");
val = qemu_opt_get(opts, "uuid");
if (val) {
@@ -1592,12 +1503,15 @@
t = g_new0(struct type9_instance, 1);
save_opt(&t->slot_designation, opts, "slot_designation");
t->slot_type = qemu_opt_get_number(opts, "slot_type", 0);
- t->slot_data_bus_width = qemu_opt_get_number(opts, "slot_data_bus_width", 0);
+ t->slot_data_bus_width =
+ qemu_opt_get_number(opts, "slot_data_bus_width", 0);
t->current_usage = qemu_opt_get_number(opts, "current_usage", 0);
t->slot_length = qemu_opt_get_number(opts, "slot_length", 0);
t->slot_id = qemu_opt_get_number(opts, "slot_id", 0);
- t->slot_characteristics1 = qemu_opt_get_number(opts, "slot_characteristics1", 0);
- t->slot_characteristics2 = qemu_opt_get_number(opts, "slot_characteristics2", 0);
+ t->slot_characteristics1 =
+ qemu_opt_get_number(opts, "slot_characteristics1", 0);
+ t->slot_characteristics2 =
+ qemu_opt_get_number(opts, "slot_characteristics2", 0);
save_opt(&t->pcidev, opts, "pcidev");
QTAILQ_INSERT_TAIL(&type9, t, next);
return;
diff --git a/hw/smbios/smbios_legacy.c b/hw/smbios/smbios_legacy.c
new file mode 100644
index 0000000..c37a8ee
--- /dev/null
+++ b/hw/smbios/smbios_legacy.c
@@ -0,0 +1,192 @@
+/*
+ * SMBIOS legacy support
+ *
+ * Copyright (C) 2009 Hewlett-Packard Development Company, L.P.
+ * Copyright (C) 2013 Red Hat, Inc.
+ *
+ * Authors:
+ * Alex Williamson <alex.williamson@hp.com>
+ * Markus Armbruster <armbru@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See
+ * the COPYING file in the top-level directory.
+ *
+ * Contributions after 2012-01-13 are licensed under the terms of the
+ * GNU GPL, version 2 or (at your option) any later version.
+ */
+
+#include "qemu/osdep.h"
+#include "qemu/bswap.h"
+#include "hw/firmware/smbios.h"
+#include "sysemu/sysemu.h"
+#include "qapi/error.h"
+
+struct smbios_header {
+ uint16_t length;
+ uint8_t type;
+} QEMU_PACKED;
+
+struct smbios_field {
+ struct smbios_header header;
+ uint8_t type;
+ uint16_t offset;
+ uint8_t data[];
+} QEMU_PACKED;
+
+struct smbios_table {
+ struct smbios_header header;
+ uint8_t data[];
+} QEMU_PACKED;
+
+#define SMBIOS_FIELD_ENTRY 0
+#define SMBIOS_TABLE_ENTRY 1
+
+static uint8_t *smbios_entries;
+static size_t smbios_entries_len;
+GArray *usr_blobs_sizes;
+
+void smbios_add_usr_blob_size(size_t size)
+{
+ if (!usr_blobs_sizes) {
+ usr_blobs_sizes = g_array_new(false, false, sizeof(size_t));
+ }
+ g_array_append_val(usr_blobs_sizes, size);
+}
+
+static void smbios_add_field(int type, int offset, const void *data, size_t len)
+{
+ struct smbios_field *field;
+
+ if (!smbios_entries) {
+ smbios_entries_len = sizeof(uint16_t);
+ smbios_entries = g_malloc0(smbios_entries_len);
+ }
+ smbios_entries = g_realloc(smbios_entries, smbios_entries_len +
+ sizeof(*field) + len);
+ field = (struct smbios_field *)(smbios_entries + smbios_entries_len);
+ field->header.type = SMBIOS_FIELD_ENTRY;
+ field->header.length = cpu_to_le16(sizeof(*field) + len);
+
+ field->type = type;
+ field->offset = cpu_to_le16(offset);
+ memcpy(field->data, data, len);
+
+ smbios_entries_len += sizeof(*field) + len;
+ (*(uint16_t *)smbios_entries) =
+ cpu_to_le16(le16_to_cpu(*(uint16_t *)smbios_entries) + 1);
+}
+
+static void smbios_maybe_add_str(int type, int offset, const char *data)
+{
+ if (data) {
+ smbios_add_field(type, offset, data, strlen(data) + 1);
+ }
+}
+
+static void smbios_build_type_0_fields(void)
+{
+ smbios_maybe_add_str(0, offsetof(struct smbios_type_0, vendor_str),
+ smbios_type0.vendor);
+ smbios_maybe_add_str(0, offsetof(struct smbios_type_0, bios_version_str),
+ smbios_type0.version);
+ smbios_maybe_add_str(0, offsetof(struct smbios_type_0,
+ bios_release_date_str),
+ smbios_type0.date);
+ if (smbios_type0.have_major_minor) {
+ smbios_add_field(0, offsetof(struct smbios_type_0,
+ system_bios_major_release),
+ &smbios_type0.major, 1);
+ smbios_add_field(0, offsetof(struct smbios_type_0,
+ system_bios_minor_release),
+ &smbios_type0.minor, 1);
+ }
+}
+
+static void smbios_build_type_1_fields(void)
+{
+ smbios_maybe_add_str(1, offsetof(struct smbios_type_1, manufacturer_str),
+ smbios_type1.manufacturer);
+ smbios_maybe_add_str(1, offsetof(struct smbios_type_1, product_name_str),
+ smbios_type1.product);
+ smbios_maybe_add_str(1, offsetof(struct smbios_type_1, version_str),
+ smbios_type1.version);
+ smbios_maybe_add_str(1, offsetof(struct smbios_type_1, serial_number_str),
+ smbios_type1.serial);
+ smbios_maybe_add_str(1, offsetof(struct smbios_type_1, sku_number_str),
+ smbios_type1.sku);
+ smbios_maybe_add_str(1, offsetof(struct smbios_type_1, family_str),
+ smbios_type1.family);
+ if (qemu_uuid_set) {
+ /*
+ * We don't encode the UUID in the "wire format" here because this
+ * function is for legacy mode and needs to keep the guest ABI, and
+ * because we don't know what's the SMBIOS version advertised by the
+ * BIOS.
+ */
+ smbios_add_field(1, offsetof(struct smbios_type_1, uuid),
+ &qemu_uuid, 16);
+ }
+}
+
+uint8_t *smbios_get_table_legacy(size_t *length, Error **errp)
+{
+ int i;
+ size_t usr_offset;
+
+ /* complain if fields were given for types > 1 */
+ if (find_next_bit(smbios_have_fields_bitmap,
+ SMBIOS_MAX_TYPE + 1, 2) < SMBIOS_MAX_TYPE + 1) {
+ error_setg(errp, "can't process fields for smbios "
+ "types > 1 on machine versions < 2.1!");
+ goto err_exit;
+ }
+
+ if (test_bit(4, smbios_have_binfile_bitmap)) {
+ error_setg(errp, "can't process table for smbios "
+ "type 4 on machine versions < 2.1!");
+ goto err_exit;
+ }
+
+ g_free(smbios_entries);
+ smbios_entries_len = sizeof(uint16_t);
+ smbios_entries = g_malloc0(smbios_entries_len);
+
+ /*
+ * build a set of legacy smbios_table entries using user provided blobs
+ */
+ for (i = 0, usr_offset = 0; usr_blobs_sizes && i < usr_blobs_sizes->len;
+ i++)
+ {
+ struct smbios_table *table;
+ struct smbios_structure_header *header;
+ size_t size = g_array_index(usr_blobs_sizes, size_t, i);
+
+ header = (struct smbios_structure_header *)(usr_blobs + usr_offset);
+ smbios_entries = g_realloc(smbios_entries, smbios_entries_len +
+ size + sizeof(*table));
+ table = (struct smbios_table *)(smbios_entries + smbios_entries_len);
+ table->header.type = SMBIOS_TABLE_ENTRY;
+ table->header.length = cpu_to_le16(sizeof(*table) + size);
+ memcpy(table->data, header, size);
+ smbios_entries_len += sizeof(*table) + size;
+ /*
+ * update number of entries in the blob,
+ * see SeaBIOS: qemu_cfg_legacy():QEMU_CFG_SMBIOS_ENTRIES
+ */
+ (*(uint16_t *)smbios_entries) =
+ cpu_to_le16(le16_to_cpu(*(uint16_t *)smbios_entries) + 1);
+ usr_offset += size;
+ }
+
+ smbios_build_type_0_fields();
+ smbios_build_type_1_fields();
+ if (!smbios_validate_table(SMBIOS_ENTRY_POINT_TYPE_32, errp)) {
+ goto err_exit;
+ }
+
+ *length = smbios_entries_len;
+ return smbios_entries;
+err_exit:
+ g_free(smbios_entries);
+ return NULL;
+}
diff --git a/hw/smbios/smbios_legacy_stub.c b/hw/smbios/smbios_legacy_stub.c
new file mode 100644
index 0000000..f29b153
--- /dev/null
+++ b/hw/smbios/smbios_legacy_stub.c
@@ -0,0 +1,15 @@
+/*
+ * IPMI SMBIOS firmware handling
+ *
+ * Copyright (c) 2024 Igor Mammedov, Red Hat, Inc.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+
+#include "qemu/osdep.h"
+#include "hw/firmware/smbios.h"
+
+void smbios_add_usr_blob_size(size_t size)
+{
+}
diff --git a/hw/ssi/aspeed_smc.c b/hw/ssi/aspeed_smc.c
index 3c93936..6e1a84c 100644
--- a/hw/ssi/aspeed_smc.c
+++ b/hw/ssi/aspeed_smc.c
@@ -23,6 +23,7 @@
*/
#include "qemu/osdep.h"
+#include "hw/block/flash.h"
#include "hw/sysbus.h"
#include "migration/vmstate.h"
#include "qemu/log.h"
@@ -695,6 +696,14 @@
for (i = 0; i < asc->cs_num_max; i++) {
DeviceState *dev = ssi_get_cs(s->spi, i);
if (dev) {
+ Object *o = OBJECT(dev);
+
+ if (!object_dynamic_cast(o, TYPE_M25P80)) {
+ warn_report("Aspeed SMC %s.%d : Invalid %s device type",
+ BUS(s->spi)->name, i, object_get_typename(o));
+ continue;
+ }
+
qemu_irq cs_line = qdev_get_gpio_in_named(dev, SSI_GPIO_CS, 0);
qdev_connect_gpio_out_named(DEVICE(s), "cs", i, cs_line);
}
diff --git a/hw/vfio/iommufd.c b/hw/vfio/iommufd.c
index bafddb8..8827ffe 100644
--- a/hw/vfio/iommufd.c
+++ b/hw/vfio/iommufd.c
@@ -118,10 +118,12 @@
{
ERRP_GUARD();
long int ret = -ENOTTY;
- char *path, *vfio_dev_path = NULL, *vfio_path = NULL;
+ g_autofree char *path = NULL;
+ g_autofree char *vfio_dev_path = NULL;
+ g_autofree char *vfio_path = NULL;
DIR *dir = NULL;
struct dirent *dent;
- gchar *contents;
+ g_autofree gchar *contents = NULL;
gsize length;
int major, minor;
dev_t vfio_devt;
@@ -130,7 +132,7 @@
dir = opendir(path);
if (!dir) {
error_setg_errno(errp, errno, "couldn't open directory %s", path);
- goto out_free_path;
+ goto out;
}
while ((dent = readdir(dir))) {
@@ -147,14 +149,13 @@
if (!g_file_get_contents(vfio_dev_path, &contents, &length, NULL)) {
error_setg(errp, "failed to load \"%s\"", vfio_dev_path);
- goto out_free_dev_path;
+ goto out_close_dir;
}
if (sscanf(contents, "%d:%d", &major, &minor) != 2) {
error_setg(errp, "failed to get major:minor for \"%s\"", vfio_dev_path);
- goto out_free_dev_path;
+ goto out_close_dir;
}
- g_free(contents);
vfio_devt = makedev(major, minor);
vfio_path = g_strdup_printf("/dev/vfio/devices/%s", dent->d_name);
@@ -164,17 +165,13 @@
}
trace_iommufd_cdev_getfd(vfio_path, ret);
- g_free(vfio_path);
-out_free_dev_path:
- g_free(vfio_dev_path);
out_close_dir:
closedir(dir);
-out_free_path:
+out:
if (*errp) {
error_prepend(errp, VFIO_MSG_PREFIX, path);
}
- g_free(path);
return ret;
}
diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h
index ce36bb1..3e53501 100644
--- a/include/exec/exec-all.h
+++ b/include/exec/exec-all.h
@@ -655,6 +655,7 @@
void tlb_reset_dirty(CPUState *cpu, ram_addr_t start1, ram_addr_t length);
void tlb_set_dirty(CPUState *cpu, vaddr addr);
+void tlb_reset_dirty_range_all(ram_addr_t start, ram_addr_t length);
MemoryRegionSection *
address_space_translate_for_iotlb(CPUState *cpu, int asidx, hwaddr addr,
diff --git a/include/exec/ram_addr.h b/include/exec/ram_addr.h
index 9067609..de45ba7 100644
--- a/include/exec/ram_addr.h
+++ b/include/exec/ram_addr.h
@@ -25,6 +25,7 @@
#include "sysemu/tcg.h"
#include "exec/ramlist.h"
#include "exec/ramblock.h"
+#include "exec/exec-all.h"
extern uint64_t total_dirty_pages;
@@ -443,6 +444,14 @@
}
#endif /* not _WIN32 */
+static inline void cpu_physical_memory_dirty_bits_cleared(ram_addr_t start,
+ ram_addr_t length)
+{
+ if (tcg_enabled()) {
+ tlb_reset_dirty_range_all(start, length);
+ }
+
+}
bool cpu_physical_memory_test_and_clear_dirty(ram_addr_t start,
ram_addr_t length,
unsigned client);
@@ -504,6 +513,9 @@
idx++;
}
}
+ if (num_dirty) {
+ cpu_physical_memory_dirty_bits_cleared(start, length);
+ }
if (rb->clear_bmap) {
/*
diff --git a/include/hw/block/flash.h b/include/hw/block/flash.h
index de93756..2b5ccd9 100644
--- a/include/hw/block/flash.h
+++ b/include/hw/block/flash.h
@@ -78,6 +78,8 @@
/* m25p80.c */
+#define TYPE_M25P80 "m25p80-generic"
+
BlockBackend *m25p80_get_blk(DeviceState *dev);
#endif
diff --git a/include/hw/firmware/smbios.h b/include/hw/firmware/smbios.h
index c21b8d3..8d3fb2f 100644
--- a/include/hw/firmware/smbios.h
+++ b/include/hw/firmware/smbios.h
@@ -2,6 +2,7 @@
#define QEMU_SMBIOS_H
#include "qapi/qapi-types-machine.h"
+#include "qemu/bitmap.h"
/*
* SMBIOS Support
@@ -16,8 +17,26 @@
*
*/
+extern uint8_t *usr_blobs;
+extern GArray *usr_blobs_sizes;
+
+typedef struct {
+ const char *vendor, *version, *date;
+ bool have_major_minor, uefi;
+ uint8_t major, minor;
+} smbios_type0_t;
+extern smbios_type0_t smbios_type0;
+
+typedef struct {
+ const char *manufacturer, *product, *version, *serial, *sku, *family;
+ /* uuid is in qemu_uuid */
+} smbios_type1_t;
+extern smbios_type1_t smbios_type1;
#define SMBIOS_MAX_TYPE 127
+extern DECLARE_BITMAP(smbios_have_binfile_bitmap, SMBIOS_MAX_TYPE + 1);
+extern DECLARE_BITMAP(smbios_have_fields_bitmap, SMBIOS_MAX_TYPE + 1);
+
#define offsetofend(TYPE, MEMBER) \
(offsetof(TYPE, MEMBER) + sizeof_field(TYPE, MEMBER))
@@ -307,14 +326,17 @@
struct smbios_structure_header header;
} QEMU_PACKED;
+bool smbios_validate_table(SmbiosEntryPointType ep_type, Error **errp);
+void smbios_add_usr_blob_size(size_t size);
void smbios_entry_add(QemuOpts *opts, Error **errp);
void smbios_set_cpuid(uint32_t version, uint32_t features);
void smbios_set_defaults(const char *manufacturer, const char *product,
- const char *version, bool legacy_mode,
- bool uuid_encoded, SmbiosEntryPointType ep_type);
+ const char *version,
+ bool uuid_encoded);
void smbios_set_default_processor_family(uint16_t processor_family);
-uint8_t *smbios_get_table_legacy(MachineState *ms, size_t *length);
+uint8_t *smbios_get_table_legacy(size_t *length, Error **errp);
void smbios_get_tables(MachineState *ms,
+ SmbiosEntryPointType ep_type,
const struct smbios_phys_mem_area *mem_array,
const unsigned int mem_array_size,
uint8_t **tables, size_t *tables_len,
diff --git a/include/io/channel-file.h b/include/io/channel-file.h
index 50e8eb1..d373a4e 100644
--- a/include/io/channel-file.h
+++ b/include/io/channel-file.h
@@ -69,6 +69,24 @@
qio_channel_file_new_fd(int fd);
/**
+ * qio_channel_file_new_dupfd:
+ * @fd: the file descriptor
+ * @errp: pointer to initialized error object
+ *
+ * Create a new IO channel object for a file represented by the @fd
+ * parameter. Like qio_channel_file_new_fd(), but the @fd is first
+ * duplicated with dup().
+ *
+ * The channel will own the duplicated file descriptor and will take
+ * responsibility for closing it, the original FD is owned by the
+ * caller.
+ *
+ * Returns: the new channel object
+ */
+QIOChannelFile *
+qio_channel_file_new_dupfd(int fd, Error **errp);
+
+/**
* qio_channel_file_new_path:
* @path: the file path
* @flags: the open flags (O_RDONLY|O_WRONLY|O_RDWR, etc)
diff --git a/include/qemu/job.h b/include/qemu/job.h
index 9ea98b5..2b873f2 100644
--- a/include/qemu/job.h
+++ b/include/qemu/job.h
@@ -483,7 +483,7 @@
*
* Called with job_mutex *not* held.
*/
-void coroutine_fn job_pause_point(Job *job);
+void coroutine_fn GRAPH_UNLOCKED job_pause_point(Job *job);
/**
* @job: The job that calls the function.
diff --git a/io/channel-file.c b/io/channel-file.c
index a6ad777..6436cfb 100644
--- a/io/channel-file.c
+++ b/io/channel-file.c
@@ -45,6 +45,18 @@
return ioc;
}
+QIOChannelFile *
+qio_channel_file_new_dupfd(int fd, Error **errp)
+{
+ int newfd = dup(fd);
+
+ if (newfd < 0) {
+ error_setg_errno(errp, errno, "Could not dup FD %d", fd);
+ return NULL;
+ }
+
+ return qio_channel_file_new_fd(newfd);
+}
QIOChannelFile *
qio_channel_file_new_path(const char *path,
diff --git a/migration/block.c b/migration/block.c
index 8c6ebaf..2b90548 100644
--- a/migration/block.c
+++ b/migration/block.c
@@ -402,7 +402,10 @@
}
sectors = bdrv_nb_sectors(bs);
- if (sectors <= 0) {
+ if (sectors == 0) {
+ continue;
+ }
+ if (sectors < 0) {
ret = sectors;
bdrv_next_cleanup(&it);
goto out;
diff --git a/migration/fd.c b/migration/fd.c
index d4ae72d..fe0d096 100644
--- a/migration/fd.c
+++ b/migration/fd.c
@@ -18,9 +18,11 @@
#include "qapi/error.h"
#include "channel.h"
#include "fd.h"
+#include "file.h"
#include "migration.h"
#include "monitor/monitor.h"
#include "io/channel-file.h"
+#include "io/channel-socket.h"
#include "io/channel-util.h"
#include "options.h"
#include "trace.h"
@@ -47,8 +49,7 @@
{
QIOChannel *ioc;
int fd = monitor_get_fd(monitor_cur(), fdname, errp);
-
- outgoing_args.fd = -1;
+ int newfd;
if (fd == -1) {
return;
@@ -61,7 +62,17 @@
return;
}
- outgoing_args.fd = fd;
+ /*
+ * This is dup()ed just to avoid referencing an fd that might
+ * be already closed by the iochannel.
+ */
+ newfd = dup(fd);
+ if (newfd == -1) {
+ error_setg_errno(errp, errno, "Could not dup FD %d", fd);
+ object_unref(ioc);
+ return;
+ }
+ outgoing_args.fd = newfd;
qio_channel_set_name(ioc, "migration-fd-outgoing");
migration_channel_connect(s, ioc, NULL, NULL);
@@ -93,28 +104,20 @@
return;
}
- qio_channel_set_name(ioc, "migration-fd-incoming");
- qio_channel_add_watch_full(ioc, G_IO_IN,
- fd_accept_incoming_migration,
- NULL, NULL,
- g_main_context_get_thread_default());
-
if (migrate_multifd()) {
- int channels = migrate_multifd_channels();
-
- while (channels--) {
- ioc = QIO_CHANNEL(qio_channel_file_new_fd(dup(fd)));
-
- if (QIO_CHANNEL_FILE(ioc)->fd == -1) {
- error_setg(errp, "Failed to duplicate fd %d", fd);
- return;
- }
-
- qio_channel_set_name(ioc, "migration-fd-incoming");
- qio_channel_add_watch_full(ioc, G_IO_IN,
- fd_accept_incoming_migration,
- NULL, NULL,
- g_main_context_get_thread_default());
+ if (fd_is_socket(fd)) {
+ error_setg(errp,
+ "Multifd migration to a socket FD is not supported");
+ object_unref(ioc);
+ return;
}
+
+ file_create_incoming_channels(ioc, errp);
+ } else {
+ qio_channel_set_name(ioc, "migration-fd-incoming");
+ qio_channel_add_watch_full(ioc, G_IO_IN,
+ fd_accept_incoming_migration,
+ NULL, NULL,
+ g_main_context_get_thread_default());
}
}
diff --git a/migration/file.c b/migration/file.c
index b0b963e..b6e8ba1 100644
--- a/migration/file.c
+++ b/migration/file.c
@@ -15,6 +15,7 @@
#include "file.h"
#include "migration.h"
#include "io/channel-file.h"
+#include "io/channel-socket.h"
#include "io/channel-util.h"
#include "options.h"
#include "trace.h"
@@ -58,12 +59,19 @@
int fd = fd_args_get_fd();
if (fd && fd != -1) {
- ioc = qio_channel_file_new_fd(dup(fd));
- } else {
- ioc = qio_channel_file_new_path(outgoing_args.fname, flags, 0, errp);
- if (!ioc) {
+ if (fd_is_socket(fd)) {
+ error_setg(errp,
+ "Multifd migration to a socket FD is not supported");
goto out;
}
+
+ ioc = qio_channel_file_new_dupfd(fd, errp);
+ } else {
+ ioc = qio_channel_file_new_path(outgoing_args.fname, flags, 0, errp);
+ }
+
+ if (!ioc) {
+ goto out;
}
multifd_channel_connect(opaque, QIO_CHANNEL(ioc));
@@ -114,13 +122,46 @@
return G_SOURCE_REMOVE;
}
+void file_create_incoming_channels(QIOChannel *ioc, Error **errp)
+{
+ int i, fd, channels = 1;
+ g_autofree QIOChannel **iocs = NULL;
+
+ if (migrate_multifd()) {
+ channels += migrate_multifd_channels();
+ }
+
+ iocs = g_new0(QIOChannel *, channels);
+ fd = QIO_CHANNEL_FILE(ioc)->fd;
+ iocs[0] = ioc;
+
+ for (i = 1; i < channels; i++) {
+ QIOChannelFile *fioc = qio_channel_file_new_dupfd(fd, errp);
+
+ if (!fioc) {
+ while (i) {
+ object_unref(iocs[--i]);
+ }
+ return;
+ }
+
+ iocs[i] = QIO_CHANNEL(fioc);
+ }
+
+ for (i = 0; i < channels; i++) {
+ qio_channel_set_name(iocs[i], "migration-file-incoming");
+ qio_channel_add_watch_full(iocs[i], G_IO_IN,
+ file_accept_incoming_migration,
+ NULL, NULL,
+ g_main_context_get_thread_default());
+ }
+}
+
void file_start_incoming_migration(FileMigrationArgs *file_args, Error **errp)
{
g_autofree char *filename = g_strdup(file_args->filename);
QIOChannelFile *fioc = NULL;
uint64_t offset = file_args->offset;
- int channels = 1;
- int i = 0;
trace_migration_file_incoming(filename);
@@ -131,29 +172,11 @@
if (offset &&
qio_channel_io_seek(QIO_CHANNEL(fioc), offset, SEEK_SET, errp) < 0) {
+ object_unref(OBJECT(fioc));
return;
}
- if (migrate_multifd()) {
- channels += migrate_multifd_channels();
- }
-
- do {
- QIOChannel *ioc = QIO_CHANNEL(fioc);
-
- qio_channel_set_name(ioc, "migration-file-incoming");
- qio_channel_add_watch_full(ioc, G_IO_IN,
- file_accept_incoming_migration,
- NULL, NULL,
- g_main_context_get_thread_default());
-
- fioc = qio_channel_file_new_fd(dup(fioc->fd));
-
- if (!fioc || fioc->fd == -1) {
- error_setg(errp, "Error creating migration incoming channel");
- break;
- }
- } while (++i < channels);
+ file_create_incoming_channels(QIO_CHANNEL(fioc), errp);
}
int file_write_ramblock_iov(QIOChannel *ioc, const struct iovec *iov,
diff --git a/migration/file.h b/migration/file.h
index 9f71e87..7699c04 100644
--- a/migration/file.h
+++ b/migration/file.h
@@ -20,6 +20,7 @@
int file_parse_offset(char *filespec, uint64_t *offsetp, Error **errp);
void file_cleanup_outgoing_migration(void);
bool file_send_channel_create(gpointer opaque, Error **errp);
+void file_create_incoming_channels(QIOChannel *ioc, Error **errp);
int file_write_ramblock_iov(QIOChannel *ioc, const struct iovec *iov,
int niov, RAMBlock *block, Error **errp);
int multifd_file_recv_data(MultiFDRecvParams *p, Error **errp);
diff --git a/migration/migration.c b/migration/migration.c
index 644e073..f60bd37 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -166,9 +166,9 @@
}
/*
- * At this point, the user might not yet have passed the file
- * descriptor to QEMU, so we cannot know for sure whether it
- * refers to a plain file or a socket. Let it through anyway.
+ * At this point QEMU has not yet fetched the fd passed in by the
+ * user, so we cannot know for sure whether it refers to a plain
+ * file or a socket. Let it through anyway and check at fd.c.
*/
if (addr->transport == MIGRATION_ADDRESS_TYPE_SOCKET) {
return addr->u.socket.type == SOCKET_ADDRESS_TYPE_FD;
diff --git a/nbd/server.c b/nbd/server.c
index 941832f..c3484cc 100644
--- a/nbd/server.c
+++ b/nbd/server.c
@@ -3007,8 +3007,8 @@
/* Owns a reference to the NBDClient passed as opaque. */
static coroutine_fn void nbd_trip(void *opaque)
{
- NBDClient *client = opaque;
- NBDRequestData *req = NULL;
+ NBDRequestData *req = opaque;
+ NBDClient *client = req->client;
NBDRequest request = { 0 }; /* GCC thinks it can be used uninitialized */
int ret;
Error *local_err = NULL;
@@ -3037,8 +3037,6 @@
goto done;
}
- req = nbd_request_get(client);
-
/*
* nbd_co_receive_request() returns -EAGAIN when nbd_drained_begin() has
* set client->quiescing but by the time we get back nbd_drained_end() may
@@ -3112,9 +3110,7 @@
}
done:
- if (req) {
- nbd_request_put(req);
- }
+ nbd_request_put(req);
qemu_mutex_unlock(&client->lock);
@@ -3143,10 +3139,13 @@
*/
static void nbd_client_receive_next_request(NBDClient *client)
{
+ NBDRequestData *req;
+
if (!client->recv_coroutine && client->nb_requests < MAX_NBD_REQUESTS &&
!client->quiescing) {
nbd_client_get(client);
- client->recv_coroutine = qemu_coroutine_create(nbd_trip, client);
+ req = nbd_request_get(client);
+ client->recv_coroutine = qemu_coroutine_create(nbd_trip, req);
aio_co_schedule(client->exp->common.ctx, client->recv_coroutine);
}
}
diff --git a/qapi/common.json b/qapi/common.json
index 867a9ad..7558ce5 100644
--- a/qapi/common.json
+++ b/qapi/common.json
@@ -107,9 +107,9 @@
#
# @16: 16.0GT/s
#
-# @32: 32.0GT/s
+# @32: 32.0GT/s (since 9.0)
#
-# @64: 64.0GT/s
+# @64: 64.0GT/s (since 9.0)
#
# Since: 4.0
##
diff --git a/qapi/machine.json b/qapi/machine.json
index bb5a178..0840c91 100644
--- a/qapi/machine.json
+++ b/qapi/machine.json
@@ -1797,10 +1797,13 @@
#
# @64: SMBIOS version 3.0 (64-bit) Entry Point
#
+# @auto: Either 2.x or 3.x SMBIOS version, 2.x if configuration can be
+# described by it and 3.x otherwise (since: 9.0)
+#
# Since: 7.0
##
{ 'enum': 'SmbiosEntryPointType',
- 'data': [ '32', '64' ] }
+ 'data': [ '32', '64', 'auto' ] }
##
# @MemorySizeConfiguration:
diff --git a/system/physmem.c b/system/physmem.c
index 6cfb7a8..a4fe3d2 100644
--- a/system/physmem.c
+++ b/system/physmem.c
@@ -819,7 +819,7 @@
return block;
}
-static void tlb_reset_dirty_range_all(ram_addr_t start, ram_addr_t length)
+void tlb_reset_dirty_range_all(ram_addr_t start, ram_addr_t length)
{
CPUState *cpu;
ram_addr_t start1;
@@ -881,8 +881,8 @@
memory_region_clear_dirty_bitmap(ramblock->mr, mr_offset, mr_size);
}
- if (dirty && tcg_enabled()) {
- tlb_reset_dirty_range_all(start, length);
+ if (dirty) {
+ cpu_physical_memory_dirty_bits_cleared(start, length);
}
return dirty;
@@ -929,9 +929,7 @@
}
}
- if (tcg_enabled()) {
- tlb_reset_dirty_range_all(start, length);
- }
+ cpu_physical_memory_dirty_bits_cleared(start, length);
memory_region_clear_dirty_bitmap(mr, offset, length);
diff --git a/system/qemu-seccomp.c b/system/qemu-seccomp.c
index 4d7439e..98ffce0 100644
--- a/system/qemu-seccomp.c
+++ b/system/qemu-seccomp.c
@@ -74,7 +74,7 @@
#define RULE_CLONE_FLAG(flag) \
{ SCMP_SYS(clone), QEMU_SECCOMP_SET_SPAWN, \
- ARRAY_SIZE(clone_arg ## flag), clone_arg ## flag, SCMP_ACT_TRAP }
+ ARRAY_SIZE(clone_arg ## flag), clone_arg ## flag, SCMP_ACT_ERRNO(EPERM) }
/* If no CLONE_* flags are set, except CSIGNAL, deny */
const struct scmp_arg_cmp clone_arg_none[] = {
@@ -214,13 +214,13 @@
0, NULL, SCMP_ACT_TRAP },
/* spawn */
{ SCMP_SYS(fork), QEMU_SECCOMP_SET_SPAWN,
- 0, NULL, SCMP_ACT_TRAP },
+ 0, NULL, SCMP_ACT_ERRNO(EPERM) },
{ SCMP_SYS(vfork), QEMU_SECCOMP_SET_SPAWN,
- 0, NULL, SCMP_ACT_TRAP },
+ 0, NULL, SCMP_ACT_ERRNO(EPERM) },
{ SCMP_SYS(execve), QEMU_SECCOMP_SET_SPAWN,
- 0, NULL, SCMP_ACT_TRAP },
+ 0, NULL, SCMP_ACT_ERRNO(EPERM) },
{ SCMP_SYS(clone), QEMU_SECCOMP_SET_SPAWN,
- ARRAY_SIZE(clone_arg_none), clone_arg_none, SCMP_ACT_TRAP },
+ ARRAY_SIZE(clone_arg_none), clone_arg_none, SCMP_ACT_ERRNO(EPERM) },
RULE_CLONE_FLAG(CLONE_VM),
RULE_CLONE_FLAG(CLONE_FS),
RULE_CLONE_FLAG(CLONE_FILES),
diff --git a/target/hppa/insns.decode b/target/hppa/insns.decode
index f5a3f02..f58455d 100644
--- a/target/hppa/insns.decode
+++ b/target/hppa/insns.decode
@@ -24,16 +24,17 @@
%assemble_sr3 13:1 14:2
%assemble_sr3x 13:1 14:2 !function=expand_sr3x
-%assemble_11a 0:s1 4:10 !function=expand_shl3
+%assemble_11a 4:12 0:1 !function=expand_11a
%assemble_12 0:s1 2:1 3:10 !function=expand_shl2
-%assemble_12a 0:s1 3:11 !function=expand_shl2
+%assemble_12a 3:13 0:1 !function=expand_12a
+%assemble_16 0:16 !function=expand_16
%assemble_17 0:s1 16:5 2:1 3:10 !function=expand_shl2
%assemble_22 0:s1 16:10 2:1 3:10 !function=expand_shl2
+%assemble_sp 14:2 !function=sp0_if_wide
%assemble_21 0:s1 1:11 14:2 16:5 12:2 !function=expand_shl11
%lowsign_11 0:s1 1:10
-%lowsign_14 0:s1 1:13
%sm_imm 16:10 !function=expand_sm_imm
@@ -143,9 +144,9 @@
nop 000001 ----- ----- -- 11001010 0 ----- # fdc, disp
nop_addrx 000001 ..... ..... -- 01001010 . ----- @addrx # fdc, index
nop_addrx 000001 ..... ..... -- 01001011 . ----- @addrx # fdce
-nop_addrx 000001 ..... ..... --- 0001010 . ----- @addrx # fic 0x0a
-nop_addrx 000001 ..... ..... -- 01001111 . 00000 @addrx # fic 0x4f
-nop_addrx 000001 ..... ..... --- 0001011 . ----- @addrx # fice
+fic 000001 ..... ..... --- 0001010 . ----- @addrx # fic 0x0a
+fic 000001 ..... ..... -- 01001111 . 00000 @addrx # fic 0x4f
+fic 000001 ..... ..... --- 0001011 . ----- @addrx # fice
nop_addrx 000001 ..... ..... -- 01001110 . 00000 @addrx # pdc
probe 000001 b:5 ri:5 sp:2 imm:1 100011 write:1 0 t:5
@@ -221,7 +222,7 @@
ldil 001000 t:5 ..................... i=%assemble_21
addil 001010 r:5 ..................... i=%assemble_21
-ldo 001101 b:5 t:5 -- .............. i=%lowsign_14
+ldo 001101 b:5 t:5 ................ i=%assemble_16
addi 101101 ..... ..... .... 0 ........... @rri_cf
addi_tsv 101101 ..... ..... .... 1 ........... @rri_cf
@@ -304,14 +305,18 @@
# Offset Mem
####
-@ldstim11 ...... b:5 t:5 sp:2 .............. \
- &ldst disp=%assemble_11a m=%ma2_to_m x=0 scale=0 size=3
-@ldstim14 ...... b:5 t:5 sp:2 .............. \
- &ldst disp=%lowsign_14 x=0 scale=0 m=0
-@ldstim14m ...... b:5 t:5 sp:2 .............. \
- &ldst disp=%lowsign_14 x=0 scale=0 m=%neg_to_m
-@ldstim12m ...... b:5 t:5 sp:2 .............. \
- &ldst disp=%assemble_12a x=0 scale=0 m=%pos_to_m
+@ldstim11 ...... b:5 t:5 ................ \
+ &ldst sp=%assemble_sp disp=%assemble_11a \
+ m=%ma2_to_m x=0 scale=0 size=3
+@ldstim14 ...... b:5 t:5 ................ \
+ &ldst sp=%assemble_sp disp=%assemble_16 \
+ x=0 scale=0 m=0
+@ldstim14m ...... b:5 t:5 ................ \
+ &ldst sp=%assemble_sp disp=%assemble_16 \
+ x=0 scale=0 m=%neg_to_m
+@ldstim12m ...... b:5 t:5 ................ \
+ &ldst sp=%assemble_sp disp=%assemble_12a \
+ x=0 scale=0 m=%pos_to_m
# LDB, LDH, LDW, LDWM
ld 010000 ..... ..... .. .............. @ldstim14 size=0
@@ -327,15 +332,19 @@
st 011011 ..... ..... .. .............. @ldstim14m size=2
st 011111 ..... ..... .. ...........10. @ldstim12m size=2
-fldw 010110 b:5 ..... sp:2 .............. \
- &ldst disp=%assemble_12a t=%rm64 m=%a_to_m x=0 scale=0 size=2
-fldw 010111 b:5 ..... sp:2 ...........0.. \
- &ldst disp=%assemble_12a t=%rm64 m=0 x=0 scale=0 size=2
+fldw 010110 b:5 ..... ................ \
+ &ldst disp=%assemble_12a sp=%assemble_sp \
+ t=%rm64 m=%a_to_m x=0 scale=0 size=2
+fldw 010111 b:5 ..... .............0.. \
+ &ldst disp=%assemble_12a sp=%assemble_sp \
+ t=%rm64 m=0 x=0 scale=0 size=2
-fstw 011110 b:5 ..... sp:2 .............. \
- &ldst disp=%assemble_12a t=%rm64 m=%a_to_m x=0 scale=0 size=2
-fstw 011111 b:5 ..... sp:2 ...........0.. \
- &ldst disp=%assemble_12a t=%rm64 m=0 x=0 scale=0 size=2
+fstw 011110 b:5 ..... ................ \
+ &ldst disp=%assemble_12a sp=%assemble_sp \
+ t=%rm64 m=%a_to_m x=0 scale=0 size=2
+fstw 011111 b:5 ..... .............0.. \
+ &ldst disp=%assemble_12a sp=%assemble_sp \
+ t=%rm64 m=0 x=0 scale=0 size=2
ld 010100 ..... ..... .. ............0. @ldstim11
fldd 010100 ..... ..... .. ............1. @ldstim11
diff --git a/target/hppa/mem_helper.c b/target/hppa/mem_helper.c
index 80f51e7..84785b5 100644
--- a/target/hppa/mem_helper.c
+++ b/target/hppa/mem_helper.c
@@ -152,6 +152,49 @@
return ent;
}
+#define ACCESS_ID_MASK 0xffff
+
+/* Return the set of protections allowed by a PID match. */
+static int match_prot_id_1(uint32_t access_id, uint32_t prot_id)
+{
+ if (((access_id ^ (prot_id >> 1)) & ACCESS_ID_MASK) == 0) {
+ return (prot_id & 1
+ ? PAGE_EXEC | PAGE_READ
+ : PAGE_EXEC | PAGE_READ | PAGE_WRITE);
+ }
+ return 0;
+}
+
+static int match_prot_id32(CPUHPPAState *env, uint32_t access_id)
+{
+ int r, i;
+
+ for (i = CR_PID1; i <= CR_PID4; ++i) {
+ r = match_prot_id_1(access_id, env->cr[i]);
+ if (r) {
+ return r;
+ }
+ }
+ return 0;
+}
+
+static int match_prot_id64(CPUHPPAState *env, uint32_t access_id)
+{
+ int r, i;
+
+ for (i = CR_PID1; i <= CR_PID4; ++i) {
+ r = match_prot_id_1(access_id, env->cr[i]);
+ if (r) {
+ return r;
+ }
+ r = match_prot_id_1(access_id, env->cr[i] >> 32);
+ if (r) {
+ return r;
+ }
+ }
+ return 0;
+}
+
int hppa_get_physical_address(CPUHPPAState *env, vaddr addr, int mmu_idx,
int type, hwaddr *pphys, int *pprot,
HPPATLBEntry **tlb_entry)
@@ -224,29 +267,30 @@
break;
}
- /* access_id == 0 means public page and no check is performed */
- if (ent->access_id && MMU_IDX_TO_P(mmu_idx)) {
- /* If bits [31:1] match, and bit 0 is set, suppress write. */
- int match = ent->access_id * 2 + 1;
-
- if (match == env->cr[CR_PID1] || match == env->cr[CR_PID2] ||
- match == env->cr[CR_PID3] || match == env->cr[CR_PID4]) {
- prot &= PAGE_READ | PAGE_EXEC;
- if (type == PAGE_WRITE) {
- ret = EXCP_DMPI;
- goto egress;
- }
- }
- }
-
- /* No guest access type indicates a non-architectural access from
- within QEMU. Bypass checks for access, D, B and T bits. */
+ /*
+ * No guest access type indicates a non-architectural access from
+ * within QEMU. Bypass checks for access, D, B, P and T bits.
+ */
if (type == 0) {
goto egress;
}
+ /* access_id == 0 means public page and no check is performed */
+ if (ent->access_id && MMU_IDX_TO_P(mmu_idx)) {
+ int access_prot = (hppa_is_pa20(env)
+ ? match_prot_id64(env, ent->access_id)
+ : match_prot_id32(env, ent->access_id));
+ if (unlikely(!(type & access_prot))) {
+ /* Not allowed -- Inst/Data Memory Protection Id Fault. */
+ ret = type & PAGE_EXEC ? EXCP_IMP : EXCP_DMPI;
+ goto egress;
+ }
+ /* Otherwise exclude permissions not allowed (i.e WD). */
+ prot &= access_prot;
+ }
+
if (unlikely(!(prot & type))) {
- /* The access isn't allowed -- Inst/Data Memory Protection Fault. */
+ /* Not allowed -- Inst/Data Memory Access Rights Fault. */
ret = (type & PAGE_EXEC) ? EXCP_IMP : EXCP_DMAR;
goto egress;
}
diff --git a/target/hppa/op_helper.c b/target/hppa/op_helper.c
index 480fe80..6cf49f3 100644
--- a/target/hppa/op_helper.c
+++ b/target/hppa/op_helper.c
@@ -281,17 +281,17 @@
case 3:
/* The 3 byte store must appear atomic. */
if (parallel) {
- atomic_store_mask32(env, addr - 3, val, 0xffffff00u, ra);
+ atomic_store_mask32(env, addr - 3, val >> 32, 0xffffff00u, ra);
} else {
- cpu_stw_data_ra(env, addr - 3, val >> 16, ra);
- cpu_stb_data_ra(env, addr - 1, val >> 8, ra);
+ cpu_stw_data_ra(env, addr - 3, val >> 48, ra);
+ cpu_stb_data_ra(env, addr - 1, val >> 40, ra);
}
break;
case 2:
- cpu_stw_data_ra(env, addr - 2, val >> 16, ra);
+ cpu_stw_data_ra(env, addr - 2, val >> 48, ra);
break;
case 1:
- cpu_stb_data_ra(env, addr - 1, val >> 24, ra);
+ cpu_stb_data_ra(env, addr - 1, val >> 56, ra);
break;
default:
/* Nothing is stored, but protection is checked and the
diff --git a/target/hppa/translate.c b/target/hppa/translate.c
index eb2046c..19594f9 100644
--- a/target/hppa/translate.c
+++ b/target/hppa/translate.c
@@ -121,12 +121,6 @@
return val << 2;
}
-/* Used for fp memory ops. */
-static int expand_shl3(DisasContext *ctx, int val)
-{
- return val << 3;
-}
-
/* Used for assemble_21. */
static int expand_shl11(DisasContext *ctx, int val)
{
@@ -144,6 +138,62 @@
return (val ^ 31) + 1;
}
+/* Expander for assemble_16a(s,cat(im10a,0),i). */
+static int expand_11a(DisasContext *ctx, int val)
+{
+ /*
+ * @val is bit 0 and bits [4:15].
+ * Swizzle thing around depending on PSW.W.
+ */
+ int im10a = extract32(val, 1, 10);
+ int s = extract32(val, 11, 2);
+ int i = (-(val & 1) << 13) | (im10a << 3);
+
+ if (ctx->tb_flags & PSW_W) {
+ i ^= s << 13;
+ }
+ return i;
+}
+
+/* Expander for assemble_16a(s,im11a,i). */
+static int expand_12a(DisasContext *ctx, int val)
+{
+ /*
+ * @val is bit 0 and bits [3:15].
+ * Swizzle thing around depending on PSW.W.
+ */
+ int im11a = extract32(val, 1, 11);
+ int s = extract32(val, 12, 2);
+ int i = (-(val & 1) << 13) | (im11a << 2);
+
+ if (ctx->tb_flags & PSW_W) {
+ i ^= s << 13;
+ }
+ return i;
+}
+
+/* Expander for assemble_16(s,im14). */
+static int expand_16(DisasContext *ctx, int val)
+{
+ /*
+ * @val is bits [0:15], containing both im14 and s.
+ * Swizzle thing around depending on PSW.W.
+ */
+ int s = extract32(val, 14, 2);
+ int i = (-(val & 1) << 13) | extract32(val, 1, 13);
+
+ if (ctx->tb_flags & PSW_W) {
+ i ^= s << 13;
+ }
+ return i;
+}
+
+/* The sp field is only present with !PSW_W. */
+static int sp0_if_wide(DisasContext *ctx, int sp)
+{
+ return ctx->tb_flags & PSW_W ? 0 : sp;
+}
+
/* Translate CMPI doubleword conditions to standard. */
static int cmpbid_c(DisasContext *ctx, int val)
{
@@ -1961,7 +2011,7 @@
{
unsigned rt = a->t;
TCGv_i64 tmp = dest_gpr(ctx, rt);
- tcg_gen_movi_i64(tmp, ctx->iaoq_f);
+ tcg_gen_movi_i64(tmp, ctx->iaoq_f & ~3ULL);
save_gpr(ctx, rt, tmp);
cond_free(&ctx->null_cond);
@@ -2293,6 +2343,13 @@
return true;
}
+static bool trans_fic(DisasContext *ctx, arg_ldst *a)
+{
+ /* End TB for flush instruction cache, so we pick up new insns. */
+ ctx->base.is_jmp = DISAS_IAQ_N_STALE;
+ return trans_nop_addrx(ctx, a);
+}
+
static bool trans_probe(DisasContext *ctx, arg_probe *a)
{
TCGv_i64 dest, ofs;
@@ -3085,7 +3142,7 @@
dest = dest_gpr(ctx, a->t);
}
- form_gva(ctx, &addr, &ofs, a->b, a->x, a->scale ? a->size : 0,
+ form_gva(ctx, &addr, &ofs, a->b, a->x, a->scale ? 3 : 0,
a->disp, a->sp, a->m, MMU_DISABLED(ctx));
/*
@@ -3462,7 +3519,7 @@
/* Install the new nullification. */
cond_free(&ctx->null_cond);
if (a->c) {
- ctx->null_cond = do_sed_cond(ctx, a->c, false, dest);
+ ctx->null_cond = do_sed_cond(ctx, a->c, a->d, dest);
}
return nullify_end(ctx);
}
@@ -3505,7 +3562,7 @@
/* Install the new nullification. */
cond_free(&ctx->null_cond);
if (a->c) {
- ctx->null_cond = do_sed_cond(ctx, a->c, false, dest);
+ ctx->null_cond = do_sed_cond(ctx, a->c, a->d, dest);
}
return nullify_end(ctx);
}
diff --git a/target/loongarch/cpu-csr.h b/target/loongarch/cpu-csr.h
index c59d7a9..0834e91 100644
--- a/target/loongarch/cpu-csr.h
+++ b/target/loongarch/cpu-csr.h
@@ -67,6 +67,9 @@
FIELD(TLBENTRY, PLV, 2, 2)
FIELD(TLBENTRY, MAT, 4, 2)
FIELD(TLBENTRY, G, 6, 1)
+FIELD(TLBENTRY, HUGE, 6, 1)
+FIELD(TLBENTRY, HGLOBAL, 12, 1)
+FIELD(TLBENTRY, LEVEL, 13, 2)
FIELD(TLBENTRY_32, PPN, 8, 24)
FIELD(TLBENTRY_64, PPN, 12, 36)
FIELD(TLBENTRY_64, NR, 61, 1)
diff --git a/target/loongarch/internals.h b/target/loongarch/internals.h
index a2fc54c..944153b 100644
--- a/target/loongarch/internals.h
+++ b/target/loongarch/internals.h
@@ -16,11 +16,6 @@
#define TARGET_PHYS_MASK MAKE_64BIT_MASK(0, TARGET_PHYS_ADDR_SPACE_BITS)
#define TARGET_VIRT_MASK MAKE_64BIT_MASK(0, TARGET_VIRT_ADDR_SPACE_BITS)
-/* Global bit used for lddir/ldpte */
-#define LOONGARCH_PAGE_HUGE_SHIFT 6
-/* Global bit for huge page */
-#define LOONGARCH_HGLOBAL_SHIFT 12
-
void loongarch_translate_init(void);
void loongarch_cpu_dump_state(CPUState *cpu, FILE *f, int flags);
diff --git a/target/loongarch/tcg/insn_trans/trans_atomic.c.inc b/target/loongarch/tcg/insn_trans/trans_atomic.c.inc
index 80c2e28..974bc2a 100644
--- a/target/loongarch/tcg/insn_trans/trans_atomic.c.inc
+++ b/target/loongarch/tcg/insn_trans/trans_atomic.c.inc
@@ -5,14 +5,14 @@
static bool gen_ll(DisasContext *ctx, arg_rr_i *a, MemOp mop)
{
- TCGv dest = gpr_dst(ctx, a->rd, EXT_NONE);
+ TCGv t1 = tcg_temp_new();
TCGv src1 = gpr_src(ctx, a->rj, EXT_NONE);
TCGv t0 = make_address_i(ctx, src1, a->imm);
- tcg_gen_qemu_ld_i64(dest, t0, ctx->mem_idx, mop);
+ tcg_gen_qemu_ld_i64(t1, t0, ctx->mem_idx, mop);
tcg_gen_st_tl(t0, tcg_env, offsetof(CPULoongArchState, lladdr));
- tcg_gen_st_tl(dest, tcg_env, offsetof(CPULoongArchState, llval));
- gen_set_gpr(a->rd, dest, EXT_NONE);
+ tcg_gen_st_tl(t1, tcg_env, offsetof(CPULoongArchState, llval));
+ gen_set_gpr(a->rd, t1, EXT_NONE);
return true;
}
diff --git a/target/loongarch/tcg/tlb_helper.c b/target/loongarch/tcg/tlb_helper.c
index 22be031..57f5308 100644
--- a/target/loongarch/tcg/tlb_helper.c
+++ b/target/loongarch/tcg/tlb_helper.c
@@ -17,6 +17,34 @@
#include "exec/log.h"
#include "cpu-csr.h"
+static void get_dir_base_width(CPULoongArchState *env, uint64_t *dir_base,
+ uint64_t *dir_width, target_ulong level)
+{
+ switch (level) {
+ case 1:
+ *dir_base = FIELD_EX64(env->CSR_PWCL, CSR_PWCL, DIR1_BASE);
+ *dir_width = FIELD_EX64(env->CSR_PWCL, CSR_PWCL, DIR1_WIDTH);
+ break;
+ case 2:
+ *dir_base = FIELD_EX64(env->CSR_PWCL, CSR_PWCL, DIR2_BASE);
+ *dir_width = FIELD_EX64(env->CSR_PWCL, CSR_PWCL, DIR2_WIDTH);
+ break;
+ case 3:
+ *dir_base = FIELD_EX64(env->CSR_PWCH, CSR_PWCH, DIR3_BASE);
+ *dir_width = FIELD_EX64(env->CSR_PWCH, CSR_PWCH, DIR3_WIDTH);
+ break;
+ case 4:
+ *dir_base = FIELD_EX64(env->CSR_PWCH, CSR_PWCH, DIR4_BASE);
+ *dir_width = FIELD_EX64(env->CSR_PWCH, CSR_PWCH, DIR4_WIDTH);
+ break;
+ default:
+ /* level may be zero for ldpte */
+ *dir_base = FIELD_EX64(env->CSR_PWCL, CSR_PWCL, PTBASE);
+ *dir_width = FIELD_EX64(env->CSR_PWCL, CSR_PWCL, PTWIDTH);
+ break;
+ }
+}
+
static void raise_mmu_exception(CPULoongArchState *env, target_ulong address,
MMUAccessType access_type, int tlb_error)
{
@@ -485,7 +513,25 @@
target_ulong badvaddr, index, phys, ret;
int shift;
uint64_t dir_base, dir_width;
- bool huge = (base >> LOONGARCH_PAGE_HUGE_SHIFT) & 0x1;
+
+ if (unlikely((level == 0) || (level > 4))) {
+ qemu_log_mask(LOG_GUEST_ERROR,
+ "Attepted LDDIR with level %"PRId64"\n", level);
+ return base;
+ }
+
+ if (FIELD_EX64(base, TLBENTRY, HUGE)) {
+ if (unlikely(level == 4)) {
+ qemu_log_mask(LOG_GUEST_ERROR,
+ "Attempted use of level 4 huge page\n");
+ }
+
+ if (FIELD_EX64(base, TLBENTRY, LEVEL)) {
+ return base;
+ } else {
+ return FIELD_DP64(base, TLBENTRY, LEVEL, level);
+ }
+ }
badvaddr = env->CSR_TLBRBADV;
base = base & TARGET_PHYS_MASK;
@@ -494,30 +540,7 @@
shift = FIELD_EX64(env->CSR_PWCL, CSR_PWCL, PTEWIDTH);
shift = (shift + 1) * 3;
- if (huge) {
- return base;
- }
- switch (level) {
- case 1:
- dir_base = FIELD_EX64(env->CSR_PWCL, CSR_PWCL, DIR1_BASE);
- dir_width = FIELD_EX64(env->CSR_PWCL, CSR_PWCL, DIR1_WIDTH);
- break;
- case 2:
- dir_base = FIELD_EX64(env->CSR_PWCL, CSR_PWCL, DIR2_BASE);
- dir_width = FIELD_EX64(env->CSR_PWCL, CSR_PWCL, DIR2_WIDTH);
- break;
- case 3:
- dir_base = FIELD_EX64(env->CSR_PWCH, CSR_PWCH, DIR3_BASE);
- dir_width = FIELD_EX64(env->CSR_PWCH, CSR_PWCH, DIR3_WIDTH);
- break;
- case 4:
- dir_base = FIELD_EX64(env->CSR_PWCH, CSR_PWCH, DIR4_BASE);
- dir_width = FIELD_EX64(env->CSR_PWCH, CSR_PWCH, DIR4_WIDTH);
- break;
- default:
- do_raise_exception(env, EXCCODE_INE, GETPC());
- return 0;
- }
+ get_dir_base_width(env, &dir_base, &dir_width, level);
index = (badvaddr >> dir_base) & ((1 << dir_width) - 1);
phys = base | index << shift;
ret = ldq_phys(cs->as, phys) & TARGET_PHYS_MASK;
@@ -530,20 +553,42 @@
CPUState *cs = env_cpu(env);
target_ulong phys, tmp0, ptindex, ptoffset0, ptoffset1, ps, badv;
int shift;
- bool huge = (base >> LOONGARCH_PAGE_HUGE_SHIFT) & 0x1;
uint64_t ptbase = FIELD_EX64(env->CSR_PWCL, CSR_PWCL, PTBASE);
uint64_t ptwidth = FIELD_EX64(env->CSR_PWCL, CSR_PWCL, PTWIDTH);
+ uint64_t dir_base, dir_width;
+ /*
+ * The parameter "base" has only two types,
+ * one is the page table base address,
+ * whose bit 6 should be 0,
+ * and the other is the huge page entry,
+ * whose bit 6 should be 1.
+ */
base = base & TARGET_PHYS_MASK;
+ if (FIELD_EX64(base, TLBENTRY, HUGE)) {
+ /*
+ * Gets the huge page level and Gets huge page size.
+ * Clears the huge page level information in the entry.
+ * Clears huge page bit.
+ * Move HGLOBAL bit to GLOBAL bit.
+ */
+ get_dir_base_width(env, &dir_base, &dir_width,
+ FIELD_EX64(base, TLBENTRY, LEVEL));
- if (huge) {
- /* Huge Page. base is paddr */
- tmp0 = base ^ (1 << LOONGARCH_PAGE_HUGE_SHIFT);
- /* Move Global bit */
- tmp0 = ((tmp0 & (1 << LOONGARCH_HGLOBAL_SHIFT)) >>
- LOONGARCH_HGLOBAL_SHIFT) << R_TLBENTRY_G_SHIFT |
- (tmp0 & (~(1 << LOONGARCH_HGLOBAL_SHIFT)));
- ps = ptbase + ptwidth - 1;
+ base = FIELD_DP64(base, TLBENTRY, LEVEL, 0);
+ base = FIELD_DP64(base, TLBENTRY, HUGE, 0);
+ if (FIELD_EX64(base, TLBENTRY, HGLOBAL)) {
+ base = FIELD_DP64(base, TLBENTRY, HGLOBAL, 0);
+ base = FIELD_DP64(base, TLBENTRY, G, 1);
+ }
+
+ ps = dir_base + dir_width - 1;
+ /*
+ * Huge pages are evenly split into parity pages
+ * when loaded into the tlb,
+ * so the tlb page size needs to be divided by 2.
+ */
+ tmp0 = base;
if (odd) {
tmp0 += MAKE_64BIT_MASK(ps, 1);
}
diff --git a/target/s390x/cpu_models.c b/target/s390x/cpu_models.c
index 1a1c096..8ed3bb6 100644
--- a/target/s390x/cpu_models.c
+++ b/target/s390x/cpu_models.c
@@ -500,6 +500,16 @@
error_prepend((Error **) opaque, "%s ", name);
}
+static void check_compat_model_failed(Error **errp,
+ const S390CPUModel *max_model,
+ const char *msg)
+{
+ error_setg(errp, "%s. Maximum supported model in the current configuration: \'%s\'",
+ msg, max_model->def->name);
+ error_append_hint(errp, "Consider a different accelerator, try \"-accel help\"\n");
+ return;
+}
+
static void check_compatibility(const S390CPUModel *max_model,
const S390CPUModel *model, Error **errp)
{
@@ -507,15 +517,11 @@
S390FeatBitmap missing;
if (model->def->gen > max_model->def->gen) {
- error_setg(errp, "Selected CPU generation is too new. Maximum "
- "supported model in the configuration: \'%s\'",
- max_model->def->name);
+ check_compat_model_failed(errp, max_model, "Selected CPU generation is too new");
return;
} else if (model->def->gen == max_model->def->gen &&
model->def->ec_ga > max_model->def->ec_ga) {
- error_setg(errp, "Selected CPU GA level is too new. Maximum "
- "supported model in the configuration: \'%s\'",
- max_model->def->name);
+ check_compat_model_failed(errp, max_model, "Selected CPU GA level is too new");
return;
}
@@ -537,7 +543,9 @@
error_setg(errp, " ");
s390_feat_bitmap_to_ascii(missing, errp, error_prepend_missing_feat);
error_prepend(errp, "Some features requested in the CPU model are not "
- "available in the configuration: ");
+ "available in the current configuration: ");
+ error_append_hint(errp,
+ "Consider a different accelerator, QEMU, or kernel version\n");
}
S390CPUModel *get_max_cpu_model(Error **errp)
diff --git a/target/sparc/cpu.c b/target/sparc/cpu.c
index dc9ead2..e820f50 100644
--- a/target/sparc/cpu.c
+++ b/target/sparc/cpu.c
@@ -574,9 +574,10 @@
{
unsigned int i;
+ qemu_printf("Available CPU types:\n");
for (i = 0; i < ARRAY_SIZE(sparc_defs); i++) {
- qemu_printf("Sparc %16s IU " TARGET_FMT_lx
- " FPU %08x MMU %08x NWINS %d ",
+ qemu_printf(" %-20s (IU " TARGET_FMT_lx
+ " FPU %08x MMU %08x NWINS %d) ",
sparc_defs[i].name,
sparc_defs[i].iu_version,
sparc_defs[i].fpu_version,
diff --git a/tests/data/acpi/q35/SSDT.dimmpxm b/tests/data/acpi/q35/SSDT.dimmpxm
index 70f1334..9ea4e0d 100644
--- a/tests/data/acpi/q35/SSDT.dimmpxm
+++ b/tests/data/acpi/q35/SSDT.dimmpxm
Binary files differ
diff --git a/tests/data/smbios/type11_blob b/tests/data/smbios/type11_blob
new file mode 100644
index 0000000..1d8fea4
--- /dev/null
+++ b/tests/data/smbios/type11_blob
Binary files differ
diff --git a/tests/data/smbios/type11_blob.legacy b/tests/data/smbios/type11_blob.legacy
new file mode 100644
index 0000000..aef463a
--- /dev/null
+++ b/tests/data/smbios/type11_blob.legacy
Binary files differ
diff --git a/tests/qemu-iotests/033 b/tests/qemu-iotests/033
index da9133c..4bc7a07 100755
--- a/tests/qemu-iotests/033
+++ b/tests/qemu-iotests/033
@@ -123,9 +123,9 @@
# next L2 table
do_test 512 "write -P 1 $L2_COVERAGE 0x200" "$TEST_IMG" | _filter_qemu_io
-# only interested in qcow2 here; also other formats might respond with
-# "not supported" error message
-if [ $IMGFMT = "qcow2" ]; then
+# only interested in qcow2 with file protocol here; also other formats
+# might respond with "not supported" error message
+if [ $IMGFMT = "qcow2" ] && [ $IMGPROTO = "file" ]; then
do_test 512 "truncate $L2_COVERAGE" "$TEST_IMG" | _filter_qemu_io
fi
diff --git a/tests/qemu-iotests/066 b/tests/qemu-iotests/066
index cf63144..336d856 100755
--- a/tests/qemu-iotests/066
+++ b/tests/qemu-iotests/066
@@ -39,7 +39,7 @@
# This tests qcow2-specific low-level functionality
_supported_fmt qcow2
-_supported_proto generic
+_supported_proto file
# We need zero clusters and snapshots
# (TODO: Consider splitting the snapshot part into a separate test
# file, so this one runs with refcount_bits=1 and data_file)
diff --git a/tests/qemu-iotests/114 b/tests/qemu-iotests/114
index de6fd32..dccc710 100755
--- a/tests/qemu-iotests/114
+++ b/tests/qemu-iotests/114
@@ -38,7 +38,7 @@
. ./common.filter
_supported_fmt qcow2
-_supported_proto generic
+_supported_proto file
# At least OpenBSD doesn't seem to have truncate
_supported_os Linux
# qcow2.py does not work too well with external data files
diff --git a/tests/qemu-iotests/130 b/tests/qemu-iotests/130
index 7257f09..7af85d2 100755
--- a/tests/qemu-iotests/130
+++ b/tests/qemu-iotests/130
@@ -42,7 +42,7 @@
. ./common.qemu
_supported_fmt qcow2
-_supported_proto generic
+_supported_proto file
_supported_os Linux
# We are going to use lazy-refcounts
_unsupported_imgopts 'compat=0.10'
diff --git a/tests/qemu-iotests/134 b/tests/qemu-iotests/134
index ded153c..b2c3c03 100755
--- a/tests/qemu-iotests/134
+++ b/tests/qemu-iotests/134
@@ -38,7 +38,7 @@
. ./common.filter
_supported_fmt qcow qcow2
-_supported_proto generic
+_supported_proto file
size=128M
diff --git a/tests/qemu-iotests/156 b/tests/qemu-iotests/156
index a9540bd..97c2d86 100755
--- a/tests/qemu-iotests/156
+++ b/tests/qemu-iotests/156
@@ -50,7 +50,7 @@
. ./common.qemu
_supported_fmt qcow2 qed
-_supported_proto generic
+_supported_proto file
# Copying files around with cp does not work with external data files
_unsupported_imgopts data_file
diff --git a/tests/qemu-iotests/158 b/tests/qemu-iotests/158
index a95878e..3a9ad7e 100755
--- a/tests/qemu-iotests/158
+++ b/tests/qemu-iotests/158
@@ -38,7 +38,7 @@
. ./common.filter
_supported_fmt qcow qcow2
-_supported_proto generic
+_supported_proto file
size=128M
diff --git a/tests/qemu-iotests/176.out b/tests/qemu-iotests/176.out
index 45e9153..9c73ef2 100644
--- a/tests/qemu-iotests/176.out
+++ b/tests/qemu-iotests/176.out
@@ -37,8 +37,8 @@
0x7ffe0000 0x20000 TEST_DIR/t.IMGFMT.itmd
0x83400000 0x200 TEST_DIR/t.IMGFMT.itmd
Snapshot list:
-ID TAG
-1 snap
+ID TAG
+1 snap
=== Test pass snapshot.1 ===
@@ -78,8 +78,8 @@
0x7fff0000 0x10000 TEST_DIR/t.IMGFMT
0x83400000 0x200 TEST_DIR/t.IMGFMT
Snapshot list:
-ID TAG
-1 snap
+ID TAG
+1 snap
=== Test pass snapshot.2 ===
@@ -119,8 +119,8 @@
0x7fff0000 0x10000 TEST_DIR/t.IMGFMT
0x83400000 0x200 TEST_DIR/t.IMGFMT
Snapshot list:
-ID TAG
-1 snap
+ID TAG
+1 snap
=== Test pass snapshot.3 ===
@@ -157,8 +157,8 @@
0x7fff0000 0x10000 TEST_DIR/t.IMGFMT
0x83400000 0x200 TEST_DIR/t.IMGFMT
Snapshot list:
-ID TAG
-1 snap
+ID TAG
+1 snap
=== Test pass bitmap.0 ===
diff --git a/tests/qemu-iotests/188 b/tests/qemu-iotests/188
index ce087d1..2950b1d 100755
--- a/tests/qemu-iotests/188
+++ b/tests/qemu-iotests/188
@@ -38,7 +38,7 @@
. ./common.filter
_supported_fmt qcow2
-_supported_proto generic
+_supported_proto file
_supported_os Linux
_require_working_luks
diff --git a/tests/qemu-iotests/189 b/tests/qemu-iotests/189
index 801494c..008f73b 100755
--- a/tests/qemu-iotests/189
+++ b/tests/qemu-iotests/189
@@ -38,7 +38,7 @@
. ./common.filter
_supported_fmt qcow2
-_supported_proto generic
+_supported_proto file
_supported_os Linux
_require_working_luks
diff --git a/tests/qemu-iotests/198 b/tests/qemu-iotests/198
index 1c93dea..6ddeffd 100755
--- a/tests/qemu-iotests/198
+++ b/tests/qemu-iotests/198
@@ -38,7 +38,7 @@
. ./common.filter
_supported_fmt qcow2
-_supported_proto generic
+_supported_proto file
_supported_os Linux
_require_working_luks
diff --git a/tests/qemu-iotests/198.out b/tests/qemu-iotests/198.out
index 8054949..62fb73f 100644
--- a/tests/qemu-iotests/198.out
+++ b/tests/qemu-iotests/198.out
@@ -39,6 +39,7 @@
compression type: COMPRESSION_TYPE
encrypt:
ivgen alg: plain64
+ detached header: false
hash alg: sha256
cipher alg: aes-256
uuid: 00000000-0000-0000-0000-000000000000
@@ -84,6 +85,7 @@
compression type: COMPRESSION_TYPE
encrypt:
ivgen alg: plain64
+ detached header: false
hash alg: sha256
cipher alg: aes-256
uuid: 00000000-0000-0000-0000-000000000000
diff --git a/tests/qemu-iotests/206.out b/tests/qemu-iotests/206.out
index 7e95694..979f00f 100644
--- a/tests/qemu-iotests/206.out
+++ b/tests/qemu-iotests/206.out
@@ -114,6 +114,7 @@
refcount bits: 16
encrypt:
ivgen alg: plain64
+ detached header: false
hash alg: sha1
cipher alg: aes-128
uuid: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX
diff --git a/tests/qemu-iotests/261 b/tests/qemu-iotests/261
index b73da56..22b969d 100755
--- a/tests/qemu-iotests/261
+++ b/tests/qemu-iotests/261
@@ -393,7 +393,7 @@
echo
echo "$((sn_count - 1)) snapshots should remain:"
-echo " qemu-img info reports $(_img_info | grep -c '^ \{32\}') snapshots"
+echo " qemu-img info reports $(_img_info | grep -c '^ \{30\}') snapshots"
echo " Image header reports $(peek_file_be "$TEST_IMG" 60 4) snapshots"
echo
@@ -520,7 +520,7 @@
echo
echo '65536 snapshots should remain:'
-echo " qemu-img info reports $(_img_info | grep -c '^ \{32\}') snapshots"
+echo " qemu-img info reports $(_img_info | grep -c '^ \{30\}') snapshots"
echo " Image header reports $(peek_file_be "$TEST_IMG" 60 4) snapshots"
# success, all done
diff --git a/tests/qemu-iotests/263 b/tests/qemu-iotests/263
index ec09b41..44fdada 100755
--- a/tests/qemu-iotests/263
+++ b/tests/qemu-iotests/263
@@ -34,6 +34,8 @@
}
trap "_cleanup; exit \$status" 0 1 2 3 15
+IMGOPTSSYNTAX=true
+
# get standard environment, filters and checks
. ./common.rc
. ./common.filter
@@ -73,7 +75,7 @@
echo
_make_test_img --object $SECRET -o "encrypt.format=luks,encrypt.key-secret=sec0,encrypt.iter-time=10,cluster_size=64K" $size
-_run_test "driver=$IMGFMT,encrypt.key-secret=sec0,file.filename=$TEST_IMG"
+_run_test "$TEST_IMG,encrypt.key-secret=sec0"
_cleanup_test_img
echo
@@ -82,7 +84,7 @@
_make_test_img --object $SECRET -o "encrypt.format=aes,encrypt.key-secret=sec0,cluster_size=64K" $size
-_run_test "driver=$IMGFMT,encrypt.key-secret=sec0,file.filename=$TEST_IMG"
+_run_test "$TEST_IMG,encrypt.key-secret=sec0"
_cleanup_test_img
diff --git a/tests/qemu-iotests/267.out b/tests/qemu-iotests/267.out
index 7176e37..f6f5d87 100644
--- a/tests/qemu-iotests/267.out
+++ b/tests/qemu-iotests/267.out
@@ -33,8 +33,8 @@
(qemu) savevm snap0
(qemu) info snapshots
List of snapshots present on all disks:
-ID TAG VM SIZE DATE VM CLOCK ICOUNT
--- snap0 SIZE yyyy-mm-dd hh:mm:ss 00:00:00.000
+ID TAG VM_SIZE DATE VM_CLOCK ICOUNT
+-- snap0 SIZE yyyy-mm-dd hh:mm:ss 0000:00:00.000 --
(qemu) loadvm snap0
(qemu) quit
@@ -44,8 +44,8 @@
(qemu) savevm snap0
(qemu) info snapshots
List of snapshots present on all disks:
-ID TAG VM SIZE DATE VM CLOCK ICOUNT
--- snap0 SIZE yyyy-mm-dd hh:mm:ss 00:00:00.000
+ID TAG VM_SIZE DATE VM_CLOCK ICOUNT
+-- snap0 SIZE yyyy-mm-dd hh:mm:ss 0000:00:00.000 --
(qemu) loadvm snap0
(qemu) quit
@@ -69,8 +69,8 @@
(qemu) savevm snap0
(qemu) info snapshots
List of snapshots present on all disks:
-ID TAG VM SIZE DATE VM CLOCK ICOUNT
--- snap0 SIZE yyyy-mm-dd hh:mm:ss 00:00:00.000
+ID TAG VM_SIZE DATE VM_CLOCK ICOUNT
+-- snap0 SIZE yyyy-mm-dd hh:mm:ss 0000:00:00.000 --
(qemu) loadvm snap0
(qemu) quit
@@ -94,8 +94,8 @@
(qemu) savevm snap0
(qemu) info snapshots
List of snapshots present on all disks:
-ID TAG VM SIZE DATE VM CLOCK ICOUNT
--- snap0 SIZE yyyy-mm-dd hh:mm:ss 00:00:00.000
+ID TAG VM_SIZE DATE VM_CLOCK ICOUNT
+-- snap0 SIZE yyyy-mm-dd hh:mm:ss 0000:00:00.000 --
(qemu) loadvm snap0
(qemu) quit
@@ -105,8 +105,8 @@
(qemu) savevm snap0
(qemu) info snapshots
List of snapshots present on all disks:
-ID TAG VM SIZE DATE VM CLOCK ICOUNT
--- snap0 SIZE yyyy-mm-dd hh:mm:ss 00:00:00.000
+ID TAG VM_SIZE DATE VM_CLOCK ICOUNT
+-- snap0 SIZE yyyy-mm-dd hh:mm:ss 0000:00:00.000 --
(qemu) loadvm snap0
(qemu) quit
@@ -119,8 +119,8 @@
(qemu) savevm snap0
(qemu) info snapshots
List of snapshots present on all disks:
-ID TAG VM SIZE DATE VM CLOCK ICOUNT
--- snap0 SIZE yyyy-mm-dd hh:mm:ss 00:00:00.000
+ID TAG VM_SIZE DATE VM_CLOCK ICOUNT
+-- snap0 SIZE yyyy-mm-dd hh:mm:ss 0000:00:00.000 --
(qemu) loadvm snap0
(qemu) quit
@@ -134,8 +134,8 @@
(qemu) savevm snap0
(qemu) info snapshots
List of snapshots present on all disks:
-ID TAG VM SIZE DATE VM CLOCK ICOUNT
--- snap0 SIZE yyyy-mm-dd hh:mm:ss 00:00:00.000
+ID TAG VM_SIZE DATE VM_CLOCK ICOUNT
+-- snap0 SIZE yyyy-mm-dd hh:mm:ss 0000:00:00.000 --
(qemu) loadvm snap0
(qemu) quit
@@ -145,15 +145,15 @@
(qemu) savevm snap0
(qemu) info snapshots
List of snapshots present on all disks:
-ID TAG VM SIZE DATE VM CLOCK ICOUNT
--- snap0 SIZE yyyy-mm-dd hh:mm:ss 00:00:00.000
+ID TAG VM_SIZE DATE VM_CLOCK ICOUNT
+-- snap0 SIZE yyyy-mm-dd hh:mm:ss 0000:00:00.000 --
(qemu) loadvm snap0
(qemu) quit
Internal snapshots on overlay:
Snapshot list:
-ID TAG VM SIZE DATE VM CLOCK ICOUNT
-1 snap0 SIZE yyyy-mm-dd hh:mm:ss 00:00:00.000
+ID TAG VM_SIZE DATE VM_CLOCK ICOUNT
+1 snap0 SIZE yyyy-mm-dd hh:mm:ss 0000:00:00.000 --
Internal snapshots on backing file:
=== -blockdev with NBD server on the backing file ===
@@ -166,17 +166,17 @@
(qemu) savevm snap0
(qemu) info snapshots
List of snapshots present on all disks:
-ID TAG VM SIZE DATE VM CLOCK ICOUNT
--- snap0 SIZE yyyy-mm-dd hh:mm:ss 00:00:00.000
+ID TAG VM_SIZE DATE VM_CLOCK ICOUNT
+-- snap0 SIZE yyyy-mm-dd hh:mm:ss 0000:00:00.000 --
(qemu) loadvm snap0
(qemu) quit
Internal snapshots on overlay:
Snapshot list:
-ID TAG VM SIZE DATE VM CLOCK ICOUNT
-1 snap0 SIZE yyyy-mm-dd hh:mm:ss 00:00:00.000
+ID TAG VM_SIZE DATE VM_CLOCK ICOUNT
+1 snap0 SIZE yyyy-mm-dd hh:mm:ss 0000:00:00.000 --
Internal snapshots on backing file:
Snapshot list:
-ID TAG VM SIZE DATE VM CLOCK ICOUNT
-1 snap0 SIZE yyyy-mm-dd hh:mm:ss 00:00:00.000
+ID TAG VM_SIZE DATE VM_CLOCK ICOUNT
+1 snap0 SIZE yyyy-mm-dd hh:mm:ss 0000:00:00.000 --
*** done
diff --git a/tests/qemu-iotests/284 b/tests/qemu-iotests/284
index 5a82639..7222674 100755
--- a/tests/qemu-iotests/284
+++ b/tests/qemu-iotests/284
@@ -33,6 +33,8 @@
}
trap "_cleanup; exit \$status" 0 1 2 3 15
+IMGOPTSSYNTAX=true
+
# get standard environment, filters and checks
. ./common.rc
. ./common.filter
@@ -47,14 +49,12 @@
SECRET="secret,id=sec0,data=astrochicken"
-IMGSPEC="driver=$IMGFMT,file.filename=$TEST_IMG,encrypt.key-secret=sec0"
QEMU_IO_OPTIONS=$QEMU_IO_OPTIONS_NO_FMT
_run_test()
{
- IMGOPTSSYNTAX=true
OLD_TEST_IMG="$TEST_IMG"
- TEST_IMG="driver=$IMGFMT,file.filename=$TEST_IMG,encrypt.key-secret=sec0"
+ TEST_IMG="$TEST_IMG,encrypt.key-secret=sec0"
QEMU_IMG_EXTRA_ARGS="--image-opts --object $SECRET"
echo
@@ -78,7 +78,6 @@
TEST_IMG="$OLD_TEST_IMG"
QEMU_IMG_EXTRA_ARGS=
- IMGOPTSSYNTAX=
}
diff --git a/tests/qemu-iotests/286 b/tests/qemu-iotests/286
index 120a837..38216c2 100755
--- a/tests/qemu-iotests/286
+++ b/tests/qemu-iotests/286
@@ -69,7 +69,8 @@
-e 's/\./(VM state size unit)/' \
-e 's/\./(snapshot date)/' \
-e 's/\./(snapshot time)/' \
- -e 's/\./(VM clock)/'
+ -e 's/\./(VM clock)/' \
+ -e 's/\./(icount)/'
# success, all done
echo "*** done"
diff --git a/tests/qemu-iotests/286.out b/tests/qemu-iotests/286.out
index 39ff07e..bb04748 100644
--- a/tests/qemu-iotests/286.out
+++ b/tests/qemu-iotests/286.out
@@ -4,5 +4,5 @@
(qemu) savevm abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz
(qemu) quit
Output structure:
-(snapshot ID) (snapshot name) (VM state size value) (VM state size unit) (snapshot date) (snapshot time) (VM clock)
+(snapshot ID) (snapshot name) (VM state size value) (VM state size unit) (snapshot date) (snapshot time) (VM clock) (icount)
*** done
diff --git a/tests/qemu-iotests/tests/detect-zeroes-registered-buf b/tests/qemu-iotests/tests/detect-zeroes-registered-buf
index edb5f2c..5eaf34e 100755
--- a/tests/qemu-iotests/tests/detect-zeroes-registered-buf
+++ b/tests/qemu-iotests/tests/detect-zeroes-registered-buf
@@ -36,6 +36,8 @@
}
trap "_cleanup; exit \$status" 0 1 2 3 15
+IMGOPTSSYNTAX=true
+
# get standard environment, filters and checks
cd ..
. ./common.rc
@@ -46,7 +48,7 @@
size=128M
_make_test_img $size
-IMGSPEC="driver=$IMGFMT,file.filename=$TEST_IMG,discard=unmap,detect-zeroes=unmap"
+IMGSPEC="$TEST_IMG,discard=unmap,detect-zeroes=unmap"
echo
echo "== writing zero buffer to image =="
diff --git a/tests/qemu-iotests/tests/iothreads-nbd-export b/tests/qemu-iotests/tests/iothreads-nbd-export
new file mode 100755
index 0000000..0372607
--- /dev/null
+++ b/tests/qemu-iotests/tests/iothreads-nbd-export
@@ -0,0 +1,66 @@
+#!/usr/bin/env python3
+# group: rw quick
+#
+# Copyright (C) 2024 Red Hat, Inc.
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program. If not, see <http://www.gnu.org/licenses/>.
+#
+# Creator/Owner: Kevin Wolf <kwolf@redhat.com>
+
+import time
+import qemu
+import iotests
+
+iotests.script_initialize(supported_fmts=['qcow2'],
+ supported_platforms=['linux'])
+
+with iotests.FilePath('disk1.img') as path, \
+ iotests.FilePath('nbd.sock', base_dir=iotests.sock_dir) as nbd_sock, \
+ qemu.machine.QEMUMachine(iotests.qemu_prog) as vm:
+
+ img_size = '10M'
+
+ iotests.log('Preparing disk...')
+ iotests.qemu_img_create('-f', iotests.imgfmt, path, img_size)
+ vm.add_args('-blockdev', f'file,node-name=disk-file,filename={path}')
+ vm.add_args('-blockdev', 'qcow2,node-name=disk,file=disk-file')
+ vm.add_args('-object', 'iothread,id=iothread0')
+ vm.add_args('-device',
+ 'virtio-blk,drive=disk,iothread=iothread0,share-rw=on')
+
+ iotests.log('Launching VM...')
+ vm.add_args('-accel', 'kvm', '-accel', 'tcg')
+ #vm.add_args('-accel', 'qtest')
+ vm.launch()
+
+ iotests.log('Exporting to NBD...')
+ iotests.log(vm.qmp('nbd-server-start',
+ addr={'type': 'unix', 'data': {'path': nbd_sock}}))
+ iotests.log(vm.qmp('block-export-add', type='nbd', id='exp0',
+ node_name='disk', writable=True))
+
+ iotests.log('Connecting qemu-img...')
+ qemu_io = iotests.QemuIoInteractive('-f', 'raw',
+ f'nbd+unix:///disk?socket={nbd_sock}')
+
+ iotests.log('Moving the NBD export to a different iothread...')
+ for i in range(0, 10):
+ iotests.log(vm.qmp('system_reset'))
+ time.sleep(0.1)
+
+ iotests.log('Checking that it is still alive...')
+ iotests.log(vm.qmp('query-status'))
+
+ qemu_io.close()
+ vm.shutdown()
diff --git a/tests/qemu-iotests/tests/iothreads-nbd-export.out b/tests/qemu-iotests/tests/iothreads-nbd-export.out
new file mode 100644
index 0000000..bc514e3
--- /dev/null
+++ b/tests/qemu-iotests/tests/iothreads-nbd-export.out
@@ -0,0 +1,19 @@
+Preparing disk...
+Launching VM...
+Exporting to NBD...
+{"return": {}}
+{"return": {}}
+Connecting qemu-img...
+Moving the NBD export to a different iothread...
+{"return": {}}
+{"return": {}}
+{"return": {}}
+{"return": {}}
+{"return": {}}
+{"return": {}}
+{"return": {}}
+{"return": {}}
+{"return": {}}
+{"return": {}}
+Checking that it is still alive...
+{"return": {"running": true, "status": "running"}}
diff --git a/tests/qemu-iotests/tests/qcow2-internal-snapshots b/tests/qemu-iotests/tests/qcow2-internal-snapshots
index 36523ab..9f83aa8 100755
--- a/tests/qemu-iotests/tests/qcow2-internal-snapshots
+++ b/tests/qemu-iotests/tests/qcow2-internal-snapshots
@@ -39,7 +39,7 @@
# This tests qcow2-specific low-level functionality
_supported_fmt qcow2
-_supported_proto generic
+_supported_proto file
# Internal snapshots are (currently) impossible with refcount_bits=1,
# and generally impossible with external data files
_unsupported_imgopts 'compat=0.10' 'refcount_bits=1[^0-9]' data_file
diff --git a/tests/qemu-iotests/tests/qcow2-internal-snapshots.out b/tests/qemu-iotests/tests/qcow2-internal-snapshots.out
index 438f535..fedb092 100644
--- a/tests/qemu-iotests/tests/qcow2-internal-snapshots.out
+++ b/tests/qemu-iotests/tests/qcow2-internal-snapshots.out
@@ -14,8 +14,8 @@
(qemu) quit
Snapshot list:
-ID TAG VM SIZE DATE VM CLOCK ICOUNT
-1 snap0 SIZE yyyy-mm-dd hh:mm:ss 00:00:00.000
+ID TAG VM_SIZE DATE VM_CLOCK ICOUNT
+1 snap0 SIZE yyyy-mm-dd hh:mm:ss 0000:00:00.000 --
No errors were found on the image.
=== Verify that loading the snapshot reverts to the old content ===
@@ -47,9 +47,9 @@
(qemu) quit
Snapshot list:
-ID TAG VM SIZE DATE VM CLOCK ICOUNT
-1 snap0 SIZE yyyy-mm-dd hh:mm:ss 00:00:00.000
-2 snap1 SIZE yyyy-mm-dd hh:mm:ss 00:00:00.000
+ID TAG VM_SIZE DATE VM_CLOCK ICOUNT
+1 snap0 SIZE yyyy-mm-dd hh:mm:ss 0000:00:00.000 --
+2 snap1 SIZE yyyy-mm-dd hh:mm:ss 0000:00:00.000 --
No errors were found on the image.
=== qemu-img snapshot can revert to snapshots ===
@@ -79,8 +79,8 @@
(qemu) quit
Snapshot list:
-ID TAG VM SIZE DATE VM CLOCK ICOUNT
-1 snap0 SIZE yyyy-mm-dd hh:mm:ss 00:00:00.000
+ID TAG VM_SIZE DATE VM_CLOCK ICOUNT
+1 snap0 SIZE yyyy-mm-dd hh:mm:ss 0000:00:00.000 --
No errors were found on the image.
=== Error cases ===
diff --git a/tests/qemu-iotests/tests/qsd-jobs b/tests/qemu-iotests/tests/qsd-jobs
index 510bf0a..9b843af 100755
--- a/tests/qemu-iotests/tests/qsd-jobs
+++ b/tests/qemu-iotests/tests/qsd-jobs
@@ -40,7 +40,7 @@
. ./common.filter
_supported_fmt qcow2
-_supported_proto generic
+_supported_proto file
size=128M
diff --git a/tests/qtest/bios-tables-test.c b/tests/qtest/bios-tables-test.c
index 21811a1..d1ff4db 100644
--- a/tests/qtest/bios-tables-test.c
+++ b/tests/qtest/bios-tables-test.c
@@ -858,6 +858,27 @@
g_free(args);
}
+static void process_smbios_tables_noexit(test_data *data)
+{
+ /*
+ * TODO: make SMBIOS tests work with UEFI firmware,
+ * Bug on uefi-test-tools to provide entry point:
+ * https://bugs.launchpad.net/qemu/+bug/1821884
+ */
+ if (!(data->uefi_fl1 && data->uefi_fl2)) {
+ SmbiosEntryPointType ep_type = test_smbios_entry_point(data);
+ test_smbios_structs(data, ep_type);
+ }
+}
+
+static void test_smbios(const char *params, test_data *data)
+{
+ test_vm_prepare(params, data);
+ boot_sector_test(data->qts);
+ process_smbios_tables_noexit(data);
+ qtest_quit(data->qts);
+}
+
static void process_acpi_tables_noexit(test_data *data)
{
test_acpi_load_tables(data);
@@ -868,15 +889,7 @@
test_acpi_asl(data);
}
- /*
- * TODO: make SMBIOS tests work with UEFI firmware,
- * Bug on uefi-test-tools to provide entry point:
- * https://bugs.launchpad.net/qemu/+bug/1821884
- */
- if (!(data->uefi_fl1 && data->uefi_fl2)) {
- SmbiosEntryPointType ep_type = test_smbios_entry_point(data);
- test_smbios_structs(data, ep_type);
- }
+ process_smbios_tables_noexit(data);
}
static void process_acpi_tables(test_data *data)
@@ -2064,6 +2077,50 @@
free_test_data(&data);
}
+static void test_acpi_pc_smbios_options(void)
+{
+ uint8_t req_type11[] = { 11 };
+ test_data data = {
+ .machine = MACHINE_PC,
+ .variant = ".pc_smbios_options",
+ .required_struct_types = req_type11,
+ .required_struct_types_len = ARRAY_SIZE(req_type11),
+ };
+
+ test_smbios("-smbios type=11,value=TEST", &data);
+ free_test_data(&data);
+}
+
+static void test_acpi_pc_smbios_blob(void)
+{
+ uint8_t req_type11[] = { 11 };
+ test_data data = {
+ .machine = MACHINE_PC,
+ .variant = ".pc_smbios_blob",
+ .required_struct_types = req_type11,
+ .required_struct_types_len = ARRAY_SIZE(req_type11),
+ };
+
+ test_smbios("-machine smbios-entry-point-type=32 "
+ "-smbios file=tests/data/smbios/type11_blob", &data);
+ free_test_data(&data);
+}
+
+static void test_acpi_isapc_smbios_legacy(void)
+{
+ uint8_t req_type11[] = { 1, 11 };
+ test_data data = {
+ .machine = "isapc",
+ .variant = ".pc_smbios_legacy",
+ .required_struct_types = req_type11,
+ .required_struct_types_len = ARRAY_SIZE(req_type11),
+ };
+
+ test_smbios("-smbios file=tests/data/smbios/type11_blob.legacy "
+ "-smbios type=1,family=TEST", &data);
+ free_test_data(&data);
+}
+
static void test_oem_fields(test_data *data)
{
int i;
@@ -2215,6 +2272,12 @@
#ifdef CONFIG_POSIX
qtest_add_func("acpi/piix4/acpierst", test_acpi_piix4_acpi_erst);
#endif
+ qtest_add_func("acpi/piix4/smbios-options",
+ test_acpi_pc_smbios_options);
+ qtest_add_func("acpi/piix4/smbios-blob",
+ test_acpi_pc_smbios_blob);
+ qtest_add_func("acpi/piix4/smbios-legacy",
+ test_acpi_isapc_smbios_legacy);
}
if (qtest_has_machine(MACHINE_Q35)) {
qtest_add_func("acpi/q35", test_acpi_q35_tcg);
diff --git a/tests/unit/meson.build b/tests/unit/meson.build
index cae925c..228a21d 100644
--- a/tests/unit/meson.build
+++ b/tests/unit/meson.build
@@ -173,9 +173,10 @@
slow_tests = {
'test-aio-multithread' : 120,
+ 'test-bufferiszero': 60,
'test-crypto-block' : 300,
- 'test-crypto-tlscredsx509': 45,
- 'test-crypto-tlssession': 45,
+ 'test-crypto-tlscredsx509': 90,
+ 'test-crypto-tlssession': 90,
'test-replication': 60,
}
diff --git a/tests/unit/test-crypto-cipher.c b/tests/unit/test-crypto-cipher.c
index 11ab1a5..f5152e5 100644
--- a/tests/unit/test-crypto-cipher.c
+++ b/tests/unit/test-crypto-cipher.c
@@ -676,9 +676,8 @@
cipher = qcrypto_cipher_new(
data->alg, data->mode,
key, nkey,
- &err);
+ data->plaintext ? &error_abort : &err);
if (data->plaintext) {
- g_assert(err == NULL);
g_assert(cipher != NULL);
} else {
error_free_or_abort(&err);
@@ -822,6 +821,10 @@
for (i = 0; i < G_N_ELEMENTS(test_data); i++) {
if (qcrypto_cipher_supports(test_data[i].alg, test_data[i].mode)) {
g_test_add_data_func(test_data[i].path, &test_data[i], test_cipher);
+ } else {
+ g_printerr("# skip unsupported %s:%s\n",
+ QCryptoCipherAlgorithm_str(test_data[i].alg),
+ QCryptoCipherMode_str(test_data[i].mode));
}
}
diff --git a/util/qemu-coroutine.c b/util/qemu-coroutine.c
index 5fd2dba..2790959 100644
--- a/util/qemu-coroutine.c
+++ b/util/qemu-coroutine.c
@@ -18,39 +18,200 @@
#include "qemu/atomic.h"
#include "qemu/coroutine_int.h"
#include "qemu/coroutine-tls.h"
+#include "qemu/cutils.h"
#include "block/aio.h"
-/**
- * The minimal batch size is always 64, coroutines from the release_pool are
- * reused as soon as there are 64 coroutines in it. The maximum pool size starts
- * with 64 and is increased on demand so that coroutines are not deleted even if
- * they are not immediately reused.
- */
enum {
- POOL_MIN_BATCH_SIZE = 64,
- POOL_INITIAL_MAX_SIZE = 64,
+ COROUTINE_POOL_BATCH_MAX_SIZE = 128,
};
-/** Free list to speed up creation */
-static QSLIST_HEAD(, Coroutine) release_pool = QSLIST_HEAD_INITIALIZER(pool);
-static unsigned int pool_max_size = POOL_INITIAL_MAX_SIZE;
-static unsigned int release_pool_size;
+/*
+ * Coroutine creation and deletion is expensive so a pool of unused coroutines
+ * is kept as a cache. When the pool has coroutines available, they are
+ * recycled instead of creating new ones from scratch. Coroutines are added to
+ * the pool upon termination.
+ *
+ * The pool is global but each thread maintains a small local pool to avoid
+ * global pool contention. Threads fetch and return batches of coroutines from
+ * the global pool to maintain their local pool. The local pool holds up to two
+ * batches whereas the maximum size of the global pool is controlled by the
+ * qemu_coroutine_inc_pool_size() API.
+ *
+ * .-----------------------------------.
+ * | Batch 1 | Batch 2 | Batch 3 | ... | global_pool
+ * `-----------------------------------'
+ *
+ * .-------------------.
+ * | Batch 1 | Batch 2 | per-thread local_pool (maximum 2 batches)
+ * `-------------------'
+ */
+typedef struct CoroutinePoolBatch {
+ /* Batches are kept in a list */
+ QSLIST_ENTRY(CoroutinePoolBatch) next;
-typedef QSLIST_HEAD(, Coroutine) CoroutineQSList;
-QEMU_DEFINE_STATIC_CO_TLS(CoroutineQSList, alloc_pool);
-QEMU_DEFINE_STATIC_CO_TLS(unsigned int, alloc_pool_size);
-QEMU_DEFINE_STATIC_CO_TLS(Notifier, coroutine_pool_cleanup_notifier);
+ /* This batch holds up to @COROUTINE_POOL_BATCH_MAX_SIZE coroutines */
+ QSLIST_HEAD(, Coroutine) list;
+ unsigned int size;
+} CoroutinePoolBatch;
-static void coroutine_pool_cleanup(Notifier *n, void *value)
+typedef QSLIST_HEAD(, CoroutinePoolBatch) CoroutinePool;
+
+/* Host operating system limit on number of pooled coroutines */
+static unsigned int global_pool_hard_max_size;
+
+static QemuMutex global_pool_lock; /* protects the following variables */
+static CoroutinePool global_pool = QSLIST_HEAD_INITIALIZER(global_pool);
+static unsigned int global_pool_size;
+static unsigned int global_pool_max_size = COROUTINE_POOL_BATCH_MAX_SIZE;
+
+QEMU_DEFINE_STATIC_CO_TLS(CoroutinePool, local_pool);
+QEMU_DEFINE_STATIC_CO_TLS(Notifier, local_pool_cleanup_notifier);
+
+static CoroutinePoolBatch *coroutine_pool_batch_new(void)
+{
+ CoroutinePoolBatch *batch = g_new(CoroutinePoolBatch, 1);
+
+ QSLIST_INIT(&batch->list);
+ batch->size = 0;
+ return batch;
+}
+
+static void coroutine_pool_batch_delete(CoroutinePoolBatch *batch)
{
Coroutine *co;
Coroutine *tmp;
- CoroutineQSList *alloc_pool = get_ptr_alloc_pool();
- QSLIST_FOREACH_SAFE(co, alloc_pool, pool_next, tmp) {
- QSLIST_REMOVE_HEAD(alloc_pool, pool_next);
+ QSLIST_FOREACH_SAFE(co, &batch->list, pool_next, tmp) {
+ QSLIST_REMOVE_HEAD(&batch->list, pool_next);
qemu_coroutine_delete(co);
}
+ g_free(batch);
+}
+
+static void local_pool_cleanup(Notifier *n, void *value)
+{
+ CoroutinePool *local_pool = get_ptr_local_pool();
+ CoroutinePoolBatch *batch;
+ CoroutinePoolBatch *tmp;
+
+ QSLIST_FOREACH_SAFE(batch, local_pool, next, tmp) {
+ QSLIST_REMOVE_HEAD(local_pool, next);
+ coroutine_pool_batch_delete(batch);
+ }
+}
+
+/* Ensure the atexit notifier is registered */
+static void local_pool_cleanup_init_once(void)
+{
+ Notifier *notifier = get_ptr_local_pool_cleanup_notifier();
+ if (!notifier->notify) {
+ notifier->notify = local_pool_cleanup;
+ qemu_thread_atexit_add(notifier);
+ }
+}
+
+/* Helper to get the next unused coroutine from the local pool */
+static Coroutine *coroutine_pool_get_local(void)
+{
+ CoroutinePool *local_pool = get_ptr_local_pool();
+ CoroutinePoolBatch *batch = QSLIST_FIRST(local_pool);
+ Coroutine *co;
+
+ if (unlikely(!batch)) {
+ return NULL;
+ }
+
+ co = QSLIST_FIRST(&batch->list);
+ QSLIST_REMOVE_HEAD(&batch->list, pool_next);
+ batch->size--;
+
+ if (batch->size == 0) {
+ QSLIST_REMOVE_HEAD(local_pool, next);
+ coroutine_pool_batch_delete(batch);
+ }
+ return co;
+}
+
+/* Get the next batch from the global pool */
+static void coroutine_pool_refill_local(void)
+{
+ CoroutinePool *local_pool = get_ptr_local_pool();
+ CoroutinePoolBatch *batch;
+
+ WITH_QEMU_LOCK_GUARD(&global_pool_lock) {
+ batch = QSLIST_FIRST(&global_pool);
+
+ if (batch) {
+ QSLIST_REMOVE_HEAD(&global_pool, next);
+ global_pool_size -= batch->size;
+ }
+ }
+
+ if (batch) {
+ QSLIST_INSERT_HEAD(local_pool, batch, next);
+ local_pool_cleanup_init_once();
+ }
+}
+
+/* Add a batch of coroutines to the global pool */
+static void coroutine_pool_put_global(CoroutinePoolBatch *batch)
+{
+ WITH_QEMU_LOCK_GUARD(&global_pool_lock) {
+ unsigned int max = MIN(global_pool_max_size,
+ global_pool_hard_max_size);
+
+ if (global_pool_size < max) {
+ QSLIST_INSERT_HEAD(&global_pool, batch, next);
+
+ /* Overshooting the max pool size is allowed */
+ global_pool_size += batch->size;
+ return;
+ }
+ }
+
+ /* The global pool was full, so throw away this batch */
+ coroutine_pool_batch_delete(batch);
+}
+
+/* Get the next unused coroutine from the pool or return NULL */
+static Coroutine *coroutine_pool_get(void)
+{
+ Coroutine *co;
+
+ co = coroutine_pool_get_local();
+ if (!co) {
+ coroutine_pool_refill_local();
+ co = coroutine_pool_get_local();
+ }
+ return co;
+}
+
+static void coroutine_pool_put(Coroutine *co)
+{
+ CoroutinePool *local_pool = get_ptr_local_pool();
+ CoroutinePoolBatch *batch = QSLIST_FIRST(local_pool);
+
+ if (unlikely(!batch)) {
+ batch = coroutine_pool_batch_new();
+ QSLIST_INSERT_HEAD(local_pool, batch, next);
+ local_pool_cleanup_init_once();
+ }
+
+ if (unlikely(batch->size >= COROUTINE_POOL_BATCH_MAX_SIZE)) {
+ CoroutinePoolBatch *next = QSLIST_NEXT(batch, next);
+
+ /* Is the local pool full? */
+ if (next) {
+ QSLIST_REMOVE_HEAD(local_pool, next);
+ coroutine_pool_put_global(batch);
+ }
+
+ batch = coroutine_pool_batch_new();
+ QSLIST_INSERT_HEAD(local_pool, batch, next);
+ }
+
+ QSLIST_INSERT_HEAD(&batch->list, co, pool_next);
+ batch->size++;
}
Coroutine *qemu_coroutine_create(CoroutineEntry *entry, void *opaque)
@@ -58,31 +219,7 @@
Coroutine *co = NULL;
if (IS_ENABLED(CONFIG_COROUTINE_POOL)) {
- CoroutineQSList *alloc_pool = get_ptr_alloc_pool();
-
- co = QSLIST_FIRST(alloc_pool);
- if (!co) {
- if (release_pool_size > POOL_MIN_BATCH_SIZE) {
- /* Slow path; a good place to register the destructor, too. */
- Notifier *notifier = get_ptr_coroutine_pool_cleanup_notifier();
- if (!notifier->notify) {
- notifier->notify = coroutine_pool_cleanup;
- qemu_thread_atexit_add(notifier);
- }
-
- /* This is not exact; there could be a little skew between
- * release_pool_size and the actual size of release_pool. But
- * it is just a heuristic, it does not need to be perfect.
- */
- set_alloc_pool_size(qatomic_xchg(&release_pool_size, 0));
- QSLIST_MOVE_ATOMIC(alloc_pool, &release_pool);
- co = QSLIST_FIRST(alloc_pool);
- }
- }
- if (co) {
- QSLIST_REMOVE_HEAD(alloc_pool, pool_next);
- set_alloc_pool_size(get_alloc_pool_size() - 1);
- }
+ co = coroutine_pool_get();
}
if (!co) {
@@ -100,19 +237,10 @@
co->caller = NULL;
if (IS_ENABLED(CONFIG_COROUTINE_POOL)) {
- if (release_pool_size < qatomic_read(&pool_max_size) * 2) {
- QSLIST_INSERT_HEAD_ATOMIC(&release_pool, co, pool_next);
- qatomic_inc(&release_pool_size);
- return;
- }
- if (get_alloc_pool_size() < qatomic_read(&pool_max_size)) {
- QSLIST_INSERT_HEAD(get_ptr_alloc_pool(), co, pool_next);
- set_alloc_pool_size(get_alloc_pool_size() + 1);
- return;
- }
+ coroutine_pool_put(co);
+ } else {
+ qemu_coroutine_delete(co);
}
-
- qemu_coroutine_delete(co);
}
void qemu_aio_coroutine_enter(AioContext *ctx, Coroutine *co)
@@ -223,10 +351,46 @@
void qemu_coroutine_inc_pool_size(unsigned int additional_pool_size)
{
- qatomic_add(&pool_max_size, additional_pool_size);
+ QEMU_LOCK_GUARD(&global_pool_lock);
+ global_pool_max_size += additional_pool_size;
}
void qemu_coroutine_dec_pool_size(unsigned int removing_pool_size)
{
- qatomic_sub(&pool_max_size, removing_pool_size);
+ QEMU_LOCK_GUARD(&global_pool_lock);
+ global_pool_max_size -= removing_pool_size;
+}
+
+static unsigned int get_global_pool_hard_max_size(void)
+{
+#ifdef __linux__
+ g_autofree char *contents = NULL;
+ int max_map_count;
+
+ /*
+ * Linux processes can have up to max_map_count virtual memory areas
+ * (VMAs). mmap(2), mprotect(2), etc fail with ENOMEM beyond this limit. We
+ * must limit the coroutine pool to a safe size to avoid running out of
+ * VMAs.
+ */
+ if (g_file_get_contents("/proc/sys/vm/max_map_count", &contents, NULL,
+ NULL) &&
+ qemu_strtoi(contents, NULL, 10, &max_map_count) == 0) {
+ /*
+ * This is a conservative upper bound that avoids exceeding
+ * max_map_count. Leave half for non-coroutine users like library
+ * dependencies, vhost-user, etc. Each coroutine takes up 2 VMAs so
+ * halve the amount again.
+ */
+ return max_map_count / 4;
+ }
+#endif
+
+ return UINT_MAX;
+}
+
+static void __attribute__((constructor)) qemu_coroutine_init(void)
+{
+ qemu_mutex_init(&global_pool_lock);
+ global_pool_hard_max_size = get_global_pool_hard_max_size();
}
