diff options
author | Peter Maydell <peter.maydell@linaro.org> | 2017-01-20 16:42:07 +0000 |
---|---|---|
committer | Peter Maydell <peter.maydell@linaro.org> | 2017-01-20 16:42:07 +0000 |
commit | 598cf1c805271564686f2d732b36f50c3c40dcdd (patch) | |
tree | f512a9398bba3023126b7303160a91c8d30b0adb | |
parent | d1c82f7cc34443841095f490345f86c9d8baca34 (diff) | |
parent | abc62c89f3191774dbd600a2caec803cbf557160 (diff) |
Merge remote-tracking branch 'remotes/bonzini/tags/for-upstream' into staging
* QOM interface fix (Eduardo)
* RTC fixes (Gaohuai, Igor)
* Memory leak fixes (Li Qiang, me)
* Ctrl-a b regression (Marc-André)
* Stubs cleanups and fixes (Leif, me)
* hxtool tweak (me)
* HAX support (Vincent)
* QemuThread, exec.c and SCSI fixes (Roman, Xinhua, me)
* PC_COMPAT_2_8 fix (Marcelo)
* stronger bitmap assertions (Peter)
# gpg: Signature made Fri 20 Jan 2017 12:49:01 GMT
# gpg: using RSA key 0xBFFBD25F78C7AE83
# gpg: Good signature from "Paolo Bonzini <bonzini@gnu.org>"
# gpg: aka "Paolo Bonzini <pbonzini@redhat.com>"
# Primary key fingerprint: 46F5 9FBD 57D6 12E7 BFD4 E2F7 7E15 100C CD36 69B1
# Subkey fingerprint: F133 3857 4B66 2389 866C 7682 BFFB D25F 78C7 AE83
* remotes/bonzini/tags/for-upstream: (35 commits)
pc.h: move x-mach-use-reliable-get-clock compat entry to PC_COMPAT_2_8
bitmap: assert that start and nr are non negative
Revert "win32: don't run subprocess tests on Mingw32 platform"
hax: add Darwin support
Plumb the HAXM-based hardware acceleration support
target/i386: Add Intel HAX files
kvm: move cpu synchronization code
KVM: PPC: eliminate unnecessary duplicate constants
ramblock-notifier: new
char: fix ctrl-a b not working
exec: Add missing rcu_read_unlock
x86: ioapic: fix fail migration when irqchip=split
x86: ioapic: dump version for "info ioapic"
x86: ioapic: add traces for ioapic
hxtool: emit Texinfo headings as @subsection
qemu-thread: fix qemu_thread_set_name() race in qemu_thread_create()
serial: fix memory leak in serial exit
scsi-block: fix direction of BYTCHK test for VERIFY commands
pc: fix crash in rtc_set_memory() if initial cpu is marked as hotplugged
acpi: filter based on CONFIG_ACPI_X86 rather than TARGET
...
# Conflicts:
# include/hw/i386/pc.h
110 files changed, 3728 insertions, 468 deletions
diff --git a/MAINTAINERS b/MAINTAINERS index b5ebfab4c3..ad1000415d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1501,6 +1501,7 @@ M: Riku Voipio <riku.voipio@iki.fi> S: Maintained F: thunk.c F: user-exec.c +F: user-exec-stub.c BSD user S: Orphan diff --git a/Makefile.target b/Makefile.target index 8ae82cb311..fa2b151caa 100644 --- a/Makefile.target +++ b/Makefile.target @@ -97,6 +97,7 @@ obj-y += target/$(TARGET_BASE_ARCH)/ obj-y += disas.o obj-y += tcg-runtime.o obj-$(call notempty,$(TARGET_XML_FILES)) += gdbstub-xml.o +obj-$(call lnot,$(CONFIG_HAX)) += hax-stub.o obj-$(call lnot,$(CONFIG_KVM)) += kvm-stub.o obj-$(CONFIG_LIBDECNUMBER) += libdecnumber/decContext.o @@ -115,7 +116,7 @@ QEMU_CFLAGS+=-I$(SRC_PATH)/linux-user/$(TARGET_ABI_DIR) \ -I$(SRC_PATH)/linux-user obj-y += linux-user/ -obj-y += gdbstub.o thunk.o user-exec.o +obj-y += gdbstub.o thunk.o user-exec.o user-exec-stub.o endif #CONFIG_LINUX_USER @@ -128,7 +129,7 @@ QEMU_CFLAGS+=-I$(SRC_PATH)/bsd-user -I$(SRC_PATH)/bsd-user/$(TARGET_ABI_DIR) \ -I$(SRC_PATH)/bsd-user/$(HOST_VARIANT_DIR) obj-y += bsd-user/ -obj-y += gdbstub.o user-exec.o +obj-y += gdbstub.o user-exec.o user-exec-stub.o endif #CONFIG_BSD_USER diff --git a/arch_init.c b/arch_init.c index 5cc58b2c35..6c4e287d57 100644 --- a/arch_init.c +++ b/arch_init.c @@ -28,7 +28,6 @@ #include "sysemu/arch_init.h" #include "hw/pci/pci.h" #include "hw/audio/audio.h" -#include "hw/smbios/smbios.h" #include "qemu/config-file.h" #include "qemu/error-report.h" #include "qmp-commands.h" @@ -235,26 +234,6 @@ void audio_init(void) } } -void do_acpitable_option(const QemuOpts *opts) -{ -#ifdef TARGET_I386 - Error *err = NULL; - - acpi_table_add(opts, &err); - if (err) { - error_reportf_err(err, "Wrong acpi table provided: "); - exit(1); - } -#endif -} - -void do_smbios_option(QemuOpts *opts) -{ -#ifdef TARGET_I386 - smbios_entry_add(opts); -#endif -} - int kvm_available(void) { #ifdef CONFIG_KVM @@ -228,7 +228,7 @@ vhost_net="no" vhost_scsi="no" vhost_vsock="no" kvm="no" -colo="yes" +hax="no" rdma="" gprof="no" debug_tcg="no" @@ -562,6 +562,7 @@ CYGWIN*) ;; MINGW32*) mingw32="yes" + hax="yes" audio_possible_drivers="dsound sdl" if check_include dsound.h; then audio_drv_list="dsound" @@ -611,6 +612,7 @@ OpenBSD) Darwin) bsd="yes" darwin="yes" + hax="yes" LDFLAGS_SHARED="-bundle -undefined dynamic_lookup" if [ "$cpu" = "x86_64" ] ; then QEMU_CFLAGS="-arch x86_64 $QEMU_CFLAGS" @@ -920,9 +922,9 @@ for opt do ;; --enable-kvm) kvm="yes" ;; - --disable-colo) colo="no" + --disable-hax) hax="no" ;; - --enable-colo) colo="yes" + --enable-hax) hax="yes" ;; --disable-tcg-interpreter) tcg_interpreter="no" ;; @@ -1372,7 +1374,7 @@ disabled with --disable-FEATURE, default is enabled if available: fdt fdt device tree bluez bluez stack connectivity kvm KVM acceleration support - colo COarse-grain LOck-stepping VM for Non-stop Service + hax HAX acceleration support rdma RDMA-based migration support vde support for vde network netmap support for netmap network @@ -3077,7 +3079,7 @@ fi # g_test_trap_subprocess added in 2.38. Used by some tests. glib_subprocess=yes -if test "$mingw32" = "yes" || ! $pkg_config --atleast-version=2.38 glib-2.0; then +if ! $pkg_config --atleast-version=2.38 glib-2.0; then glib_subprocess=no fi @@ -5062,7 +5064,7 @@ echo "Linux AIO support $linux_aio" echo "ATTR/XATTR support $attr" echo "Install blobs $blobs" echo "KVM support $kvm" -echo "COLO support $colo" +echo "HAX support $hax" echo "RDMA support $rdma" echo "TCG interpreter $tcg_interpreter" echo "fdt support $fdt" @@ -5701,10 +5703,6 @@ if have_backend "syslog"; then fi echo "CONFIG_TRACE_FILE=$trace_file" >> $config_host_mak -if test "$colo" = "yes"; then - echo "CONFIG_COLO=y" >> $config_host_mak -fi - if test "$rdma" = "yes" ; then echo "CONFIG_RDMA=y" >> $config_host_mak fi @@ -6050,6 +6048,15 @@ case "$target_name" in fi fi esac +if test "$hax" = "yes" ; then + if test "$target_softmmu" = "yes" ; then + case "$target_name" in + i386|x86_64) + echo "CONFIG_HAX=y" >> $config_target_mak + ;; + esac + fi +fi if test "$target_bigendian" = "yes" ; then echo "TARGET_WORDS_BIGENDIAN=y" >> $config_target_mak fi @@ -33,7 +33,9 @@ #include "sysemu/block-backend.h" #include "exec/gdbstub.h" #include "sysemu/dma.h" +#include "sysemu/hw_accel.h" #include "sysemu/kvm.h" +#include "sysemu/hax.h" #include "qmp-commands.h" #include "exec/exec-all.h" @@ -1220,6 +1222,46 @@ static void *qemu_tcg_cpu_thread_fn(void *arg) return NULL; } +static void *qemu_hax_cpu_thread_fn(void *arg) +{ + CPUState *cpu = arg; + int r; + qemu_thread_get_self(cpu->thread); + qemu_mutex_lock(&qemu_global_mutex); + + cpu->thread_id = qemu_get_thread_id(); + cpu->created = true; + cpu->halted = 0; + current_cpu = cpu; + + hax_init_vcpu(cpu); + qemu_cond_signal(&qemu_cpu_cond); + + while (1) { + if (cpu_can_run(cpu)) { + r = hax_smp_cpu_exec(cpu); + if (r == EXCP_DEBUG) { + cpu_handle_guest_debug(cpu); + } + } + + while (cpu_thread_is_idle(cpu)) { + qemu_cond_wait(cpu->halt_cond, &qemu_global_mutex); + } +#ifdef _WIN32 + SleepEx(0, TRUE); +#endif + qemu_wait_io_event_common(cpu); + } + return NULL; +} + +#ifdef _WIN32 +static void CALLBACK dummy_apc_func(ULONG_PTR unused) +{ +} +#endif + static void qemu_cpu_kick_thread(CPUState *cpu) { #ifndef _WIN32 @@ -1235,7 +1277,13 @@ static void qemu_cpu_kick_thread(CPUState *cpu) exit(1); } #else /* _WIN32 */ - abort(); + if (!qemu_cpu_is_self(cpu)) { + if (!QueueUserAPC(dummy_apc_func, cpu->hThread, 0)) { + fprintf(stderr, "%s: QueueUserAPC failed with error %lu\n", + __func__, GetLastError()); + exit(1); + } + } #endif } @@ -1258,6 +1306,13 @@ void qemu_cpu_kick(CPUState *cpu) if (tcg_enabled()) { qemu_cpu_kick_no_halt(); } else { + if (hax_enabled()) { + /* + * FIXME: race condition with the exit_request check in + * hax_vcpu_hax_exec + */ + cpu->exit_request = 1; + } qemu_cpu_kick_thread(cpu); } } @@ -1418,6 +1473,26 @@ static void qemu_tcg_init_vcpu(CPUState *cpu) } } +static void qemu_hax_start_vcpu(CPUState *cpu) +{ + char thread_name[VCPU_THREAD_NAME_SIZE]; + + cpu->thread = g_malloc0(sizeof(QemuThread)); + cpu->halt_cond = g_malloc0(sizeof(QemuCond)); + qemu_cond_init(cpu->halt_cond); + + snprintf(thread_name, VCPU_THREAD_NAME_SIZE, "CPU %d/HAX", + cpu->cpu_index); + qemu_thread_create(cpu->thread, thread_name, qemu_hax_cpu_thread_fn, + cpu, QEMU_THREAD_JOINABLE); +#ifdef _WIN32 + cpu->hThread = qemu_thread_get_handle(cpu->thread); +#endif + while (!cpu->created) { + qemu_cond_wait(&qemu_cpu_cond, &qemu_global_mutex); + } +} + static void qemu_kvm_start_vcpu(CPUState *cpu) { char thread_name[VCPU_THREAD_NAME_SIZE]; @@ -1468,6 +1543,8 @@ void qemu_init_vcpu(CPUState *cpu) if (kvm_enabled()) { qemu_kvm_start_vcpu(cpu); + } else if (hax_enabled()) { + qemu_hax_start_vcpu(cpu); } else if (tcg_enabled()) { qemu_tcg_init_vcpu(cpu); } else { @@ -1687,6 +1687,7 @@ static void ram_block_add(RAMBlock *new_block, Error **errp) qemu_madvise(new_block->host, new_block->max_length, QEMU_MADV_HUGEPAGE); /* MADV_DONTFORK is also needed by KVM in absence of synchronous MMU */ qemu_madvise(new_block->host, new_block->max_length, QEMU_MADV_DONTFORK); + ram_block_notify_add(new_block->host, new_block->max_length); } } @@ -1817,6 +1818,10 @@ void qemu_ram_free(RAMBlock *block) return; } + if (block->host) { + ram_block_notify_remove(block->host, block->max_length); + } + qemu_mutex_lock_ramlist(); QLIST_REMOVE_RCU(block, next); ram_list.mru_block = NULL; @@ -2960,6 +2965,7 @@ bool address_space_access_valid(AddressSpace *as, hwaddr addr, int len, bool is_ if (!memory_access_is_direct(mr, is_write)) { l = memory_access_size(mr, l, addr); if (!memory_region_access_valid(mr, xlat, l, is_write)) { + rcu_read_unlock(); return false; } } @@ -32,6 +32,7 @@ #define MAX_PACKET_LENGTH 4096 #include "qemu/sockets.h" +#include "sysemu/hw_accel.h" #include "sysemu/kvm.h" #include "exec/semihost.h" #include "exec/exec-all.h" diff --git a/hax-stub.c b/hax-stub.c new file mode 100644 index 0000000000..c0e6f892e5 --- /dev/null +++ b/hax-stub.c @@ -0,0 +1,34 @@ +/* + * QEMU HAXM support + * + * Copyright (c) 2015, Intel Corporation + * + * Copyright 2016 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * See the COPYING file in the top-level directory. + * + */ + +#include "qemu/osdep.h" +#include "qemu-common.h" +#include "cpu.h" +#include "sysemu/hax.h" + +int hax_sync_vcpus(void) +{ + return 0; +} + +int hax_init_vcpu(CPUState *cpu) +{ + return -ENOSYS; +} + +int hax_smp_cpu_exec(CPUState *cpu) +{ + return -ENOSYS; +} diff --git a/hw/Makefile.objs b/hw/Makefile.objs index 0ffd281145..a2c61f6b09 100644 --- a/hw/Makefile.objs +++ b/hw/Makefile.objs @@ -1,5 +1,5 @@ devices-dirs-$(call land, $(CONFIG_VIRTIO),$(call land,$(CONFIG_VIRTFS),$(CONFIG_PCI))) += 9pfs/ -devices-dirs-$(CONFIG_ACPI) += acpi/ +devices-dirs-$(CONFIG_SOFTMMU) += acpi/ devices-dirs-$(CONFIG_SOFTMMU) += adc/ devices-dirs-$(CONFIG_SOFTMMU) += audio/ devices-dirs-$(CONFIG_SOFTMMU) += block/ @@ -29,11 +29,11 @@ devices-dirs-$(CONFIG_SOFTMMU) += timer/ devices-dirs-$(CONFIG_TPM) += tpm/ devices-dirs-$(CONFIG_SOFTMMU) += usb/ devices-dirs-$(CONFIG_SOFTMMU) += vfio/ -devices-dirs-$(CONFIG_VIRTIO) += virtio/ +devices-dirs-$(CONFIG_SOFTMMU) += virtio/ devices-dirs-$(CONFIG_SOFTMMU) += watchdog/ devices-dirs-$(CONFIG_SOFTMMU) += xen/ devices-dirs-$(CONFIG_MEM_HOTPLUG) += mem/ -devices-dirs-$(CONFIG_SMBIOS) += smbios/ +devices-dirs-$(CONFIG_SOFTMMU) += smbios/ devices-dirs-y += core/ common-obj-y += $(devices-dirs-y) obj-y += $(devices-dirs-y) diff --git a/hw/acpi/Makefile.objs b/hw/acpi/Makefile.objs index 834c63b980..6acf79860a 100644 --- a/hw/acpi/Makefile.objs +++ b/hw/acpi/Makefile.objs @@ -1,10 +1,19 @@ +ifeq ($(CONFIG_ACPI),y) common-obj-$(CONFIG_ACPI_X86) += core.o piix4.o pcihp.o common-obj-$(CONFIG_ACPI_X86_ICH) += ich9.o tco.o common-obj-$(CONFIG_ACPI_CPU_HOTPLUG) += cpu_hotplug.o common-obj-$(CONFIG_ACPI_MEMORY_HOTPLUG) += memory_hotplug.o common-obj-$(CONFIG_ACPI_CPU_HOTPLUG) += cpu.o common-obj-$(CONFIG_ACPI_NVDIMM) += nvdimm.o -common-obj-$(CONFIG_ACPI) += acpi_interface.o -common-obj-$(CONFIG_ACPI) += bios-linker-loader.o -common-obj-$(CONFIG_ACPI) += aml-build.o -common-obj-$(call land,$(CONFIG_ACPI),$(CONFIG_IPMI)) += ipmi.o +common-obj-$(call lnot,$(CONFIG_ACPI_X86)) += acpi-stub.o + +common-obj-y += acpi_interface.o +common-obj-y += bios-linker-loader.o +common-obj-y += aml-build.o + +common-obj-$(CONFIG_IPMI) += ipmi.o +common-obj-$(call lnot,$(CONFIG_IPMI)) += ipmi-stub.o +else +common-obj-y += acpi-stub.o +endif +common-obj-$(CONFIG_ALL) += acpi-stub.o ipmi-stub.o diff --git a/hw/acpi/acpi-stub.c b/hw/acpi/acpi-stub.c new file mode 100644 index 0000000000..26bd22f7ec --- /dev/null +++ b/hw/acpi/acpi-stub.c @@ -0,0 +1,29 @@ +/* + * ACPI stubs for platforms that don't support ACPI. + * + * Copyright (c) 2006 Fabrice Bellard + * Copyright (c) 2016 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/>. + */ + +#include "qemu/osdep.h" +#include "qapi/qmp/qerror.h" +#include "qmp-commands.h" +#include "hw/acpi/acpi.h" + +void acpi_table_add(const QemuOpts *opts, Error **errp) +{ + error_setg(errp, QERR_UNSUPPORTED); +} diff --git a/stubs/ipmi.c b/hw/acpi/ipmi-stub.c index 98b6dcee0d..98b6dcee0d 100644 --- a/stubs/ipmi.c +++ b/hw/acpi/ipmi-stub.c diff --git a/hw/char/serial.c b/hw/char/serial.c index ffbacd8227..67b18eda12 100644 --- a/hw/char/serial.c +++ b/hw/char/serial.c @@ -906,6 +906,16 @@ void serial_realize_core(SerialState *s, Error **errp) void serial_exit_core(SerialState *s) { qemu_chr_fe_deinit(&s->chr); + + timer_del(s->modem_status_poll); + timer_free(s->modem_status_poll); + + timer_del(s->fifo_timeout_timer); + timer_free(s->fifo_timeout_timer); + + fifo8_destroy(&s->recv_fifo); + fifo8_destroy(&s->xmit_fifo); + qemu_unregister_reset(serial_reset, s); } diff --git a/hw/core/Makefile.objs b/hw/core/Makefile.objs index a4c94e522d..833fd46897 100644 --- a/hw/core/Makefile.objs +++ b/hw/core/Makefile.objs @@ -1,6 +1,6 @@ # core qdev-related obj files, also used by *-user: common-obj-y += qdev.o qdev-properties.o -common-obj-y += bus.o +common-obj-y += bus.o reset.o common-obj-y += fw-path-provider.o # irq.o needed for qdev GPIO handling: common-obj-y += irq.o diff --git a/hw/core/reset.c b/hw/core/reset.c new file mode 100644 index 0000000000..84c8869371 --- /dev/null +++ b/hw/core/reset.c @@ -0,0 +1,72 @@ +/* + * Reset handlers. + * + * Copyright (c) 2003-2008 Fabrice Bellard + * Copyright (c) 2016 Red Hat, Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#include "qemu/osdep.h" +#include "qemu/queue.h" +#include "sysemu/reset.h" + +/* reset/shutdown handler */ + +typedef struct QEMUResetEntry { + QTAILQ_ENTRY(QEMUResetEntry) entry; + QEMUResetHandler *func; + void *opaque; +} QEMUResetEntry; + +static QTAILQ_HEAD(reset_handlers, QEMUResetEntry) reset_handlers = + QTAILQ_HEAD_INITIALIZER(reset_handlers); + +void qemu_register_reset(QEMUResetHandler *func, void *opaque) +{ + QEMUResetEntry *re = g_malloc0(sizeof(QEMUResetEntry)); + + re->func = func; + re->opaque = opaque; + QTAILQ_INSERT_TAIL(&reset_handlers, re, entry); +} + +void qemu_unregister_reset(QEMUResetHandler *func, void *opaque) +{ + QEMUResetEntry *re; + + QTAILQ_FOREACH(re, &reset_handlers, entry) { + if (re->func == func && re->opaque == opaque) { + QTAILQ_REMOVE(&reset_handlers, re, entry); + g_free(re); + return; + } + } +} + +void qemu_devices_reset(void) +{ + QEMUResetEntry *re, *nre; + + /* reset all devices */ + QTAILQ_FOREACH_SAFE(re, &reset_handlers, entry, nre) { + re->func(re->opaque); + } +} + diff --git a/hw/i386/kvm/apic.c b/hw/i386/kvm/apic.c index df5180b1e0..1df6d26816 100644 --- a/hw/i386/kvm/apic.c +++ b/hw/i386/kvm/apic.c @@ -14,6 +14,7 @@ #include "cpu.h" #include "hw/i386/apic_internal.h" #include "hw/pci/msi.h" +#include "sysemu/hw_accel.h" #include "sysemu/kvm.h" #include "target/i386/kvm_i386.h" diff --git a/hw/i386/kvmvapic.c b/hw/i386/kvmvapic.c index b30d1b90c6..2f767b620e 100644 --- a/hw/i386/kvmvapic.c +++ b/hw/i386/kvmvapic.c @@ -14,6 +14,7 @@ #include "exec/exec-all.h" #include "sysemu/sysemu.h" #include "sysemu/cpus.h" +#include "sysemu/hw_accel.h" #include "sysemu/kvm.h" #include "hw/i386/apic_internal.h" #include "hw/sysbus.h" diff --git a/hw/i386/pc.c b/hw/i386/pc.c index 25e8586b48..f721fde0c2 100644 --- a/hw/i386/pc.c +++ b/hw/i386/pc.c @@ -1820,8 +1820,10 @@ static void pc_cpu_plug(HotplugHandler *hotplug_dev, /* increment the number of CPUs */ pcms->boot_cpus++; - if (dev->hotplugged) { + if (pcms->rtc) { rtc_set_cpus_count(pcms->rtc, pcms->boot_cpus); + } + if (pcms->fw_cfg) { fw_cfg_modify_i16(pcms->fw_cfg, FW_CFG_NB_CPUS, pcms->boot_cpus); } diff --git a/hw/intc/apic_common.c b/hw/intc/apic_common.c index d78c885509..3945dfd7b9 100644 --- a/hw/intc/apic_common.c +++ b/hw/intc/apic_common.c @@ -26,6 +26,7 @@ #include "hw/i386/apic.h" #include "hw/i386/apic_internal.h" #include "trace.h" +#include "sysemu/hax.h" #include "sysemu/kvm.h" #include "hw/qdev.h" #include "hw/sysbus.h" @@ -316,7 +317,7 @@ static void apic_common_realize(DeviceState *dev, Error **errp) /* Note: We need at least 1M to map the VAPIC option ROM */ if (!vapic && s->vapic_control & VAPIC_ENABLE_MASK && - ram_size >= 1024 * 1024) { + !hax_enabled() && ram_size >= 1024 * 1024) { vapic = sysbus_create_simple("kvmvapic", -1, NULL); } s->vapic = vapic; diff --git a/hw/intc/ioapic.c b/hw/intc/ioapic.c index ea7ea0bce8..9047b8950a 100644 --- a/hw/intc/ioapic.c +++ b/hw/intc/ioapic.c @@ -33,6 +33,7 @@ #include "target/i386/cpu.h" #include "hw/i386/apic-msidef.h" #include "hw/i386/x86-iommu.h" +#include "trace.h" //#define DEBUG_IOAPIC @@ -115,6 +116,7 @@ static void ioapic_service(IOAPICCommonState *s) s->irr &= ~mask; } else { coalesce = s->ioredtbl[i] & IOAPIC_LVT_REMOTE_IRR; + trace_ioapic_set_remote_irr(i); s->ioredtbl[i] |= IOAPIC_LVT_REMOTE_IRR; } @@ -220,6 +222,8 @@ void ioapic_eoi_broadcast(int vector) uint64_t entry; int i, n; + trace_ioapic_eoi_broadcast(vector); + for (i = 0; i < MAX_IOAPICS; i++) { s = ioapics[i]; if (!s) { @@ -229,6 +233,7 @@ void ioapic_eoi_broadcast(int vector) entry = s->ioredtbl[n]; if ((entry & IOAPIC_LVT_REMOTE_IRR) && (entry & IOAPIC_VECTOR_MASK) == vector) { + trace_ioapic_clear_remote_irr(n, vector); s->ioredtbl[n] = entry & ~IOAPIC_LVT_REMOTE_IRR; if (!(entry & IOAPIC_LVT_MASKED) && (s->irr & (1 << n))) { ioapic_service(s); @@ -256,7 +261,9 @@ ioapic_mem_read(void *opaque, hwaddr addr, unsigned int size) int index; uint32_t val = 0; - switch (addr & 0xff) { + addr &= 0xff; + + switch (addr) { case IOAPIC_IOREGSEL: val = s->ioregsel; break; @@ -286,6 +293,9 @@ ioapic_mem_read(void *opaque, hwaddr addr, unsigned int size) DPRINTF("read: %08x = %08x\n", s->ioregsel, val); break; } + + trace_ioapic_mem_read(addr, size, val); + return val; } @@ -324,7 +334,10 @@ ioapic_mem_write(void *opaque, hwaddr addr, uint64_t val, IOAPICCommonState *s = opaque; int index; - switch (addr & 0xff) { + addr &= 0xff; + trace_ioapic_mem_write(addr, size, val); + + switch (addr) { case IOAPIC_IOREGSEL: s->ioregsel = val; break; @@ -426,6 +439,11 @@ static void ioapic_class_init(ObjectClass *klass, void *data) DeviceClass *dc = DEVICE_CLASS(klass); k->realize = ioapic_realize; + /* + * If APIC is in kernel, we need to update the kernel cache after + * migration, otherwise first 24 gsi routes will be invalid. + */ + k->post_load = ioapic_update_kvm_routes; dc->reset = ioapic_reset_common; dc->props = ioapic_properties; } diff --git a/hw/intc/ioapic_common.c b/hw/intc/ioapic_common.c index 1b7ec5ec20..97c4f9c2df 100644 --- a/hw/intc/ioapic_common.c +++ b/hw/intc/ioapic_common.c @@ -58,7 +58,8 @@ void ioapic_print_redtbl(Monitor *mon, IOAPICCommonState *s) uint32_t remote_irr = 0; int i; - monitor_printf(mon, "ioapic id=0x%02x sel=0x%02x", s->id, s->ioregsel); + monitor_printf(mon, "ioapic ver=0x%x id=0x%02x sel=0x%02x", + s->version, s->id, s->ioregsel); if (s->ioregsel) { monitor_printf(mon, " (redir[%u])\n", (s->ioregsel - IOAPIC_REG_REDTBL_BASE) >> 1); diff --git a/hw/intc/trace-events b/hw/intc/trace-events index 6116df5436..92a6171692 100644 --- a/hw/intc/trace-events +++ b/hw/intc/trace-events @@ -14,6 +14,13 @@ apic_deliver_irq(uint8_t dest, uint8_t dest_mode, uint8_t delivery_mode, uint8_t apic_mem_readl(uint64_t addr, uint32_t val) "%"PRIx64" = %08x" apic_mem_writel(uint64_t addr, uint32_t val) "%"PRIx64" = %08x" +# hw/intc/ioapic.c +ioapic_set_remote_irr(int n) "set remote irr for pin %d" +ioapic_clear_remote_irr(int n, int vector) "clear remote irr for pin %d vector %d" +ioapic_eoi_broadcast(int vector) "EOI broadcast for vector %d" +ioapic_mem_read(uint8_t addr, uint8_t size, uint32_t val) "ioapic mem read addr 0x%"PRIx8" size 0x%"PRIx8" retval 0x%"PRIx32 +ioapic_mem_write(uint8_t addr, uint8_t size, uint32_t val) "ioapic mem write addr 0x%"PRIx8" size 0x%"PRIx8" val 0x%"PRIx32 + # hw/intc/slavio_intctl.c slavio_intctl_mem_readl(uint32_t cpu, uint64_t addr, uint32_t ret) "read cpu %d reg 0x%"PRIx64" = %x" slavio_intctl_mem_writel(uint32_t cpu, uint64_t addr, uint32_t val) "write cpu %d reg 0x%"PRIx64" = %x" diff --git a/hw/misc/vmport.c b/hw/misc/vmport.c index c763811a9f..be40930b8b 100644 --- a/hw/misc/vmport.c +++ b/hw/misc/vmport.c @@ -25,7 +25,7 @@ #include "hw/hw.h" #include "hw/isa/isa.h" #include "hw/i386/pc.h" -#include "sysemu/kvm.h" +#include "sysemu/hw_accel.h" #include "hw/qdev.h" //#define VMPORT_DEBUG diff --git a/hw/ppc/pnv_xscom.c b/hw/ppc/pnv_xscom.c index b82af4f086..38bc85f117 100644 --- a/hw/ppc/pnv_xscom.c +++ b/hw/ppc/pnv_xscom.c @@ -20,7 +20,7 @@ #include "qapi/error.h" #include "hw/hw.h" #include "qemu/log.h" -#include "sysemu/kvm.h" +#include "sysemu/hw_accel.h" #include "target/ppc/cpu.h" #include "hw/sysbus.h" diff --git a/hw/ppc/ppce500_spin.c b/hw/ppc/ppce500_spin.c index cf958a9e00..eb219abdff 100644 --- a/hw/ppc/ppce500_spin.c +++ b/hw/ppc/ppce500_spin.c @@ -29,9 +29,9 @@ #include "qemu/osdep.h" #include "hw/hw.h" -#include "sysemu/sysemu.h" #include "hw/sysbus.h" -#include "sysemu/kvm.h" +#include "sysemu/hw_accel.h" +#include "sysemu/sysemu.h" #include "e500.h" #define MAX_CPUS 32 diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c index 208ef7b110..a642e663d4 100644 --- a/hw/ppc/spapr.c +++ b/hw/ppc/spapr.c @@ -36,7 +36,7 @@ #include "sysemu/device_tree.h" #include "sysemu/block-backend.h" #include "sysemu/cpus.h" -#include "sysemu/kvm.h" +#include "sysemu/hw_accel.h" #include "kvm_ppc.h" #include "migration/migration.h" #include "mmu-hash64.h" diff --git a/hw/ppc/spapr_hcall.c b/hw/ppc/spapr_hcall.c index 9a9bedf1bd..b2a8e48569 100644 --- a/hw/ppc/spapr_hcall.c +++ b/hw/ppc/spapr_hcall.c @@ -1,5 +1,6 @@ #include "qemu/osdep.h" #include "qapi/error.h" +#include "sysemu/hw_accel.h" #include "sysemu/sysemu.h" #include "qemu/log.h" #include "cpu.h" @@ -9,7 +10,6 @@ #include "mmu-hash64.h" #include "cpu-models.h" #include "trace.h" -#include "sysemu/kvm.h" #include "kvm_ppc.h" #include "hw/ppc/spapr_ovec.h" diff --git a/hw/s390x/s390-pci-inst.c b/hw/s390x/s390-pci-inst.c index 405cccd2d0..d2a8c0a083 100644 --- a/hw/s390x/s390-pci-inst.c +++ b/hw/s390x/s390-pci-inst.c @@ -18,6 +18,7 @@ #include "s390-pci-bus.h" #include "exec/memory-internal.h" #include "qemu/error-report.h" +#include "sysemu/hw_accel.h" /* #define DEBUG_S390PCI_INST */ #ifdef DEBUG_S390PCI_INST diff --git a/hw/scsi/megasas.c b/hw/scsi/megasas.c index 67fc1e7893..6233865494 100644 --- a/hw/scsi/megasas.c +++ b/hw/scsi/megasas.c @@ -683,14 +683,14 @@ static int megasas_map_dcmd(MegasasState *s, MegasasCmd *cmd) trace_megasas_dcmd_invalid_sge(cmd->index, cmd->frame->header.sge_count); cmd->iov_size = 0; - return -1; + return -EINVAL; } iov_pa = megasas_sgl_get_addr(cmd, &cmd->frame->dcmd.sgl); iov_size = megasas_sgl_get_len(cmd, &cmd->frame->dcmd.sgl); pci_dma_sglist_init(&cmd->qsg, PCI_DEVICE(s), 1); qemu_sglist_add(&cmd->qsg, iov_pa, iov_size); cmd->iov_size = iov_size; - return cmd->iov_size; + return 0; } static void megasas_finish_dcmd(MegasasCmd *cmd, uint32_t iov_size) @@ -1559,19 +1559,20 @@ static const struct dcmd_cmd_tbl_t { static int megasas_handle_dcmd(MegasasState *s, MegasasCmd *cmd) { - int opcode, len; + int opcode; int retval = 0; + size_t len; const struct dcmd_cmd_tbl_t *cmdptr = dcmd_cmd_tbl; opcode = le32_to_cpu(cmd->frame->dcmd.opcode); trace_megasas_handle_dcmd(cmd->index, opcode); - len = megasas_map_dcmd(s, cmd); - if (len < 0) { + if (megasas_map_dcmd(s, cmd) < 0) { return MFI_STAT_MEMORY_NOT_AVAILABLE; } while (cmdptr->opcode != -1 && cmdptr->opcode != opcode) { cmdptr++; } + len = cmd->iov_size; if (cmdptr->opcode == -1) { trace_megasas_dcmd_unhandled(cmd->index, opcode, len); retval = megasas_dcmd_dummy(s, cmd); diff --git a/hw/scsi/scsi-disk.c b/hw/scsi/scsi-disk.c index bdd1e5f86c..c080888413 100644 --- a/hw/scsi/scsi-disk.c +++ b/hw/scsi/scsi-disk.c @@ -2701,7 +2701,7 @@ static bool scsi_block_is_passthrough(SCSIDiskState *s, uint8_t *buf) * for the number of logical blocks specified in the length * field). For other modes, do not use scatter/gather operation. */ - if ((buf[1] & 6) != 2) { + if ((buf[1] & 6) == 2) { return false; } break; diff --git a/hw/smbios/Makefile.objs b/hw/smbios/Makefile.objs index c3d3753602..23bb2bac07 100644 --- a/hw/smbios/Makefile.objs +++ b/hw/smbios/Makefile.objs @@ -1,2 +1,10 @@ -common-obj-$(CONFIG_SMBIOS) += smbios.o -common-obj-$(call land,$(CONFIG_SMBIOS),$(CONFIG_IPMI)) += smbios_type_38.o +ifeq ($(CONFIG_SMBIOS),y) +common-obj-y += smbios.o +common-obj-$(CONFIG_IPMI) += smbios_type_38.o +common-obj-$(call lnot,$(CONFIG_IPMI)) += smbios_type_38-stub.o +else +common-obj-y += smbios-stub.o +endif + +common-obj-$(CONFIG_ALL) += smbios-stub.o +common-obj-$(CONFIG_ALL) += smbios_type_38-stub.o diff --git a/hw/smbios/smbios-stub.c b/hw/smbios/smbios-stub.c new file mode 100644 index 0000000000..308739410f --- /dev/null +++ b/hw/smbios/smbios-stub.c @@ -0,0 +1,31 @@ +/* + * SMBIOS stubs for platforms that don't support SMBIOS. + * + * Copyright (c) 2010 Isaku Yamahata <yamahata at valinux co jp> + * VA Linux Systems Japan K.K. + * Copyright (c) 2016 Leif Lindholm <leif.lindholm@linaro.org> + * Linaro Ltd. + * + * 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/>. + */ + +#include "qemu/osdep.h" +#include "qapi/qmp/qerror.h" +#include "qmp-commands.h" +#include "hw/smbios/smbios.h" + +void smbios_entry_add(QemuOpts *opts, Error **errp) +{ + error_setg(errp, QERR_UNSUPPORTED); +} diff --git a/hw/smbios/smbios.c b/hw/smbios/smbios.c index 3a96cededd..1a5437a07d 100644 --- a/hw/smbios/smbios.c +++ b/hw/smbios/smbios.c @@ -882,7 +882,7 @@ static void save_opt(const char **dest, QemuOpts *opts, const char *name) } } -void smbios_entry_add(QemuOpts *opts) +void smbios_entry_add(QemuOpts *opts, Error **errp) { const char *val; diff --git a/stubs/smbios_type_38.c b/hw/smbios/smbios_type_38-stub.c index 9528c2c28e..9528c2c28e 100644 --- a/stubs/smbios_type_38.c +++ b/hw/smbios/smbios_type_38-stub.c diff --git a/hw/timer/mc146818rtc.c b/hw/timer/mc146818rtc.c index da209d02f0..637f8722a7 100644 --- a/hw/timer/mc146818rtc.c +++ b/hw/timer/mc146818rtc.c @@ -946,11 +946,23 @@ static Property mc146818rtc_properties[] = { DEFINE_PROP_END_OF_LIST(), }; +static void rtc_resetdev(DeviceState *d) +{ + RTCState *s = MC146818_RTC(d); + + /* Reason: VM do suspend self will set 0xfe + * Reset any values other than 0xfe(Guest suspend case) */ + if (s->cmos_data[0x0f] != 0xfe) { + s->cmos_data[0x0f] = 0x00; + } +} + static void rtc_class_initfn(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); dc->realize = rtc_realizefn; + dc->reset = rtc_resetdev; dc->vmsd = &vmstate_rtc; dc->props = mc146818rtc_properties; /* Reason: needs to be wired up by rtc_init() */ diff --git a/hw/usb/ccid-card-emulated.c b/hw/usb/ccid-card-emulated.c index eceb5f3ee2..99627860a3 100644 --- a/hw/usb/ccid-card-emulated.c +++ b/hw/usb/ccid-card-emulated.c @@ -407,7 +407,7 @@ static int init_event_notifier(EmulatedState *card) DPRINTF(card, 2, "event notifier creation failed\n"); return -1; } - event_notifier_set_handler(&card->notifier, false, card_event_handler); + event_notifier_set_handler(&card->notifier, card_event_handler); return 0; } diff --git a/hw/virtio/Makefile.objs b/hw/virtio/Makefile.objs index 95c4c30ea1..765d363c1f 100644 --- a/hw/virtio/Makefile.objs +++ b/hw/virtio/Makefile.objs @@ -1,3 +1,4 @@ +ifeq ($(CONFIG_VIRTIO),y) common-obj-y += virtio-rng.o common-obj-$(CONFIG_VIRTIO_PCI) += virtio-pci.o common-obj-y += virtio-bus.o @@ -5,7 +6,10 @@ common-obj-y += virtio-mmio.o obj-y += virtio.o virtio-balloon.o obj-$(CONFIG_LINUX) += vhost.o vhost-backend.o vhost-user.o - obj-$(CONFIG_VHOST_VSOCK) += vhost-vsock.o obj-y += virtio-crypto.o obj-$(CONFIG_VIRTIO_PCI) += virtio-crypto-pci.o +endif + +common-obj-$(call lnot,$(CONFIG_LINUX)) += vhost-stub.o +common-obj-$(CONFIG_ALL) += vhost-stub.o diff --git a/stubs/vhost.c b/hw/virtio/vhost-stub.c index 2d76cdebdc..2d76cdebdc 100644 --- a/stubs/vhost.c +++ b/hw/virtio/vhost-stub.c diff --git a/hw/virtio/virtio.c b/hw/virtio/virtio.c index ac9b99b928..cc17b97899 100644 --- a/hw/virtio/virtio.c +++ b/hw/virtio/virtio.c @@ -2082,10 +2082,10 @@ void virtio_queue_set_guest_notifier_fd_handler(VirtQueue *vq, bool assign, bool with_irqfd) { if (assign && !with_irqfd) { - event_notifier_set_handler(&vq->guest_notifier, false, + event_notifier_set_handler(&vq->guest_notifier, virtio_queue_guest_notifier_read); } else { - event_notifier_set_handler(&vq->guest_notifier, false, NULL); + event_notifier_set_handler(&vq->guest_notifier, NULL); } if (!assign) { /* Test and clear notifier before closing it, @@ -2257,7 +2257,7 @@ static int virtio_device_start_ioeventfd_impl(VirtIODevice *vdev) err = r; goto assign_error; } - event_notifier_set_handler(&vq->host_notifier, true, + event_notifier_set_handler(&vq->host_notifier, virtio_queue_host_notifier_read); } @@ -2278,7 +2278,7 @@ assign_error: continue; } - event_notifier_set_handler(&vq->host_notifier, true, NULL); + event_notifier_set_handler(&vq->host_notifier, NULL); r = virtio_bus_set_host_notifier(qbus, n, false); assert(r >= 0); } @@ -2304,7 +2304,7 @@ static void virtio_device_stop_ioeventfd_impl(VirtIODevice *vdev) if (!virtio_queue_get_num(vdev, n)) { continue; } - event_notifier_set_handler(&vq->host_notifier, true, NULL); + event_notifier_set_handler(&vq->host_notifier, NULL); r = virtio_bus_set_host_notifier(qbus, n, false); assert(r >= 0); } diff --git a/include/exec/memory.h b/include/exec/memory.h index bec9756667..a10044f08f 100644 --- a/include/exec/memory.h +++ b/include/exec/memory.h @@ -16,16 +16,12 @@ #ifndef CONFIG_USER_ONLY -#define DIRTY_MEMORY_VGA 0 -#define DIRTY_MEMORY_CODE 1 -#define DIRTY_MEMORY_MIGRATION 2 -#define DIRTY_MEMORY_NUM 3 /* num of dirty bits */ - #include "exec/cpu-common.h" #ifndef CONFIG_USER_ONLY #include "exec/hwaddr.h" #endif #include "exec/memattrs.h" +#include "exec/ramlist.h" #include "qemu/queue.h" #include "qemu/int128.h" #include "qemu/notify.h" diff --git a/include/exec/ram_addr.h b/include/exec/ram_addr.h index 54d7108a9e..3e79466a44 100644 --- a/include/exec/ram_addr.h +++ b/include/exec/ram_addr.h @@ -21,6 +21,7 @@ #ifndef CONFIG_USER_ONLY #include "hw/xen/xen.h" +#include "exec/ramlist.h" struct RAMBlock { struct rcu_head rcu; @@ -35,6 +36,7 @@ struct RAMBlock { char idstr[256]; /* RCU-enabled, writes protected by the ramlist lock */ QLIST_ENTRY(RAMBlock) next; + QLIST_HEAD(, RAMBlockNotifier) ramblock_notifiers; int fd; size_t page_size; }; @@ -50,51 +52,7 @@ static inline void *ramblock_ptr(RAMBlock *block, ram_addr_t offset) return (char *)block->host + offset; } -/* The dirty memory bitmap is split into fixed-size blocks to allow growth - * under RCU. The bitmap for a block can be accessed as follows: - * - * rcu_read_lock(); - * - * DirtyMemoryBlocks *blocks = - * atomic_rcu_read(&ram_list.dirty_memory[DIRTY_MEMORY_MIGRATION]); - * - * ram_addr_t idx = (addr >> TARGET_PAGE_BITS) / DIRTY_MEMORY_BLOCK_SIZE; - * unsigned long *block = blocks.blocks[idx]; - * ...access block bitmap... - * - * rcu_read_unlock(); - * - * Remember to check for the end of the block when accessing a range of - * addresses. Move on to the next block if you reach the end. - * - * Organization into blocks allows dirty memory to grow (but not shrink) under - * RCU. When adding new RAMBlocks requires the dirty memory to grow, a new - * DirtyMemoryBlocks array is allocated with pointers to existing blocks kept - * the same. Other threads can safely access existing blocks while dirty - * memory is being grown. When no threads are using the old DirtyMemoryBlocks - * anymore it is freed by RCU (but the underlying blocks stay because they are - * pointed to from the new DirtyMemoryBlocks). - */ -#define DIRTY_MEMORY_BLOCK_SIZE ((ram_addr_t)256 * 1024 * 8) -typedef struct { - struct rcu_head rcu; - unsigned long *blocks[]; -} DirtyMemoryBlocks; - -typedef struct RAMList { - QemuMutex mutex; - RAMBlock *mru_block; - /* RCU-enabled, writes protected by the ramlist lock. */ - QLIST_HEAD(, RAMBlock) blocks; - DirtyMemoryBlocks *dirty_memory[DIRTY_MEMORY_NUM]; - uint32_t version; -} RAMList; -extern RAMList ram_list; - ram_addr_t last_ram_offset(void); -void qemu_mutex_lock_ramlist(void); -void qemu_mutex_unlock_ramlist(void); - RAMBlock *qemu_ram_alloc_from_file(ram_addr_t size, MemoryRegion *mr, bool share, const char *mem_path, Error **errp); diff --git a/include/exec/ramlist.h b/include/exec/ramlist.h new file mode 100644 index 0000000000..c59880de82 --- /dev/null +++ b/include/exec/ramlist.h @@ -0,0 +1,72 @@ +#ifndef RAMLIST_H +#define RAMLIST_H + +#include "qemu/queue.h" +#include "qemu/thread.h" +#include "qemu/rcu.h" + +typedef struct RAMBlockNotifier RAMBlockNotifier; + +#define DIRTY_MEMORY_VGA 0 +#define DIRTY_MEMORY_CODE 1 +#define DIRTY_MEMORY_MIGRATION 2 +#define DIRTY_MEMORY_NUM 3 /* num of dirty bits */ + +/* The dirty memory bitmap is split into fixed-size blocks to allow growth + * under RCU. The bitmap for a block can be accessed as follows: + * + * rcu_read_lock(); + * + * DirtyMemoryBlocks *blocks = + * atomic_rcu_read(&ram_list.dirty_memory[DIRTY_MEMORY_MIGRATION]); + * + * ram_addr_t idx = (addr >> TARGET_PAGE_BITS) / DIRTY_MEMORY_BLOCK_SIZE; + * unsigned long *block = blocks.blocks[idx]; + * ...access block bitmap... + * + * rcu_read_unlock(); + * + * Remember to check for the end of the block when accessing a range of + * addresses. Move on to the next block if you reach the end. + * + * Organization into blocks allows dirty memory to grow (but not shrink) under + * RCU. When adding new RAMBlocks requires the dirty memory to grow, a new + * DirtyMemoryBlocks array is allocated with pointers to existing blocks kept + * the same. Other threads can safely access existing blocks while dirty + * memory is being grown. When no threads are using the old DirtyMemoryBlocks + * anymore it is freed by RCU (but the underlying blocks stay because they are + * pointed to from the new DirtyMemoryBlocks). + */ +#define DIRTY_MEMORY_BLOCK_SIZE ((ram_addr_t)256 * 1024 * 8) +typedef struct { + struct rcu_head rcu; + unsigned long *blocks[]; +} DirtyMemoryBlocks; + +typedef struct RAMList { + QemuMutex mutex; + RAMBlock *mru_block; + /* RCU-enabled, writes protected by the ramlist lock. */ + QLIST_HEAD(, RAMBlock) blocks; + DirtyMemoryBlocks *dirty_memory[DIRTY_MEMORY_NUM]; + uint32_t version; + QLIST_HEAD(, RAMBlockNotifier) ramblock_notifiers; +} RAMList; +extern RAMList ram_list; + +void qemu_mutex_lock_ramlist(void); +void qemu_mutex_unlock_ramlist(void); + +struct RAMBlockNotifier { + void (*ram_block_added)(RAMBlockNotifier *n, void *host, size_t size); + void (*ram_block_removed)(RAMBlockNotifier *n, void *host, size_t size); + QLIST_ENTRY(RAMBlockNotifier) next; +}; + +void ram_block_notifier_add(RAMBlockNotifier *n); +void ram_block_notifier_remove(RAMBlockNotifier *n); +void ram_block_notify_add(void *host, size_t size); +void ram_block_notify_remove(void *host, size_t size); + + +#endif /* RAMLIST_H */ diff --git a/include/hw/hw.h b/include/hw/hw.h index 3669ebd916..e22d4ce5fa 100644 --- a/include/hw/hw.h +++ b/include/hw/hw.h @@ -12,11 +12,7 @@ #include "hw/irq.h" #include "migration/vmstate.h" #include "qemu/module.h" - -typedef void QEMUResetHandler(void *opaque); - -void qemu_register_reset(QEMUResetHandler *func, void *opaque); -void qemu_unregister_reset(QEMUResetHandler *func, void *opaque); +#include "sysemu/reset.h" void QEMU_NORETURN hw_error(const char *fmt, ...) GCC_FMT_ATTR(1, 2); diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h index 230e9e70c5..738bfd6c60 100644 --- a/include/hw/i386/pc.h +++ b/include/hw/i386/pc.h @@ -376,15 +376,14 @@ bool e820_get_entry(int, uint32_t, uint64_t *, uint64_t *); #define PC_COMPAT_2_8 \ HW_COMPAT_2_8 \ - - -#define PC_COMPAT_2_7 \ - HW_COMPAT_2_7 \ {\ .driver = "kvmclock",\ .property = "x-mach-use-reliable-get-clock",\ .value = "off",\ },\ + +#define PC_COMPAT_2_7 \ + HW_COMPAT_2_7 \ {\ .driver = TYPE_X86_CPU,\ .property = "l3-cache",\ diff --git a/include/hw/smbios/smbios.h b/include/hw/smbios/smbios.h index 1cd53cc58c..31e8d5f47e 100644 --- a/include/hw/smbios/smbios.h +++ b/include/hw/smbios/smbios.h @@ -257,7 +257,7 @@ struct smbios_type_127 { struct smbios_structure_header header; } QEMU_PACKED; -void smbios_entry_add(QemuOpts *opts); +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, diff --git a/include/qemu/event_notifier.h b/include/qemu/event_notifier.h index e326990db4..599c99f1a5 100644 --- a/include/qemu/event_notifier.h +++ b/include/qemu/event_notifier.h @@ -34,9 +34,6 @@ int event_notifier_init(EventNotifier *, int active); void event_notifier_cleanup(EventNotifier *); int event_notifier_set(EventNotifier *); int event_notifier_test_and_clear(EventNotifier *); -int event_notifier_set_handler(EventNotifier *, - bool is_external, - EventNotifierHandler *); #ifdef CONFIG_POSIX void event_notifier_init_fd(EventNotifier *, int fd); diff --git a/include/qemu/main-loop.h b/include/qemu/main-loop.h index a9d4f23cd9..d7e24af78d 100644 --- a/include/qemu/main-loop.h +++ b/include/qemu/main-loop.h @@ -203,6 +203,21 @@ void qemu_set_fd_handler(int fd, IOHandler *fd_write, void *opaque); + +/** + * event_notifier_set_handler: Register an EventNotifier with the main loop + * + * This function tells the main loop to wake up whenever the + * #EventNotifier was set. + * + * @e: The #EventNotifier to be observed. + * + * @handler: A level-triggered callback that is fired when @e + * has been set. @e is passed to it as a parameter. + */ +void event_notifier_set_handler(EventNotifier *e, + EventNotifierHandler *handler); + GSource *iohandler_get_g_source(void); AioContext *iohandler_get_aio_context(void); #ifdef CONFIG_POSIX diff --git a/include/qom/cpu.h b/include/qom/cpu.h index 3f79a8e955..ca4d0fb1b4 100644 --- a/include/qom/cpu.h +++ b/include/qom/cpu.h @@ -227,6 +227,8 @@ struct CPUWatchpoint { struct KVMState; struct kvm_run; +struct hax_vcpu_state; + #define TB_JMP_CACHE_BITS 12 #define TB_JMP_CACHE_SIZE (1 << TB_JMP_CACHE_BITS) @@ -392,6 +394,9 @@ struct CPUState { (absolute value) offset as small as possible. This reduces code size, especially for hosts without large memory offsets. */ uint32_t tcg_exit_req; + + bool hax_vcpu_dirty; + struct hax_vcpu_state *hax_vcpu; }; QTAILQ_HEAD(CPUTailQ, CPUState); diff --git a/include/sysemu/arch_init.h b/include/sysemu/arch_init.h index 1c9dad1b72..20b01e3004 100644 --- a/include/sysemu/arch_init.h +++ b/include/sysemu/arch_init.h @@ -28,8 +28,6 @@ enum { extern const uint32_t arch_type; void select_soundhw(const char *optarg); -void do_acpitable_option(const QemuOpts *opts); -void do_smbios_option(QemuOpts *opts); void audio_init(void); int kvm_available(void); int xen_available(void); diff --git a/include/sysemu/hax.h b/include/sysemu/hax.h new file mode 100644 index 0000000000..d9f023918e --- /dev/null +++ b/include/sysemu/hax.h @@ -0,0 +1,56 @@ +/* + * QEMU HAXM support + * + * Copyright IBM, Corp. 2008 + * + * Authors: + * Anthony Liguori <aliguori@us.ibm.com> + * + * Copyright (c) 2011 Intel Corporation + * Written by: + * Jiang Yunhong<yunhong.jiang@intel.com> + * Xin Xiaohui<xiaohui.xin@intel.com> + * Zhang Xiantao<xiantao.zhang@intel.com> + * + * Copyright 2016 Google, 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. + * + */ + +#ifndef QEMU_HAX_H +#define QEMU_HAX_H + +#include "config-host.h" +#include "qemu-common.h" + +int hax_sync_vcpus(void); +int hax_init_vcpu(CPUState *cpu); +int hax_smp_cpu_exec(CPUState *cpu); +int hax_populate_ram(uint64_t va, uint32_t size); + +void hax_cpu_synchronize_state(CPUState *cpu); +void hax_cpu_synchronize_post_reset(CPUState *cpu); +void hax_cpu_synchronize_post_init(CPUState *cpu); + +#ifdef CONFIG_HAX + +int hax_enabled(void); + +#include "hw/hw.h" +#include "qemu/bitops.h" +#include "exec/memory.h" +int hax_vcpu_destroy(CPUState *cpu); +void hax_raise_event(CPUState *cpu); +void hax_reset_vcpu_state(void *opaque); +#include "target/i386/hax-interface.h" +#include "target/i386/hax-i386.h" + +#else /* CONFIG_HAX */ + +#define hax_enabled() (0) + +#endif /* CONFIG_HAX */ + +#endif /* QEMU_HAX_H */ diff --git a/include/sysemu/hw_accel.h b/include/sysemu/hw_accel.h new file mode 100644 index 0000000000..c9b3105bc7 --- /dev/null +++ b/include/sysemu/hw_accel.h @@ -0,0 +1,48 @@ +/* + * QEMU Hardware accelertors support + * + * Copyright 2016 Google, 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. + * + */ + +#ifndef QEMU_HW_ACCEL_H +#define QEMU_HW_ACCEL_H + +#include "qom/cpu.h" +#include "sysemu/hax.h" +#include "sysemu/kvm.h" + +static inline void cpu_synchronize_state(CPUState *cpu) +{ + if (kvm_enabled()) { + kvm_cpu_synchronize_state(cpu); + } + if (hax_enabled()) { + hax_cpu_synchronize_state(cpu); + } +} + +static inline void cpu_synchronize_post_reset(CPUState *cpu) +{ + if (kvm_enabled()) { + kvm_cpu_synchronize_post_reset(cpu); + } + if (hax_enabled()) { + hax_cpu_synchronize_post_reset(cpu); + } +} + +static inline void cpu_synchronize_post_init(CPUState *cpu) +{ + if (kvm_enabled()) { + kvm_cpu_synchronize_post_init(cpu); + } + if (hax_enabled()) { + hax_cpu_synchronize_post_init(cpu); + } +} + +#endif /* QEMU_HW_ACCEL_H */ diff --git a/include/sysemu/kvm.h b/include/sysemu/kvm.h index df67cc0672..3045ee7678 100644 --- a/include/sysemu/kvm.h +++ b/include/sysemu/kvm.h @@ -461,29 +461,6 @@ void kvm_cpu_synchronize_state(CPUState *cpu); void kvm_cpu_synchronize_post_reset(CPUState *cpu); void kvm_cpu_synchronize_post_init(CPUState *cpu); -/* generic hooks - to be moved/refactored once there are more users */ - -static inline void cpu_synchronize_state(CPUState *cpu) -{ - if (kvm_enabled()) { - kvm_cpu_synchronize_state(cpu); - } -} - -static inline void cpu_synchronize_post_reset(CPUState *cpu) -{ - if (kvm_enabled()) { - kvm_cpu_synchronize_post_reset(cpu); - } -} - -static inline void cpu_synchronize_post_init(CPUState *cpu) -{ - if (kvm_enabled()) { - kvm_cpu_synchronize_post_init(cpu); - } -} - /** * kvm_irqchip_add_msi_route - Add MSI route for specific vector * @s: KVM state diff --git a/include/sysemu/reset.h b/include/sysemu/reset.h new file mode 100644 index 0000000000..0b0d6d7598 --- /dev/null +++ b/include/sysemu/reset.h @@ -0,0 +1,10 @@ +#ifndef QEMU_SYSEMU_RESET_H +#define QEMU_SYSEMU_RESET_H + +typedef void QEMUResetHandler(void *opaque); + +void qemu_register_reset(QEMUResetHandler *func, void *opaque); +void qemu_unregister_reset(QEMUResetHandler *func, void *opaque); +void qemu_devices_reset(void); + +#endif diff --git a/include/sysemu/sysemu.h b/include/sysemu/sysemu.h index cccde56454..ff8ffb5e47 100644 --- a/include/sysemu/sysemu.h +++ b/include/sysemu/sysemu.h @@ -63,7 +63,6 @@ void qemu_system_vmstop_request_prepare(void); int qemu_shutdown_requested_get(void); int qemu_reset_requested_get(void); void qemu_system_killed(int signal, pid_t pid); -void qemu_devices_reset(void); void qemu_system_reset(bool report); void qemu_system_guest_panicked(void); size_t qemu_target_page_bits(void); diff --git a/iohandler.c b/iohandler.c index eb625d93dd..623b55b9ec 100644 --- a/iohandler.c +++ b/iohandler.c @@ -66,6 +66,14 @@ void qemu_set_fd_handler(int fd, fd_read, fd_write, NULL, opaque); } +void event_notifier_set_handler(EventNotifier *e, + EventNotifierHandler *handler) +{ + iohandler_init(); + aio_set_event_notifier(iohandler_ctx, e, false, + handler, NULL); +} + /* reaping of zombies. right now we're not passing the status to anyone, but it would be possible to add a callback. */ #ifndef _WIN32 diff --git a/migration/Makefile.objs b/migration/Makefile.objs index 3f3e237142..480dd493a9 100644 --- a/migration/Makefile.objs +++ b/migration/Makefile.objs @@ -1,7 +1,6 @@ common-obj-y += migration.o socket.o fd.o exec.o common-obj-y += tls.o -common-obj-y += colo-comm.o -common-obj-$(CONFIG_COLO) += colo.o colo-failover.o +common-obj-y += colo-comm.o colo.o colo-failover.o common-obj-y += vmstate.o common-obj-y += qemu-file.o common-obj-y += qemu-file-channel.o @@ -50,7 +50,7 @@ #include "sysemu/balloon.h" #include "qemu/timer.h" #include "migration/migration.h" -#include "sysemu/kvm.h" +#include "sysemu/hw_accel.h" #include "qemu/acl.h" #include "sysemu/tpm.h" #include "qapi/qmp/qerror.h" @@ -25,6 +25,7 @@ #include "qemu/osdep.h" #include "sysemu/numa.h" #include "exec/cpu-common.h" +#include "exec/ramlist.h" #include "qemu/bitmap.h" #include "qom/cpu.h" #include "qemu/error-report.h" @@ -572,3 +573,31 @@ int numa_get_node_for_cpu(int idx) } return i; } + +void ram_block_notifier_add(RAMBlockNotifier *n) +{ + QLIST_INSERT_HEAD(&ram_list.ramblock_notifiers, n, next); +} + +void ram_block_notifier_remove(RAMBlockNotifier *n) +{ + QLIST_REMOVE(n, next); +} + +void ram_block_notify_add(void *host, size_t size) +{ + RAMBlockNotifier *notifier; + + QLIST_FOREACH(notifier, &ram_list.ramblock_notifiers, next) { + notifier->ram_block_added(notifier, host, size); + } +} + +void ram_block_notify_remove(void *host, size_t size) +{ + RAMBlockNotifier *notifier; + + QLIST_FOREACH(notifier, &ram_list.ramblock_notifiers, next) { + notifier->ram_block_removed(notifier, host, size); + } +} diff --git a/qemu-char.c b/qemu-char.c index 2c9940cea4..676944a765 100644 --- a/qemu-char.c +++ b/qemu-char.c @@ -499,7 +499,7 @@ void qemu_chr_fe_printf(CharBackend *be, const char *fmt, ...) static void remove_fd_in_watch(CharDriverState *chr); static void mux_chr_set_handlers(CharDriverState *chr, GMainContext *context); -static void mux_set_focus(MuxDriver *d, int focus); +static void mux_set_focus(CharDriverState *chr, int focus); static int null_chr_write(CharDriverState *chr, const uint8_t *buf, int len) { @@ -666,7 +666,7 @@ static int mux_proc_byte(CharDriverState *chr, MuxDriver *d, int ch) case 'c': assert(d->mux_cnt > 0); /* handler registered with first fe */ /* Switch to the next registered device */ - mux_set_focus(d, (d->focus + 1) % d->mux_cnt); + mux_set_focus(chr, (d->focus + 1) % d->mux_cnt); break; case 't': d->timestamps = !d->timestamps; @@ -826,8 +826,10 @@ static void mux_chr_set_handlers(CharDriverState *chr, GMainContext *context) context, true); } -static void mux_set_focus(MuxDriver *d, int focus) +static void mux_set_focus(CharDriverState *chr, int focus) { + MuxDriver *d = chr->opaque; + assert(focus >= 0); assert(focus < d->mux_cnt); @@ -836,6 +838,7 @@ static void mux_set_focus(MuxDriver *d, int focus) } d->focus = focus; + chr->be = d->backends[focus]; mux_chr_send_event(d, d->focus, CHR_EVENT_MUX_IN); } @@ -935,7 +938,9 @@ void qemu_chr_fe_deinit(CharBackend *b) if (b->chr) { qemu_chr_fe_set_handlers(b, NULL, NULL, NULL, NULL, NULL, true); - b->chr->be = NULL; + if (b->chr->be == b) { + b->chr->be = NULL; + } if (b->chr->is_mux) { MuxDriver *d = b->chr->opaque; d->backends[b->tag] = NULL; @@ -999,7 +1004,7 @@ void qemu_chr_fe_take_focus(CharBackend *b) } if (b->chr->is_mux) { - mux_set_focus(b->chr->opaque, b->tag); + mux_set_focus(b->chr, b->tag); } } diff --git a/qemu-options-wrapper.h b/qemu-options-wrapper.h index 13bfea0294..4d7aeb1352 100644 --- a/qemu-options-wrapper.h +++ b/qemu-options-wrapper.h @@ -14,7 +14,7 @@ #define ARCHHEADING(text, arch_mask) \ if ((arch_mask) & arch_type) \ - puts(stringify(text)); + puts(stringify(text) ":"); #define DEFHEADING(text) ARCHHEADING(text, QEMU_ARCH_ALL) diff --git a/qemu-options.hx b/qemu-options.hx index c534a2f7f9..80df52651a 100644 --- a/qemu-options.hx +++ b/qemu-options.hx @@ -6,7 +6,7 @@ HXCOMM construct option structures, enums and help message for specified HXCOMM architectures. HXCOMM HXCOMM can be used for comments, discarded from both texi and C -DEFHEADING(Standard options:) +DEFHEADING(Standard options) STEXI @table @option ETEXI @@ -468,7 +468,7 @@ STEXI ETEXI DEFHEADING() -DEFHEADING(Block device options:) +DEFHEADING(Block device options) STEXI @table @option ETEXI @@ -856,7 +856,7 @@ STEXI ETEXI DEFHEADING() -DEFHEADING(USB options:) +DEFHEADING(USB options) STEXI @table @option ETEXI @@ -920,7 +920,7 @@ STEXI ETEXI DEFHEADING() -DEFHEADING(Display options:) +DEFHEADING(Display options) STEXI @table @option ETEXI @@ -1449,7 +1449,7 @@ STEXI ETEXI ARCHHEADING(, QEMU_ARCH_I386) -ARCHHEADING(i386 target only:, QEMU_ARCH_I386) +ARCHHEADING(i386 target only, QEMU_ARCH_I386) STEXI @table @option ETEXI @@ -1565,7 +1565,7 @@ STEXI ETEXI DEFHEADING() -DEFHEADING(Network options:) +DEFHEADING(Network options) STEXI @table @option ETEXI @@ -2146,7 +2146,7 @@ STEXI ETEXI DEFHEADING() -DEFHEADING(Character device options:) +DEFHEADING(Character device options) STEXI The general form of a character device option is: @@ -2481,7 +2481,7 @@ STEXI ETEXI DEFHEADING() -DEFHEADING(Device URL Syntax:) +DEFHEADING(Device URL Syntax) STEXI In addition to using normal file images for the emulated storage devices, @@ -2711,7 +2711,7 @@ STEXI @end table ETEXI -DEFHEADING(Bluetooth(R) options:) +DEFHEADING(Bluetooth(R) options) STEXI @table @option ETEXI @@ -2787,7 +2787,7 @@ ETEXI DEFHEADING() #ifdef CONFIG_TPM -DEFHEADING(TPM device options:) +DEFHEADING(TPM device options) DEF("tpmdev", HAS_ARG, QEMU_OPTION_tpmdev, \ "-tpmdev passthrough,id=id[,path=path][,cancel-path=path]\n" @@ -2861,7 +2861,7 @@ DEFHEADING() #endif -DEFHEADING(Linux/Multiboot boot specific:) +DEFHEADING(Linux/Multiboot boot specific) STEXI When using these options, you can use a given Linux or Multiboot @@ -2917,7 +2917,7 @@ STEXI ETEXI DEFHEADING() -DEFHEADING(Debug/Expert options:) +DEFHEADING(Debug/Expert options) STEXI @table @option ETEXI @@ -3280,6 +3280,17 @@ Enable KVM full virtualization support. This option is only available if KVM support is enabled when compiling. ETEXI +DEF("enable-hax", 0, QEMU_OPTION_enable_hax, \ + "-enable-hax enable HAX virtualization support\n", QEMU_ARCH_I386) +STEXI +@item -enable-hax +@findex -enable-hax +Enable HAX (Hardware-based Acceleration eXecution) support. This option +is only available if HAX support is enabled when compiling. HAX is only +applicable to MAC and Windows platform, and thus does not conflict with +KVM. +ETEXI + DEF("xen-domid", HAS_ARG, QEMU_OPTION_xen_domid, "-xen-domid id specify xen guest domain id\n", QEMU_ARCH_ALL) DEF("xen-create", 0, QEMU_OPTION_xen_create, @@ -3775,7 +3786,14 @@ Dump json-encoded vmstate information for current machine type to file in @var{file} ETEXI +STEXI +@end table +ETEXI +DEFHEADING() DEFHEADING(Generic object creation) +STEXI +@table @option +ETEXI DEF("object", HAS_ARG, QEMU_OPTION_object, "-object TYPENAME[,PROP1=VALUE1,...]\n" @@ -22,7 +22,7 @@ #include "qapi/error.h" #include "qemu-common.h" #include "qom/cpu.h" -#include "sysemu/kvm.h" +#include "sysemu/hw_accel.h" #include "qemu/notify.h" #include "qemu/log.h" #include "exec/log.h" diff --git a/qom/object.c b/qom/object.c index 7a05e35ed9..760fafb0dc 100644 --- a/qom/object.c +++ b/qom/object.c @@ -272,6 +272,12 @@ static void type_initialize(TypeImpl *ti) ti->class_size = type_class_get_size(ti); ti->instance_size = type_object_get_size(ti); + /* Any type with zero instance_size is implicitly abstract. + * This means interface types are all abstract. + */ + if (ti->instance_size == 0) { + ti->abstract = true; + } ti->class = g_malloc0(ti->class_size); diff --git a/scripts/hxtool b/scripts/hxtool index 04f7d7b0ed..5468cd7782 100644 --- a/scripts/hxtool +++ b/scripts/hxtool @@ -16,6 +16,13 @@ hxtoh() done } +print_texi_heading() +{ + if test "$*" != ""; then + printf "@subsection %s\n" "$*" + fi +} + hxtotexi() { flag=0 @@ -45,10 +52,10 @@ hxtotexi() fi ;; DEFHEADING*) - printf '%s\n' "$(expr "$str" : "DEFHEADING(\(.*\))")" + print_texi_heading "$(expr "$str" : "DEFHEADING(\(.*\))")" ;; ARCHHEADING*) - printf '%s\n' "$(expr "$str" : "ARCHHEADING(\(.*\),.*)")" + print_texi_heading "$(expr "$str" : "ARCHHEADING(\(.*\),.*)")" ;; *) test $flag -eq 1 && printf '%s\n' "$str" diff --git a/stubs/Makefile.objs b/stubs/Makefile.objs index 2b5bb74fce..a187295161 100644 --- a/stubs/Makefile.objs +++ b/stubs/Makefile.objs @@ -10,26 +10,18 @@ stub-obj-y += cpu-get-clock.o stub-obj-y += cpu-get-icount.o stub-obj-y += dump.o stub-obj-y += error-printf.o -stub-obj-y += fdset-add-fd.o -stub-obj-y += fdset-find-fd.o -stub-obj-y += fdset-get-fd.o -stub-obj-y += fdset-remove-fd.o +stub-obj-y += fdset.o stub-obj-y += gdbstub.o -stub-obj-y += get-fd.o -stub-obj-y += get-next-serial.o stub-obj-y += get-vm-name.o stub-obj-y += iothread.o stub-obj-y += iothread-lock.o stub-obj-y += is-daemonized.o stub-obj-y += machine-init-done.o stub-obj-y += migr-blocker.o -stub-obj-y += mon-is-qmp.o -stub-obj-y += monitor-init.o +stub-obj-y += monitor.o stub-obj-y += notify-event.o stub-obj-y += qtest.o stub-obj-y += replay.o -stub-obj-y += replay-user.o -stub-obj-y += reset.o stub-obj-y += runstate-check.o stub-obj-y += set-fd-handler.o stub-obj-y += slirp.o @@ -39,14 +31,7 @@ stub-obj-y += uuid.o stub-obj-y += vm-stop.o stub-obj-y += vmstate.o stub-obj-$(CONFIG_WIN32) += fd-register.o -stub-obj-y += cpus.o -stub-obj-y += kvm.o stub-obj-y += qmp_pc_dimm_device_list.o stub-obj-y += target-monitor-defs.o stub-obj-y += target-get-monitor-def.o -stub-obj-y += vhost.o -stub-obj-y += iohandler.o -stub-obj-y += smbios_type_38.o -stub-obj-y += ipmi.o stub-obj-y += pc_madt_cpu_entry.o -stub-obj-y += migration-colo.o diff --git a/stubs/cpus.c b/stubs/cpus.c deleted file mode 100644 index e19272297a..0000000000 --- a/stubs/cpus.c +++ /dev/null @@ -1,11 +0,0 @@ -#include "qemu/osdep.h" -#include "qemu-common.h" -#include "qom/cpu.h" - -void cpu_resume(CPUState *cpu) -{ -} - -void qemu_init_vcpu(CPUState *cpu) -{ -} diff --git a/stubs/fdset-add-fd.c b/stubs/fdset-add-fd.c deleted file mode 100644 index bf9e60aed5..0000000000 --- a/stubs/fdset-add-fd.c +++ /dev/null @@ -1,8 +0,0 @@ -#include "qemu/osdep.h" -#include "qemu-common.h" -#include "monitor/monitor.h" - -int monitor_fdset_dup_fd_add(int64_t fdset_id, int dup_fd) -{ - return -1; -} diff --git a/stubs/fdset-find-fd.c b/stubs/fdset-find-fd.c deleted file mode 100644 index 1d9caf37ec..0000000000 --- a/stubs/fdset-find-fd.c +++ /dev/null @@ -1,8 +0,0 @@ -#include "qemu/osdep.h" -#include "qemu-common.h" -#include "monitor/monitor.h" - -int monitor_fdset_dup_fd_find(int dup_fd) -{ - return -1; -} diff --git a/stubs/fdset-get-fd.c b/stubs/fdset-get-fd.c deleted file mode 100644 index 5325044b5a..0000000000 --- a/stubs/fdset-get-fd.c +++ /dev/null @@ -1,8 +0,0 @@ -#include "qemu/osdep.h" -#include "qemu-common.h" -#include "monitor/monitor.h" - -int monitor_fdset_get_fd(int64_t fdset_id, int flags) -{ - return -1; -} diff --git a/stubs/fdset-remove-fd.c b/stubs/fdset-remove-fd.c deleted file mode 100644 index 47ea297210..0000000000 --- a/stubs/fdset-remove-fd.c +++ /dev/null @@ -1,7 +0,0 @@ -#include "qemu/osdep.h" -#include "qemu-common.h" -#include "monitor/monitor.h" - -void monitor_fdset_dup_fd_remove(int dupfd) -{ -} diff --git a/stubs/fdset.c b/stubs/fdset.c new file mode 100644 index 0000000000..6020cf28c8 --- /dev/null +++ b/stubs/fdset.c @@ -0,0 +1,22 @@ +#include "qemu/osdep.h" +#include "qemu-common.h" +#include "monitor/monitor.h" + +int monitor_fdset_dup_fd_add(int64_t fdset_id, int dup_fd) +{ + return -1; +} + +int monitor_fdset_dup_fd_find(int dup_fd) +{ + return -1; +} + +int monitor_fdset_get_fd(int64_t fdset_id, int flags) +{ + return -1; +} + +void monitor_fdset_dup_fd_remove(int dupfd) +{ +} diff --git a/stubs/get-next-serial.c b/stubs/get-next-serial.c deleted file mode 100644 index 6ff6a6d3b2..0000000000 --- a/stubs/get-next-serial.c +++ /dev/null @@ -1,4 +0,0 @@ -#include "qemu/osdep.h" -#include "qemu-common.h" - -CharDriverState *serial_hds[0]; diff --git a/stubs/iohandler.c b/stubs/iohandler.c deleted file mode 100644 index 22b0ee5b0a..0000000000 --- a/stubs/iohandler.c +++ /dev/null @@ -1,8 +0,0 @@ -#include "qemu/osdep.h" -#include "qemu-common.h" -#include "qemu/main-loop.h" - -AioContext *iohandler_get_aio_context(void) -{ - abort(); -} diff --git a/stubs/kvm.c b/stubs/kvm.c deleted file mode 100644 index ddd620499d..0000000000 --- a/stubs/kvm.c +++ /dev/null @@ -1,8 +0,0 @@ -#include "qemu/osdep.h" -#include "qemu-common.h" -#include "sysemu/kvm.h" - -int kvm_arch_irqchip_create(MachineState *ms, KVMState *s) -{ - return 0; -} diff --git a/stubs/migration-colo.c b/stubs/migration-colo.c deleted file mode 100644 index 7811764c4b..0000000000 --- a/stubs/migration-colo.c +++ /dev/null @@ -1,46 +0,0 @@ -/* - * COarse-grain LOck-stepping Virtual Machines for Non-stop Service (COLO) - * (a.k.a. Fault Tolerance or Continuous Replication) - * - * Copyright (c) 2016 HUAWEI TECHNOLOGIES CO., LTD. - * Copyright (c) 2016 FUJITSU LIMITED - * Copyright (c) 2016 Intel Corporation - * - * 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 "migration/colo.h" -#include "qmp-commands.h" - -bool colo_supported(void) -{ - return false; -} - -bool migration_in_colo_state(void) -{ - return false; -} - -bool migration_incoming_in_colo_state(void) -{ - return false; -} - -void migrate_start_colo_process(MigrationState *s) -{ -} - -void *colo_process_incoming_thread(void *opaque) -{ - return NULL; -} - -void qmp_x_colo_lost_heartbeat(Error **errp) -{ - error_setg(errp, "COLO is not supported, please rerun configure" - " with --enable-colo option in order to support" - " COLO feature"); -} diff --git a/stubs/mon-is-qmp.c b/stubs/mon-is-qmp.c deleted file mode 100644 index a8344ced80..0000000000 --- a/stubs/mon-is-qmp.c +++ /dev/null @@ -1,10 +0,0 @@ -#include "qemu/osdep.h" -#include "qemu-common.h" -#include "monitor/monitor.h" - -Monitor *cur_mon; - -bool monitor_cur_is_qmp(void) -{ - return false; -} diff --git a/stubs/monitor-init.c b/stubs/monitor-init.c deleted file mode 100644 index de1bc7cd54..0000000000 --- a/stubs/monitor-init.c +++ /dev/null @@ -1,7 +0,0 @@ -#include "qemu/osdep.h" -#include "qemu-common.h" -#include "monitor/monitor.h" - -void monitor_init(CharDriverState *chr, int flags) -{ -} diff --git a/stubs/get-fd.c b/stubs/monitor.c index 7dfdfb55f7..1d574b1c6f 100644 --- a/stubs/get-fd.c +++ b/stubs/monitor.c @@ -3,8 +3,14 @@ #include "qemu-common.h" #include "monitor/monitor.h" +Monitor *cur_mon = NULL; + int monitor_get_fd(Monitor *mon, const char *name, Error **errp) { error_setg(errp, "only QEMU supports file descriptor passing"); return -1; } + +void monitor_init(CharDriverState *chr, int flags) +{ +} diff --git a/stubs/replay-user.c b/stubs/replay-user.c deleted file mode 100644 index b29e7ebba1..0000000000 --- a/stubs/replay-user.c +++ /dev/null @@ -1,33 +0,0 @@ -/* - * replay.c - * - * Copyright (c) 2010-2015 Institute for System Programming - * of the Russian Academy of Sciences. - * - * 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 "sysemu/replay.h" - -bool replay_exception(void) -{ - return true; -} - -bool replay_has_exception(void) -{ - return false; -} - -bool replay_interrupt(void) -{ - return true; -} - -bool replay_has_interrupt(void) -{ - return false; -} diff --git a/stubs/reset.c b/stubs/reset.c deleted file mode 100644 index 5d47711f9a..0000000000 --- a/stubs/reset.c +++ /dev/null @@ -1,14 +0,0 @@ -#include "qemu/osdep.h" -#include "hw/hw.h" - -/* Stub functions for binaries that never call qemu_devices_reset(), - * and don't need to keep track of the reset handler list. - */ - -void qemu_register_reset(QEMUResetHandler *func, void *opaque) -{ -} - -void qemu_unregister_reset(QEMUResetHandler *func, void *opaque) -{ -} diff --git a/target/arm/cpu.c b/target/arm/cpu.c index 3f2cdb65bf..a941f6611b 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -31,7 +31,7 @@ #endif #include "hw/arm/arm.h" #include "sysemu/sysemu.h" -#include "sysemu/kvm.h" +#include "sysemu/hw_accel.h" #include "kvm_arm.h" static void arm_cpu_set_pc(CPUState *cs, vaddr value) diff --git a/target/i386/Makefile.objs b/target/i386/Makefile.objs index b223d7932b..4fcb7f3df0 100644 --- a/target/i386/Makefile.objs +++ b/target/i386/Makefile.objs @@ -5,3 +5,10 @@ obj-y += gdbstub.o obj-$(CONFIG_SOFTMMU) += machine.o arch_memory_mapping.o arch_dump.o monitor.o obj-$(CONFIG_KVM) += kvm.o hyperv.o obj-$(call lnot,$(CONFIG_KVM)) += kvm-stub.o +# HAX support +ifdef CONFIG_WIN32 +obj-$(CONFIG_HAX) += hax-all.o hax-mem.o hax-windows.o +endif +ifdef CONFIG_DARWIN +obj-$(CONFIG_HAX) += hax-all.o hax-mem.o hax-darwin.o +endif diff --git a/target/i386/hax-all.c b/target/i386/hax-all.c new file mode 100644 index 0000000000..ef13015215 --- /dev/null +++ b/target/i386/hax-all.c @@ -0,0 +1,1155 @@ +/* + * QEMU HAX support + * + * Copyright IBM, Corp. 2008 + * Red Hat, Inc. 2008 + * + * Authors: + * Anthony Liguori <aliguori@us.ibm.com> + * Glauber Costa <gcosta@redhat.com> + * + * Copyright (c) 2011 Intel Corporation + * Written by: + * Jiang Yunhong<yunhong.jiang@intel.com> + * Xin Xiaohui<xiaohui.xin@intel.com> + * Zhang Xiantao<xiantao.zhang@intel.com> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +/* + * HAX common code for both windows and darwin + */ + +#include "qemu/osdep.h" +#include "cpu.h" +#include "exec/address-spaces.h" +#include "exec/exec-all.h" +#include "exec/ioport.h" + +#include "qemu-common.h" +#include "strings.h" +#include "hax-i386.h" +#include "sysemu/accel.h" +#include "sysemu/sysemu.h" +#include "qemu/main-loop.h" +#include "hw/boards.h" + +#define DEBUG_HAX 0 + +#define DPRINTF(fmt, ...) \ + do { \ + if (DEBUG_HAX) { \ + fprintf(stdout, fmt, ## __VA_ARGS__); \ + } \ + } while (0) + +/* Current version */ +const uint32_t hax_cur_version = 0x4; /* API v4: unmapping and MMIO moves */ +/* Minimum HAX kernel version */ +const uint32_t hax_min_version = 0x4; /* API v4: supports unmapping */ + +static bool hax_allowed; + +struct hax_state hax_global; + +static void hax_vcpu_sync_state(CPUArchState *env, int modified); +static int hax_arch_get_registers(CPUArchState *env); + +int hax_enabled(void) +{ + return hax_allowed; +} + +int valid_hax_tunnel_size(uint16_t size) +{ + return size >= sizeof(struct hax_tunnel); +} + +hax_fd hax_vcpu_get_fd(CPUArchState *env) +{ + struct hax_vcpu_state *vcpu = ENV_GET_CPU(env)->hax_vcpu; + if (!vcpu) { + return HAX_INVALID_FD; + } + return vcpu->fd; +} + +static int hax_get_capability(struct hax_state *hax) +{ + int ret; + struct hax_capabilityinfo capinfo, *cap = &capinfo; + + ret = hax_capability(hax, cap); + if (ret) { + return ret; + } + + if ((cap->wstatus & HAX_CAP_WORKSTATUS_MASK) == HAX_CAP_STATUS_NOTWORKING) { + if (cap->winfo & HAX_CAP_FAILREASON_VT) { + DPRINTF + ("VTX feature is not enabled, HAX driver will not work.\n"); + } else if (cap->winfo & HAX_CAP_FAILREASON_NX) { + DPRINTF + ("NX feature is not enabled, HAX driver will not work.\n"); + } + return -ENXIO; + + } + + if (!(cap->winfo & HAX_CAP_UG)) { + fprintf(stderr, "UG mode is not supported by the hardware.\n"); + return -ENOTSUP; + } + + if (cap->wstatus & HAX_CAP_MEMQUOTA) { + if (cap->mem_quota < hax->mem_quota) { + fprintf(stderr, "The VM memory needed exceeds the driver limit.\n"); + return -ENOSPC; + } + } + return 0; +} + +static int hax_version_support(struct hax_state *hax) +{ + int ret; + struct hax_module_version version; + + ret = hax_mod_version(hax, &version); + if (ret < 0) { + return 0; + } + + if (hax_min_version > version.cur_version) { + fprintf(stderr, "Incompatible HAX module version %d,", + version.cur_version); + fprintf(stderr, "requires minimum version %d\n", hax_min_version); + return 0; + } + if (hax_cur_version < version.compat_version) { + fprintf(stderr, "Incompatible QEMU HAX API version %x,", + hax_cur_version); + fprintf(stderr, "requires minimum HAX API version %x\n", + version.compat_version); + return 0; + } + + return 1; +} + +int hax_vcpu_create(int id) +{ + struct hax_vcpu_state *vcpu = NULL; + int ret; + + if (!hax_global.vm) { + fprintf(stderr, "vcpu %x created failed, vm is null\n", id); + return -1; + } + + if (hax_global.vm->vcpus[id]) { + fprintf(stderr, "vcpu %x allocated already\n", id); + return 0; + } + + vcpu = g_malloc(sizeof(struct hax_vcpu_state)); + if (!vcpu) { + fprintf(stderr, "Failed to alloc vcpu state\n"); + return -ENOMEM; + } + + memset(vcpu, 0, sizeof(struct hax_vcpu_state)); + + ret = hax_host_create_vcpu(hax_global.vm->fd, id); + if (ret) { + fprintf(stderr, "Failed to create vcpu %x\n", id); + goto error; + } + + vcpu->vcpu_id = id; + vcpu->fd = hax_host_open_vcpu(hax_global.vm->id, id); + if (hax_invalid_fd(vcpu->fd)) { + fprintf(stderr, "Failed to open the vcpu\n"); + ret = -ENODEV; + goto error; + } + + hax_global.vm->vcpus[id] = vcpu; + + ret = hax_host_setup_vcpu_channel(vcpu); + if (ret) { + fprintf(stderr, "Invalid hax tunnel size\n"); + ret = -EINVAL; + goto error; + } + return 0; + + error: + /* vcpu and tunnel will be closed automatically */ + if (vcpu && !hax_invalid_fd(vcpu->fd)) { + hax_close_fd(vcpu->fd); + } + + hax_global.vm->vcpus[id] = NULL; + g_free(vcpu); + return -1; +} + +int hax_vcpu_destroy(CPUState *cpu) +{ + struct hax_vcpu_state *vcpu = cpu->hax_vcpu; + + if (!hax_global.vm) { + fprintf(stderr, "vcpu %x destroy failed, vm is null\n", vcpu->vcpu_id); + return -1; + } + + if (!vcpu) { + return 0; + } + + /* + * 1. The hax_tunnel is also destroied when vcpu destroy + * 2. close fd will cause hax module vcpu be cleaned + */ + hax_close_fd(vcpu->fd); + hax_global.vm->vcpus[vcpu->vcpu_id] = NULL; + g_free(vcpu); + return 0; +} + +int hax_init_vcpu(CPUState *cpu) +{ + int ret; + + ret = hax_vcpu_create(cpu->cpu_index); + if (ret < 0) { + fprintf(stderr, "Failed to create HAX vcpu\n"); + exit(-1); + } + + cpu->hax_vcpu = hax_global.vm->vcpus[cpu->cpu_index]; + cpu->hax_vcpu_dirty = true; + qemu_register_reset(hax_reset_vcpu_state, (CPUArchState *) (cpu->env_ptr)); + + return ret; +} + +struct hax_vm *hax_vm_create(struct hax_state *hax) +{ + struct hax_vm *vm; + int vm_id = 0, ret; + + if (hax_invalid_fd(hax->fd)) { + return NULL; + } + + if (hax->vm) { + return hax->vm; + } + + vm = g_malloc(sizeof(struct hax_vm)); + if (!vm) { + return NULL; + } + memset(vm, 0, sizeof(struct hax_vm)); + ret = hax_host_create_vm(hax, &vm_id); + if (ret) { + fprintf(stderr, "Failed to create vm %x\n", ret); + goto error; + } + vm->id = vm_id; + vm->fd = hax_host_open_vm(hax, vm_id); + if (hax_invalid_fd(vm->fd)) { + fprintf(stderr, "Failed to open vm %d\n", vm_id); + goto error; + } + + hax->vm = vm; + return vm; + + error: + g_free(vm); + hax->vm = NULL; + return NULL; +} + +int hax_vm_destroy(struct hax_vm *vm) +{ + int i; + + for (i = 0; i < HAX_MAX_VCPU; i++) + if (vm->vcpus[i]) { + fprintf(stderr, "VCPU should be cleaned before vm clean\n"); + return -1; + } + hax_close_fd(vm->fd); + g_free(vm); + hax_global.vm = NULL; + return 0; +} + +static void hax_handle_interrupt(CPUState *cpu, int mask) +{ + cpu->interrupt_request |= mask; + + if (!qemu_cpu_is_self(cpu)) { + qemu_cpu_kick(cpu); + } +} + +static int hax_init(ram_addr_t ram_size) +{ + struct hax_state *hax = NULL; + struct hax_qemu_version qversion; + int ret; + + hax = &hax_global; + + memset(hax, 0, sizeof(struct hax_state)); + hax->mem_quota = ram_size; + + hax->fd = hax_mod_open(); + if (hax_invalid_fd(hax->fd)) { + hax->fd = 0; + ret = -ENODEV; + goto error; + } + + ret = hax_get_capability(hax); + + if (ret) { + if (ret != -ENOSPC) { + ret = -EINVAL; + } + goto error; + } + + if (!hax_version_support(hax)) { + ret = -EINVAL; + goto error; + } + + hax->vm = hax_vm_create(hax); + if (!hax->vm) { + fprintf(stderr, "Failed to create HAX VM\n"); + ret = -EINVAL; + goto error; + } + + hax_memory_init(); + + qversion.cur_version = hax_cur_version; + qversion.min_version = hax_min_version; + hax_notify_qemu_version(hax->vm->fd, &qversion); + cpu_interrupt_handler = hax_handle_interrupt; + + return ret; + error: + if (hax->vm) { + hax_vm_destroy(hax->vm); + } + if (hax->fd) { + hax_mod_close(hax); + } + + return ret; +} + +static int hax_accel_init(MachineState *ms) +{ + int ret = hax_init(ms->ram_size); + + if (ret && (ret != -ENOSPC)) { + fprintf(stderr, "No accelerator found.\n"); + } else { + fprintf(stdout, "HAX is %s and emulator runs in %s mode.\n", + !ret ? "working" : "not working", + !ret ? "fast virt" : "emulation"); + } + return ret; +} + +static int hax_handle_fastmmio(CPUArchState *env, struct hax_fastmmio *hft) +{ + if (hft->direction < 2) { + cpu_physical_memory_rw(hft->gpa, (uint8_t *) &hft->value, hft->size, + hft->direction); + } else { + /* + * HAX API v4 supports transferring data between two MMIO addresses, + * hft->gpa and hft->gpa2 (instructions such as MOVS require this): + * hft->direction == 2: gpa ==> gpa2 + */ + uint64_t value; + cpu_physical_memory_rw(hft->gpa, (uint8_t *) &value, hft->size, 0); + cpu_physical_memory_rw(hft->gpa2, (uint8_t *) &value, hft->size, 1); + } + + return 0; +} + +static int hax_handle_io(CPUArchState *env, uint32_t df, uint16_t port, + int direction, int size, int count, void *buffer) +{ + uint8_t *ptr; + int i; + MemTxAttrs attrs = { 0 }; + + if (!df) { + ptr = (uint8_t *) buffer; + } else { + ptr = buffer + size * count - size; + } + for (i = 0; i < count; i++) { + address_space_rw(&address_space_io, port, attrs, + ptr, size, direction == HAX_EXIT_IO_OUT); + if (!df) { + ptr += size; + } else { + ptr -= size; + } + } + + return 0; +} + +static int hax_vcpu_interrupt(CPUArchState *env) +{ + CPUState *cpu = ENV_GET_CPU(env); + struct hax_vcpu_state *vcpu = cpu->hax_vcpu; + struct hax_tunnel *ht = vcpu->tunnel; + + /* + * Try to inject an interrupt if the guest can accept it + * Unlike KVM, HAX kernel check for the eflags, instead of qemu + */ + if (ht->ready_for_interrupt_injection && + (cpu->interrupt_request & CPU_INTERRUPT_HARD)) { + int irq; + + irq = cpu_get_pic_interrupt(env); + if (irq >= 0) { + hax_inject_interrupt(env, irq); + cpu->interrupt_request &= ~CPU_INTERRUPT_HARD; + } + } + + /* If we have an interrupt but the guest is not ready to receive an + * interrupt, request an interrupt window exit. This will + * cause a return to userspace as soon as the guest is ready to + * receive interrupts. */ + if ((cpu->interrupt_request & CPU_INTERRUPT_HARD)) { + ht->request_interrupt_window = 1; + } else { + ht->request_interrupt_window = 0; + } + return 0; +} + +void hax_raise_event(CPUState *cpu) +{ + struct hax_vcpu_state *vcpu = cpu->hax_vcpu; + + if (!vcpu) { + return; + } + vcpu->tunnel->user_event_pending = 1; +} + +/* + * Ask hax kernel module to run the CPU for us till: + * 1. Guest crash or shutdown + * 2. Need QEMU's emulation like guest execute MMIO instruction + * 3. Guest execute HLT + * 4. QEMU have Signal/event pending + * 5. An unknown VMX exit happens + */ +static int hax_vcpu_hax_exec(CPUArchState *env) +{ + int ret = 0; + CPUState *cpu = ENV_GET_CPU(env); + X86CPU *x86_cpu = X86_CPU(cpu); + struct hax_vcpu_state *vcpu = cpu->hax_vcpu; + struct hax_tunnel *ht = vcpu->tunnel; + + if (!hax_enabled()) { + DPRINTF("Trying to vcpu execute at eip:" TARGET_FMT_lx "\n", env->eip); + return 0; + } + + cpu->halted = 0; + + if (cpu->interrupt_request & CPU_INTERRUPT_POLL) { + cpu->interrupt_request &= ~CPU_INTERRUPT_POLL; + apic_poll_irq(x86_cpu->apic_state); + } + + if (cpu->interrupt_request & CPU_INTERRUPT_INIT) { + DPRINTF("\nhax_vcpu_hax_exec: handling INIT for %d\n", + cpu->cpu_index); + do_cpu_init(x86_cpu); + hax_vcpu_sync_state(env, 1); + } + + if (cpu->interrupt_request & CPU_INTERRUPT_SIPI) { + DPRINTF("hax_vcpu_hax_exec: handling SIPI for %d\n", + cpu->cpu_index); + hax_vcpu_sync_state(env, 0); + do_cpu_sipi(x86_cpu); + hax_vcpu_sync_state(env, 1); + } + + do { + int hax_ret; + + if (cpu->exit_request) { + ret = 1; + break; + } + + hax_vcpu_interrupt(env); + + qemu_mutex_unlock_iothread(); + hax_ret = hax_vcpu_run(vcpu); + qemu_mutex_lock_iothread(); + current_cpu = cpu; + + /* Simply continue the vcpu_run if system call interrupted */ + if (hax_ret == -EINTR || hax_ret == -EAGAIN) { + DPRINTF("io window interrupted\n"); + continue; + } + + if (hax_ret < 0) { + fprintf(stderr, "vcpu run failed for vcpu %x\n", vcpu->vcpu_id); + abort(); + } + switch (ht->_exit_status) { + case HAX_EXIT_IO: + ret = hax_handle_io(env, ht->pio._df, ht->pio._port, + ht->pio._direction, + ht->pio._size, ht->pio._count, vcpu->iobuf); + break; + case HAX_EXIT_FAST_MMIO: + ret = hax_handle_fastmmio(env, (struct hax_fastmmio *) vcpu->iobuf); + break; + /* Guest state changed, currently only for shutdown */ + case HAX_EXIT_STATECHANGE: + fprintf(stdout, "VCPU shutdown request\n"); + qemu_system_shutdown_request(); + hax_vcpu_sync_state(env, 0); + ret = 1; + break; + case HAX_EXIT_UNKNOWN_VMEXIT: + fprintf(stderr, "Unknown VMX exit %x from guest\n", + ht->_exit_reason); + qemu_system_reset_request(); + hax_vcpu_sync_state(env, 0); + cpu_dump_state(cpu, stderr, fprintf, 0); + ret = -1; + break; + case HAX_EXIT_HLT: + if (!(cpu->interrupt_request & CPU_INTERRUPT_HARD) && + !(cpu->interrupt_request & CPU_INTERRUPT_NMI)) { + /* hlt instruction with interrupt disabled is shutdown */ + env->eflags |= IF_MASK; + cpu->halted = 1; + cpu->exception_index = EXCP_HLT; + ret = 1; + } + break; + /* these situations will continue to hax module */ + case HAX_EXIT_INTERRUPT: + case HAX_EXIT_PAUSED: + break; + case HAX_EXIT_MMIO: + /* Should not happen on UG system */ + fprintf(stderr, "HAX: unsupported MMIO emulation\n"); + ret = -1; + break; + case HAX_EXIT_REAL: + /* Should not happen on UG system */ + fprintf(stderr, "HAX: unimplemented real mode emulation\n"); + ret = -1; + break; + default: + fprintf(stderr, "Unknown exit %x from HAX\n", ht->_exit_status); + qemu_system_reset_request(); + hax_vcpu_sync_state(env, 0); + cpu_dump_state(cpu, stderr, fprintf, 0); + ret = 1; + break; + } + } while (!ret); + + if (cpu->exit_request) { + cpu->exit_request = 0; + cpu->exception_index = EXCP_INTERRUPT; + } + return ret < 0; +} + +static void do_hax_cpu_synchronize_state(CPUState *cpu, run_on_cpu_data arg) +{ + CPUArchState *env = cpu->env_ptr; + + hax_arch_get_registers(env); + cpu->hax_vcpu_dirty = true; +} + +void hax_cpu_synchronize_state(CPUState *cpu) +{ + if (!cpu->hax_vcpu_dirty) { + run_on_cpu(cpu, do_hax_cpu_synchronize_state, RUN_ON_CPU_NULL); + } +} + +static void do_hax_cpu_synchronize_post_reset(CPUState *cpu, + run_on_cpu_data arg) +{ + CPUArchState *env = cpu->env_ptr; + + hax_vcpu_sync_state(env, 1); + cpu->hax_vcpu_dirty = false; +} + +void hax_cpu_synchronize_post_reset(CPUState *cpu) +{ + run_on_cpu(cpu, do_hax_cpu_synchronize_post_reset, RUN_ON_CPU_NULL); +} + +static void do_hax_cpu_synchronize_post_init(CPUState *cpu, run_on_cpu_data arg) +{ + CPUArchState *env = cpu->env_ptr; + + hax_vcpu_sync_state(env, 1); + cpu->hax_vcpu_dirty = false; +} + +void hax_cpu_synchronize_post_init(CPUState *cpu) +{ + run_on_cpu(cpu, do_hax_cpu_synchronize_post_init, RUN_ON_CPU_NULL); +} + +int hax_smp_cpu_exec(CPUState *cpu) +{ + CPUArchState *env = (CPUArchState *) (cpu->env_ptr); + int fatal; + int ret; + + while (1) { + if (cpu->exception_index >= EXCP_INTERRUPT) { + ret = cpu->exception_index; + cpu->exception_index = -1; + break; + } + + fatal = hax_vcpu_hax_exec(env); + + if (fatal) { + fprintf(stderr, "Unsupported HAX vcpu return\n"); + abort(); + } + } + + return ret; +} + +static void set_v8086_seg(struct segment_desc_t *lhs, const SegmentCache *rhs) +{ + memset(lhs, 0, sizeof(struct segment_desc_t)); + lhs->selector = rhs->selector; + lhs->base = rhs->base; + lhs->limit = rhs->limit; + lhs->type = 3; + lhs->present = 1; + lhs->dpl = 3; + lhs->operand_size = 0; + lhs->desc = 1; + lhs->long_mode = 0; + lhs->granularity = 0; + lhs->available = 0; +} + +static void get_seg(SegmentCache *lhs, const struct segment_desc_t *rhs) +{ + lhs->selector = rhs->selector; + lhs->base = rhs->base; + lhs->limit = rhs->limit; + lhs->flags = (rhs->type << DESC_TYPE_SHIFT) + | (rhs->present * DESC_P_MASK) + | (rhs->dpl << DESC_DPL_SHIFT) + | (rhs->operand_size << DESC_B_SHIFT) + | (rhs->desc * DESC_S_MASK) + | (rhs->long_mode << DESC_L_SHIFT) + | (rhs->granularity * DESC_G_MASK) | (rhs->available * DESC_AVL_MASK); +} + +static void set_seg(struct segment_desc_t *lhs, const SegmentCache *rhs) +{ + unsigned flags = rhs->flags; + + memset(lhs, 0, sizeof(struct segment_desc_t)); + lhs->selector = rhs->selector; + lhs->base = rhs->base; + lhs->limit = rhs->limit; + lhs->type = (flags >> DESC_TYPE_SHIFT) & 15; + lhs->present = (flags & DESC_P_MASK) != 0; + lhs->dpl = rhs->selector & 3; + lhs->operand_size = (flags >> DESC_B_SHIFT) & 1; + lhs->desc = (flags & DESC_S_MASK) != 0; + lhs->long_mode = (flags >> DESC_L_SHIFT) & 1; + lhs->granularity = (flags & DESC_G_MASK) != 0; + lhs->available = (flags & DESC_AVL_MASK) != 0; +} + +static void hax_getput_reg(uint64_t *hax_reg, target_ulong *qemu_reg, int set) +{ + target_ulong reg = *hax_reg; + + if (set) { + *hax_reg = *qemu_reg; + } else { + *qemu_reg = reg; + } +} + +/* The sregs has been synced with HAX kernel already before this call */ +static int hax_get_segments(CPUArchState *env, struct vcpu_state_t *sregs) +{ + get_seg(&env->segs[R_CS], &sregs->_cs); + get_seg(&env->segs[R_DS], &sregs->_ds); + get_seg(&env->segs[R_ES], &sregs->_es); + get_seg(&env->segs[R_FS], &sregs->_fs); + get_seg(&env->segs[R_GS], &sregs->_gs); + get_seg(&env->segs[R_SS], &sregs->_ss); + + get_seg(&env->tr, &sregs->_tr); + get_seg(&env->ldt, &sregs->_ldt); + env->idt.limit = sregs->_idt.limit; + env->idt.base = sregs->_idt.base; + env->gdt.limit = sregs->_gdt.limit; + env->gdt.base = sregs->_gdt.base; + return 0; +} + +static int hax_set_segments(CPUArchState *env, struct vcpu_state_t *sregs) +{ + if ((env->eflags & VM_MASK)) { + set_v8086_seg(&sregs->_cs, &env->segs[R_CS]); + set_v8086_seg(&sregs->_ds, &env->segs[R_DS]); + set_v8086_seg(&sregs->_es, &env->segs[R_ES]); + set_v8086_seg(&sregs->_fs, &env->segs[R_FS]); + set_v8086_seg(&sregs->_gs, &env->segs[R_GS]); + set_v8086_seg(&sregs->_ss, &env->segs[R_SS]); + } else { + set_seg(&sregs->_cs, &env->segs[R_CS]); + set_seg(&sregs->_ds, &env->segs[R_DS]); + set_seg(&sregs->_es, &env->segs[R_ES]); + set_seg(&sregs->_fs, &env->segs[R_FS]); + set_seg(&sregs->_gs, &env->segs[R_GS]); + set_seg(&sregs->_ss, &env->segs[R_SS]); + + if (env->cr[0] & CR0_PE_MASK) { + /* force ss cpl to cs cpl */ + sregs->_ss.selector = (sregs->_ss.selector & ~3) | + (sregs->_cs.selector & 3); + sregs->_ss.dpl = sregs->_ss.selector & 3; + } + } + + set_seg(&sregs->_tr, &env->tr); + set_seg(&sregs->_ldt, &env->ldt); + sregs->_idt.limit = env->idt.limit; + sregs->_idt.base = env->idt.base; + sregs->_gdt.limit = env->gdt.limit; + sregs->_gdt.base = env->gdt.base; + return 0; +} + +/* + * After get the state from the kernel module, some + * qemu emulator state need be updated also + */ +static int hax_setup_qemu_emulator(CPUArchState *env) +{ + +#define HFLAG_COPY_MASK (~( \ + HF_CPL_MASK | HF_PE_MASK | HF_MP_MASK | HF_EM_MASK | \ + HF_TS_MASK | HF_TF_MASK | HF_VM_MASK | HF_IOPL_MASK | \ + HF_OSFXSR_MASK | HF_LMA_MASK | HF_CS32_MASK | \ + HF_SS32_MASK | HF_CS64_MASK | HF_ADDSEG_MASK)) + + uint32_t hflags; + + hflags = (env->segs[R_CS].flags >> DESC_DPL_SHIFT) & HF_CPL_MASK; + hflags |= (env->cr[0] & CR0_PE_MASK) << (HF_PE_SHIFT - CR0_PE_SHIFT); + hflags |= (env->cr[0] << (HF_MP_SHIFT - CR0_MP_SHIFT)) & + (HF_MP_MASK | HF_EM_MASK | HF_TS_MASK); + hflags |= (env->eflags & (HF_TF_MASK | HF_VM_MASK | HF_IOPL_MASK)); + hflags |= (env->cr[4] & CR4_OSFXSR_MASK) << + (HF_OSFXSR_SHIFT - CR4_OSFXSR_SHIFT); + + if (env->efer & MSR_EFER_LMA) { + hflags |= HF_LMA_MASK; + } + + if ((hflags & HF_LMA_MASK) && (env->segs[R_CS].flags & DESC_L_MASK)) { + hflags |= HF_CS32_MASK | HF_SS32_MASK | HF_CS64_MASK; + } else { + hflags |= (env->segs[R_CS].flags & DESC_B_MASK) >> + (DESC_B_SHIFT - HF_CS32_SHIFT); + hflags |= (env->segs[R_SS].flags & DESC_B_MASK) >> + (DESC_B_SHIFT - HF_SS32_SHIFT); + if (!(env->cr[0] & CR0_PE_MASK) || + (env->eflags & VM_MASK) || !(hflags & HF_CS32_MASK)) { + hflags |= HF_ADDSEG_MASK; + } else { + hflags |= ((env->segs[R_DS].base | + env->segs[R_ES].base | + env->segs[R_SS].base) != 0) << HF_ADDSEG_SHIFT; + } + } + + hflags &= ~HF_SMM_MASK; + + env->hflags = (env->hflags & HFLAG_COPY_MASK) | hflags; + return 0; +} + +static int hax_sync_vcpu_register(CPUArchState *env, int set) +{ + struct vcpu_state_t regs; + int ret; + memset(®s, 0, sizeof(struct vcpu_state_t)); + + if (!set) { + ret = hax_sync_vcpu_state(env, ®s, 0); + if (ret < 0) { + return -1; + } + } + + /* generic register */ + hax_getput_reg(®s._rax, &env->regs[R_EAX], set); + hax_getput_reg(®s._rbx, &env->regs[R_EBX], set); + hax_getput_reg(®s._rcx, &env->regs[R_ECX], set); + hax_getput_reg(®s._rdx, &env->regs[R_EDX], set); + hax_getput_reg(®s._rsi, &env->regs[R_ESI], set); + hax_getput_reg(®s._rdi, &env->regs[R_EDI], set); + hax_getput_reg(®s._rsp, &env->regs[R_ESP], set); + hax_getput_reg(®s._rbp, &env->regs[R_EBP], set); +#ifdef TARGET_X86_64 + hax_getput_reg(®s._r8, &env->regs[8], set); + hax_getput_reg(®s._r9, &env->regs[9], set); + hax_getput_reg(®s._r10, &env->regs[10], set); + hax_getput_reg(®s._r11, &env->regs[11], set); + hax_getput_reg(®s._r12, &env->regs[12], set); + hax_getput_reg(®s._r13, &env->regs[13], set); + hax_getput_reg(®s._r14, &env->regs[14], set); + hax_getput_reg(®s._r15, &env->regs[15], set); +#endif + hax_getput_reg(®s._rflags, &env->eflags, set); + hax_getput_reg(®s._rip, &env->eip, set); + + if (set) { + regs._cr0 = env->cr[0]; + regs._cr2 = env->cr[2]; + regs._cr3 = env->cr[3]; + regs._cr4 = env->cr[4]; + hax_set_segments(env, ®s); + } else { + env->cr[0] = regs._cr0; + env->cr[2] = regs._cr2; + env->cr[3] = regs._cr3; + env->cr[4] = regs._cr4; + hax_get_segments(env, ®s); + } + + if (set) { + ret = hax_sync_vcpu_state(env, ®s, 1); + if (ret < 0) { + return -1; + } + } + if (!set) { + hax_setup_qemu_emulator(env); + } + return 0; +} + +static void hax_msr_entry_set(struct vmx_msr *item, uint32_t index, + uint64_t value) +{ + item->entry = index; + item->value = value; +} + +static int hax_get_msrs(CPUArchState *env) +{ + struct hax_msr_data md; + struct vmx_msr *msrs = md.entries; + int ret, i, n; + + n = 0; + msrs[n++].entry = MSR_IA32_SYSENTER_CS; + msrs[n++].entry = MSR_IA32_SYSENTER_ESP; + msrs[n++].entry = MSR_IA32_SYSENTER_EIP; + msrs[n++].entry = MSR_IA32_TSC; +#ifdef TARGET_X86_64 + msrs[n++].entry = MSR_EFER; + msrs[n++].entry = MSR_STAR; + msrs[n++].entry = MSR_LSTAR; + msrs[n++].entry = MSR_CSTAR; + msrs[n++].entry = MSR_FMASK; + msrs[n++].entry = MSR_KERNELGSBASE; +#endif + md.nr_msr = n; + ret = hax_sync_msr(env, &md, 0); + if (ret < 0) { + return ret; + } + + for (i = 0; i < md.done; i++) { + switch (msrs[i].entry) { + case MSR_IA32_SYSENTER_CS: + env->sysenter_cs = msrs[i].value; + break; + case MSR_IA32_SYSENTER_ESP: + env->sysenter_esp = msrs[i].value; + break; + case MSR_IA32_SYSENTER_EIP: + env->sysenter_eip = msrs[i].value; + break; + case MSR_IA32_TSC: + env->tsc = msrs[i].value; + break; +#ifdef TARGET_X86_64 + case MSR_EFER: + env->efer = msrs[i].value; + break; + case MSR_STAR: + env->star = msrs[i].value; + break; + case MSR_LSTAR: + env->lstar = msrs[i].value; + break; + case MSR_CSTAR: + env->cstar = msrs[i].value; + break; + case MSR_FMASK: + env->fmask = msrs[i].value; + break; + case MSR_KERNELGSBASE: + env->kernelgsbase = msrs[i].value; + break; +#endif + } + } + + return 0; +} + +static int hax_set_msrs(CPUArchState *env) +{ + struct hax_msr_data md; + struct vmx_msr *msrs; + msrs = md.entries; + int n = 0; + + memset(&md, 0, sizeof(struct hax_msr_data)); + hax_msr_entry_set(&msrs[n++], MSR_IA32_SYSENTER_CS, env->sysenter_cs); + hax_msr_entry_set(&msrs[n++], MSR_IA32_SYSENTER_ESP, env->sysenter_esp); + hax_msr_entry_set(&msrs[n++], MSR_IA32_SYSENTER_EIP, env->sysenter_eip); + hax_msr_entry_set(&msrs[n++], MSR_IA32_TSC, env->tsc); +#ifdef TARGET_X86_64 + hax_msr_entry_set(&msrs[n++], MSR_EFER, env->efer); + hax_msr_entry_set(&msrs[n++], MSR_STAR, env->star); + hax_msr_entry_set(&msrs[n++], MSR_LSTAR, env->lstar); + hax_msr_entry_set(&msrs[n++], MSR_CSTAR, env->cstar); + hax_msr_entry_set(&msrs[n++], MSR_FMASK, env->fmask); + hax_msr_entry_set(&msrs[n++], MSR_KERNELGSBASE, env->kernelgsbase); +#endif + md.nr_msr = n; + md.done = 0; + + return hax_sync_msr(env, &md, 1); +} + +static int hax_get_fpu(CPUArchState *env) +{ + struct fx_layout fpu; + int i, ret; + + ret = hax_sync_fpu(env, &fpu, 0); + if (ret < 0) { + return ret; + } + + env->fpstt = (fpu.fsw >> 11) & 7; + env->fpus = fpu.fsw; + env->fpuc = fpu.fcw; + for (i = 0; i < 8; ++i) { + env->fptags[i] = !((fpu.ftw >> i) & 1); + } + memcpy(env->fpregs, fpu.st_mm, sizeof(env->fpregs)); + + for (i = 0; i < 8; i++) { + env->xmm_regs[i].ZMM_Q(0) = ldq_p(&fpu.mmx_1[i][0]); + env->xmm_regs[i].ZMM_Q(1) = ldq_p(&fpu.mmx_1[i][8]); + if (CPU_NB_REGS > 8) { + env->xmm_regs[i + 8].ZMM_Q(0) = ldq_p(&fpu.mmx_2[i][0]); + env->xmm_regs[i + 8].ZMM_Q(1) = ldq_p(&fpu.mmx_2[i][8]); + } + } + env->mxcsr = fpu.mxcsr; + + return 0; +} + +static int hax_set_fpu(CPUArchState *env) +{ + struct fx_layout fpu; + int i; + + memset(&fpu, 0, sizeof(fpu)); + fpu.fsw = env->fpus & ~(7 << 11); + fpu.fsw |= (env->fpstt & 7) << 11; + fpu.fcw = env->fpuc; + + for (i = 0; i < 8; ++i) { + fpu.ftw |= (!env->fptags[i]) << i; + } + + memcpy(fpu.st_mm, env->fpregs, sizeof(env->fpregs)); + for (i = 0; i < 8; i++) { + stq_p(&fpu.mmx_1[i][0], env->xmm_regs[i].ZMM_Q(0)); + stq_p(&fpu.mmx_1[i][8], env->xmm_regs[i].ZMM_Q(1)); + if (CPU_NB_REGS > 8) { + stq_p(&fpu.mmx_2[i][0], env->xmm_regs[i + 8].ZMM_Q(0)); + stq_p(&fpu.mmx_2[i][8], env->xmm_regs[i + 8].ZMM_Q(1)); + } + } + + fpu.mxcsr = env->mxcsr; + + return hax_sync_fpu(env, &fpu, 1); +} + +static int hax_arch_get_registers(CPUArchState *env) +{ + int ret; + + ret = hax_sync_vcpu_register(env, 0); + if (ret < 0) { + return ret; + } + + ret = hax_get_fpu(env); + if (ret < 0) { + return ret; + } + + ret = hax_get_msrs(env); + if (ret < 0) { + return ret; + } + + return 0; +} + +static int hax_arch_set_registers(CPUArchState *env) +{ + int ret; + ret = hax_sync_vcpu_register(env, 1); + + if (ret < 0) { + fprintf(stderr, "Failed to sync vcpu reg\n"); + return ret; + } + ret = hax_set_fpu(env); + if (ret < 0) { + fprintf(stderr, "FPU failed\n"); + return ret; + } + ret = hax_set_msrs(env); + if (ret < 0) { + fprintf(stderr, "MSR failed\n"); + return ret; + } + + return 0; +} + +static void hax_vcpu_sync_state(CPUArchState *env, int modified) +{ + if (hax_enabled()) { + if (modified) { + hax_arch_set_registers(env); + } else { + hax_arch_get_registers(env); + } + } +} + +/* + * much simpler than kvm, at least in first stage because: + * We don't need consider the device pass-through, we don't need + * consider the framebuffer, and we may even remove the bios at all + */ +int hax_sync_vcpus(void) +{ + if (hax_enabled()) { + CPUState *cpu; + + cpu = first_cpu; + if (!cpu) { + return 0; + } + + for (; cpu != NULL; cpu = CPU_NEXT(cpu)) { + int ret; + + ret = hax_arch_set_registers(cpu->env_ptr); + if (ret < 0) { + return ret; + } + } + } + + return 0; +} + +void hax_reset_vcpu_state(void *opaque) +{ + CPUState *cpu; + for (cpu = first_cpu; cpu != NULL; cpu = CPU_NEXT(cpu)) { + cpu->hax_vcpu->tunnel->user_event_pending = 0; + cpu->hax_vcpu->tunnel->ready_for_interrupt_injection = 0; + } +} + +static void hax_accel_class_init(ObjectClass *oc, void *data) +{ + AccelClass *ac = ACCEL_CLASS(oc); + ac->name = "HAX"; + ac->init_machine = hax_accel_init; + ac->allowed = &hax_allowed; +} + +static const TypeInfo hax_accel_type = { + .name = ACCEL_CLASS_NAME("hax"), + .parent = TYPE_ACCEL, + .class_init = hax_accel_class_init, +}; + +static void hax_type_init(void) +{ + type_register_static(&hax_accel_type); +} + +type_init(hax_type_init); diff --git a/target/i386/hax-darwin.c b/target/i386/hax-darwin.c new file mode 100644 index 0000000000..1c5bbd0a2d --- /dev/null +++ b/target/i386/hax-darwin.c @@ -0,0 +1,316 @@ +/* + * QEMU HAXM support + * + * Copyright (c) 2011 Intel Corporation + * Written by: + * Jiang Yunhong<yunhong.jiang@intel.com> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +/* HAX module interface - darwin version */ +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <errno.h> +#include <sys/ioctl.h> + +#include "qemu/osdep.h" +#include "target/i386/hax-i386.h" + +hax_fd hax_mod_open(void) +{ + int fd = open("/dev/HAX", O_RDWR); + if (fd == -1) { + fprintf(stderr, "Failed to open the hax module\n"); + } + + fcntl(fd, F_SETFD, FD_CLOEXEC); + + return fd; +} + +int hax_populate_ram(uint64_t va, uint32_t size) +{ + int ret; + struct hax_alloc_ram_info info; + + if (!hax_global.vm || !hax_global.vm->fd) { + fprintf(stderr, "Allocate memory before vm create?\n"); + return -EINVAL; + } + + info.size = size; + info.va = va; + ret = ioctl(hax_global.vm->fd, HAX_VM_IOCTL_ALLOC_RAM, &info); + if (ret < 0) { + fprintf(stderr, "Failed to allocate %x memory\n", size); + return ret; + } + return 0; +} + +int hax_set_ram(uint64_t start_pa, uint32_t size, uint64_t host_va, int flags) +{ + struct hax_set_ram_info info; + int ret; + + info.pa_start = start_pa; + info.size = size; + info.va = host_va; + info.flags = (uint8_t) flags; + + ret = ioctl(hax_global.vm->fd, HAX_VM_IOCTL_SET_RAM, &info); + if (ret < 0) { + return -errno; + } + return 0; +} + +int hax_capability(struct hax_state *hax, struct hax_capabilityinfo *cap) +{ + int ret; + + ret = ioctl(hax->fd, HAX_IOCTL_CAPABILITY, cap); + if (ret == -1) { + fprintf(stderr, "Failed to get HAX capability\n"); + return -errno; + } + + return 0; +} + +int hax_mod_version(struct hax_state *hax, struct hax_module_version *version) +{ + int ret; + + ret = ioctl(hax->fd, HAX_IOCTL_VERSION, version); + if (ret == -1) { + fprintf(stderr, "Failed to get HAX version\n"); + return -errno; + } + + return 0; +} + +static char *hax_vm_devfs_string(int vm_id) +{ + char *name; + + if (vm_id > MAX_VM_ID) { + fprintf(stderr, "Too big VM id\n"); + return NULL; + } + +#define HAX_VM_DEVFS "/dev/hax_vm/vmxx" + name = g_strdup(HAX_VM_DEVFS); + if (!name) { + return NULL; + } + + snprintf(name, sizeof HAX_VM_DEVFS, "/dev/hax_vm/vm%02d", vm_id); + return name; +} + +static char *hax_vcpu_devfs_string(int vm_id, int vcpu_id) +{ + char *name; + + if (vm_id > MAX_VM_ID || vcpu_id > MAX_VCPU_ID) { + fprintf(stderr, "Too big vm id %x or vcpu id %x\n", vm_id, vcpu_id); + return NULL; + } + +#define HAX_VCPU_DEVFS "/dev/hax_vmxx/vcpuxx" + name = g_strdup(HAX_VCPU_DEVFS); + if (!name) { + return NULL; + } + + snprintf(name, sizeof HAX_VCPU_DEVFS, "/dev/hax_vm%02d/vcpu%02d", + vm_id, vcpu_id); + return name; +} + +int hax_host_create_vm(struct hax_state *hax, int *vmid) +{ + int ret; + int vm_id = 0; + + if (hax_invalid_fd(hax->fd)) { + return -EINVAL; + } + + if (hax->vm) { + return 0; + } + + ret = ioctl(hax->fd, HAX_IOCTL_CREATE_VM, &vm_id); + *vmid = vm_id; + return ret; +} + +hax_fd hax_host_open_vm(struct hax_state *hax, int vm_id) +{ + hax_fd fd; + char *vm_name = NULL; + + vm_name = hax_vm_devfs_string(vm_id); + if (!vm_name) { + return -1; + } + + fd = open(vm_name, O_RDWR); + g_free(vm_name); + + fcntl(fd, F_SETFD, FD_CLOEXEC); + + return fd; +} + +int hax_notify_qemu_version(hax_fd vm_fd, struct hax_qemu_version *qversion) +{ + int ret; + + if (hax_invalid_fd(vm_fd)) { + return -EINVAL; + } + + ret = ioctl(vm_fd, HAX_VM_IOCTL_NOTIFY_QEMU_VERSION, qversion); + + if (ret < 0) { + fprintf(stderr, "Failed to notify qemu API version\n"); + return ret; + } + return 0; +} + +/* Simply assume the size should be bigger than the hax_tunnel, + * since the hax_tunnel can be extended later with compatibility considered + */ +int hax_host_create_vcpu(hax_fd vm_fd, int vcpuid) +{ + int ret; + + ret = ioctl(vm_fd, HAX_VM_IOCTL_VCPU_CREATE, &vcpuid); + if (ret < 0) { + fprintf(stderr, "Failed to create vcpu %x\n", vcpuid); + } + + return ret; +} + +hax_fd hax_host_open_vcpu(int vmid, int vcpuid) +{ + char *devfs_path = NULL; + hax_fd fd; + + devfs_path = hax_vcpu_devfs_string(vmid, vcpuid); + if (!devfs_path) { + fprintf(stderr, "Failed to get the devfs\n"); + return -EINVAL; + } + + fd = open(devfs_path, O_RDWR); + g_free(devfs_path); + if (fd < 0) { + fprintf(stderr, "Failed to open the vcpu devfs\n"); + } + fcntl(fd, F_SETFD, FD_CLOEXEC); + return fd; +} + +int hax_host_setup_vcpu_channel(struct hax_vcpu_state *vcpu) +{ + int ret; + struct hax_tunnel_info info; + + ret = ioctl(vcpu->fd, HAX_VCPU_IOCTL_SETUP_TUNNEL, &info); + if (ret) { + fprintf(stderr, "Failed to setup the hax tunnel\n"); + return ret; + } + + if (!valid_hax_tunnel_size(info.size)) { + fprintf(stderr, "Invalid hax tunnel size %x\n", info.size); + ret = -EINVAL; + return ret; + } + + vcpu->tunnel = (struct hax_tunnel *) (intptr_t) (info.va); + vcpu->iobuf = (unsigned char *) (intptr_t) (info.io_va); + return 0; +} + +int hax_vcpu_run(struct hax_vcpu_state *vcpu) +{ + int ret; + + ret = ioctl(vcpu->fd, HAX_VCPU_IOCTL_RUN, NULL); + return ret; +} + +int hax_sync_fpu(CPUArchState *env, struct fx_layout *fl, int set) +{ + int ret, fd; + + fd = hax_vcpu_get_fd(env); + if (fd <= 0) { + return -1; + } + + if (set) { + ret = ioctl(fd, HAX_VCPU_IOCTL_SET_FPU, fl); + } else { + ret = ioctl(fd, HAX_VCPU_IOCTL_GET_FPU, fl); + } + return ret; +} + +int hax_sync_msr(CPUArchState *env, struct hax_msr_data *msrs, int set) +{ + int ret, fd; + + fd = hax_vcpu_get_fd(env); + if (fd <= 0) { + return -1; + } + if (set) { + ret = ioctl(fd, HAX_VCPU_IOCTL_SET_MSRS, msrs); + } else { + ret = ioctl(fd, HAX_VCPU_IOCTL_GET_MSRS, msrs); + } + return ret; +} + +int hax_sync_vcpu_state(CPUArchState *env, struct vcpu_state_t *state, int set) +{ + int ret, fd; + + fd = hax_vcpu_get_fd(env); + if (fd <= 0) { + return -1; + } + + if (set) { + ret = ioctl(fd, HAX_VCPU_SET_REGS, state); + } else { + ret = ioctl(fd, HAX_VCPU_GET_REGS, state); + } + return ret; +} + +int hax_inject_interrupt(CPUArchState *env, int vector) +{ + int ret, fd; + + fd = hax_vcpu_get_fd(env); + if (fd <= 0) { + return -1; + } + + ret = ioctl(fd, HAX_VCPU_IOCTL_INTERRUPT, &vector); + return ret; +} diff --git a/target/i386/hax-darwin.h b/target/i386/hax-darwin.h new file mode 100644 index 0000000000..0c0968b77d --- /dev/null +++ b/target/i386/hax-darwin.h @@ -0,0 +1,63 @@ +/* + * QEMU HAXM support + * + * Copyright (c) 2011 Intel Corporation + * Written by: + * Jiang Yunhong<yunhong.jiang@intel.com> + * Xin Xiaohui<xiaohui.xin@intel.com> + * Zhang Xiantao<xiantao.zhang@intel.com> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#ifndef TARGET_I386_HAX_DARWIN_H +#define TARGET_I386_HAX_DARWIN_H + +#include <sys/types.h> +#include <sys/ioctl.h> +#include <sys/mman.h> +#include <stdarg.h> + +#define HAX_INVALID_FD (-1) +static inline int hax_invalid_fd(hax_fd fd) +{ + return fd <= 0; +} + +static inline void hax_mod_close(struct hax_state *hax) +{ + close(hax->fd); +} + +static inline void hax_close_fd(hax_fd fd) +{ + close(fd); +} + +/* HAX model level ioctl */ +#define HAX_IOCTL_VERSION _IOWR(0, 0x20, struct hax_module_version) +#define HAX_IOCTL_CREATE_VM _IOWR(0, 0x21, uint32_t) +#define HAX_IOCTL_DESTROY_VM _IOW(0, 0x22, uint32_t) +#define HAX_IOCTL_CAPABILITY _IOR(0, 0x23, struct hax_capabilityinfo) + +#define HAX_VM_IOCTL_VCPU_CREATE _IOWR(0, 0x80, uint32_t) +#define HAX_VM_IOCTL_ALLOC_RAM _IOWR(0, 0x81, struct hax_alloc_ram_info) +#define HAX_VM_IOCTL_SET_RAM _IOWR(0, 0x82, struct hax_set_ram_info) +#define HAX_VM_IOCTL_VCPU_DESTROY _IOW(0, 0x83, uint32_t) +#define HAX_VM_IOCTL_NOTIFY_QEMU_VERSION _IOW(0, 0x84, struct hax_qemu_version) + +#define HAX_VCPU_IOCTL_RUN _IO(0, 0xc0) +#define HAX_VCPU_IOCTL_SET_MSRS _IOWR(0, 0xc1, struct hax_msr_data) +#define HAX_VCPU_IOCTL_GET_MSRS _IOWR(0, 0xc2, struct hax_msr_data) + +#define HAX_VCPU_IOCTL_SET_FPU _IOW(0, 0xc3, struct fx_layout) +#define HAX_VCPU_IOCTL_GET_FPU _IOR(0, 0xc4, struct fx_layout) + +#define HAX_VCPU_IOCTL_SETUP_TUNNEL _IOWR(0, 0xc5, struct hax_tunnel_info) +#define HAX_VCPU_IOCTL_INTERRUPT _IOWR(0, 0xc6, uint32_t) +#define HAX_VCPU_SET_REGS _IOWR(0, 0xc7, struct vcpu_state_t) +#define HAX_VCPU_GET_REGS _IOWR(0, 0xc8, struct vcpu_state_t) + +#endif /* TARGET_I386_HAX_DARWIN_H */ diff --git a/target/i386/hax-i386.h b/target/i386/hax-i386.h new file mode 100644 index 0000000000..8ffe91fcb5 --- /dev/null +++ b/target/i386/hax-i386.h @@ -0,0 +1,94 @@ +/* + * QEMU HAXM support + * + * Copyright (c) 2011 Intel Corporation + * Written by: + * Jiang Yunhong<yunhong.jiang@intel.com> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#ifndef _HAX_I386_H +#define _HAX_I386_H + +#include "cpu.h" +#include "sysemu/hax.h" + +#ifdef CONFIG_DARWIN +typedef int hax_fd; +#endif + +#ifdef CONFIG_WIN32 +typedef HANDLE hax_fd; +#endif + +extern struct hax_state hax_global; +struct hax_vcpu_state { + hax_fd fd; + int vcpu_id; + struct hax_tunnel *tunnel; + unsigned char *iobuf; +}; + +struct hax_state { + hax_fd fd; /* the global hax device interface */ + uint32_t version; + struct hax_vm *vm; + uint64_t mem_quota; +}; + +#define HAX_MAX_VCPU 0x10 +#define MAX_VM_ID 0x40 +#define MAX_VCPU_ID 0x40 + +struct hax_vm { + hax_fd fd; + int id; + struct hax_vcpu_state *vcpus[HAX_MAX_VCPU]; +}; + +#ifdef NEED_CPU_H +/* Functions exported to host specific mode */ +hax_fd hax_vcpu_get_fd(CPUArchState *env); +int valid_hax_tunnel_size(uint16_t size); + +/* Host specific functions */ +int hax_mod_version(struct hax_state *hax, struct hax_module_version *version); +int hax_inject_interrupt(CPUArchState *env, int vector); +struct hax_vm *hax_vm_create(struct hax_state *hax); +int hax_vcpu_run(struct hax_vcpu_state *vcpu); +int hax_vcpu_create(int id); +int hax_sync_vcpu_state(CPUArchState *env, struct vcpu_state_t *state, + int set); +int hax_sync_msr(CPUArchState *env, struct hax_msr_data *msrs, int set); +int hax_sync_fpu(CPUArchState *env, struct fx_layout *fl, int set); +#endif + +int hax_vm_destroy(struct hax_vm *vm); +int hax_capability(struct hax_state *hax, struct hax_capabilityinfo *cap); +int hax_notify_qemu_version(hax_fd vm_fd, struct hax_qemu_version *qversion); +int hax_set_ram(uint64_t start_pa, uint32_t size, uint64_t host_va, int flags); + +/* Common host function */ +int hax_host_create_vm(struct hax_state *hax, int *vm_id); +hax_fd hax_host_open_vm(struct hax_state *hax, int vm_id); +int hax_host_create_vcpu(hax_fd vm_fd, int vcpuid); +hax_fd hax_host_open_vcpu(int vmid, int vcpuid); +int hax_host_setup_vcpu_channel(struct hax_vcpu_state *vcpu); +hax_fd hax_mod_open(void); +void hax_memory_init(void); + + +#ifdef CONFIG_DARWIN +#include "target/i386/hax-darwin.h" +#endif + +#ifdef CONFIG_WIN32 +#include "target/i386/hax-windows.h" +#endif + +#include "target/i386/hax-interface.h" + +#endif diff --git a/target/i386/hax-interface.h b/target/i386/hax-interface.h new file mode 100644 index 0000000000..d141308831 --- /dev/null +++ b/target/i386/hax-interface.h @@ -0,0 +1,361 @@ +/* + * QEMU HAXM support + * + * Copyright (c) 2011 Intel Corporation + * Written by: + * Jiang Yunhong<yunhong.jiang@intel.com> + * Xin Xiaohui<xiaohui.xin@intel.com> + * Zhang Xiantao<xiantao.zhang@intel.com> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +/* Interface with HAX kernel module */ + +#ifndef _HAX_INTERFACE_H +#define _HAX_INTERFACE_H + +/* fx_layout has 3 formats table 3-56, 512bytes */ +struct fx_layout { + uint16_t fcw; + uint16_t fsw; + uint8_t ftw; + uint8_t res1; + uint16_t fop; + union { + struct { + uint32_t fip; + uint16_t fcs; + uint16_t res2; + }; + uint64_t fpu_ip; + }; + union { + struct { + uint32_t fdp; + uint16_t fds; + uint16_t res3; + }; + uint64_t fpu_dp; + }; + uint32_t mxcsr; + uint32_t mxcsr_mask; + uint8_t st_mm[8][16]; + uint8_t mmx_1[8][16]; + uint8_t mmx_2[8][16]; + uint8_t pad[96]; +} __attribute__ ((aligned(8))); + +struct vmx_msr { + uint64_t entry; + uint64_t value; +} __attribute__ ((__packed__)); + +/* + * Fixed array is not good, but it makes Mac support a bit easier by avoiding + * memory map or copyin staff. + */ +#define HAX_MAX_MSR_ARRAY 0x20 +struct hax_msr_data { + uint16_t nr_msr; + uint16_t done; + uint16_t pad[2]; + struct vmx_msr entries[HAX_MAX_MSR_ARRAY]; +} __attribute__ ((__packed__)); + +union interruptibility_state_t { + uint32_t raw; + struct { + uint32_t sti_blocking:1; + uint32_t movss_blocking:1; + uint32_t smi_blocking:1; + uint32_t nmi_blocking:1; + uint32_t reserved:28; + }; + uint64_t pad; +}; + +typedef union interruptibility_state_t interruptibility_state_t; + +/* Segment descriptor */ +struct segment_desc_t { + uint16_t selector; + uint16_t _dummy; + uint32_t limit; + uint64_t base; + union { + struct { + uint32_t type:4; + uint32_t desc:1; + uint32_t dpl:2; + uint32_t present:1; + uint32_t:4; + uint32_t available:1; + uint32_t long_mode:1; + uint32_t operand_size:1; + uint32_t granularity:1; + uint32_t null:1; + uint32_t:15; + }; + uint32_t ar; + }; + uint32_t ipad; +}; + +typedef struct segment_desc_t segment_desc_t; + +struct vcpu_state_t { + union { + uint64_t _regs[16]; + struct { + union { + struct { + uint8_t _al, _ah; + }; + uint16_t _ax; + uint32_t _eax; + uint64_t _rax; + }; + union { + struct { + uint8_t _cl, _ch; + }; + uint16_t _cx; + uint32_t _ecx; + uint64_t _rcx; + }; + union { + struct { + uint8_t _dl, _dh; + }; + uint16_t _dx; + uint32_t _edx; + uint64_t _rdx; + }; + union { + struct { + uint8_t _bl, _bh; + }; + uint16_t _bx; + uint32_t _ebx; + uint64_t _rbx; + }; + union { + uint16_t _sp; + uint32_t _esp; + uint64_t _rsp; + }; + union { + uint16_t _bp; + uint32_t _ebp; + uint64_t _rbp; + }; + union { + uint16_t _si; + uint32_t _esi; + uint64_t _rsi; + }; + union { + uint16_t _di; + uint32_t _edi; + uint64_t _rdi; + }; + + uint64_t _r8; + uint64_t _r9; + uint64_t _r10; + uint64_t _r11; + uint64_t _r12; + uint64_t _r13; + uint64_t _r14; + uint64_t _r15; + }; + }; + + union { + uint32_t _eip; + uint64_t _rip; + }; + + union { + uint32_t _eflags; + uint64_t _rflags; + }; + + segment_desc_t _cs; + segment_desc_t _ss; + segment_desc_t _ds; + segment_desc_t _es; + segment_desc_t _fs; + segment_desc_t _gs; + segment_desc_t _ldt; + segment_desc_t _tr; + + segment_desc_t _gdt; + segment_desc_t _idt; + + uint64_t _cr0; + uint64_t _cr2; + uint64_t _cr3; + uint64_t _cr4; + + uint64_t _dr0; + uint64_t _dr1; + uint64_t _dr2; + uint64_t _dr3; + uint64_t _dr6; + uint64_t _dr7; + uint64_t _pde; + + uint32_t _efer; + + uint32_t _sysenter_cs; + uint64_t _sysenter_eip; + uint64_t _sysenter_esp; + + uint32_t _activity_state; + uint32_t pad; + interruptibility_state_t _interruptibility_state; +}; + +/* HAX exit status */ +enum exit_status { + /* IO port request */ + HAX_EXIT_IO = 1, + /* MMIO instruction emulation */ + HAX_EXIT_MMIO, + /* QEMU emulation mode request, currently means guest enter non-PG mode */ + HAX_EXIT_REAL, + /* + * Interrupt window open, qemu can inject interrupt now + * Also used when signal pending since at that time qemu usually need + * check interrupt + */ + HAX_EXIT_INTERRUPT, + /* Unknown vmexit, mostly trigger reboot */ + HAX_EXIT_UNKNOWN_VMEXIT, + /* HALT from guest */ + HAX_EXIT_HLT, + /* Reboot request, like because of tripple fault in guest */ + HAX_EXIT_STATECHANGE, + /* the vcpu is now only paused when destroy, so simply return to hax */ + HAX_EXIT_PAUSED, + HAX_EXIT_FAST_MMIO, +}; + +/* + * The interface definition: + * 1. vcpu_run execute will return 0 on success, otherwise mean failed + * 2. exit_status return the exit reason, as stated in enum exit_status + * 3. exit_reason is the vmx exit reason + */ +struct hax_tunnel { + uint32_t _exit_reason; + uint32_t _exit_flag; + uint32_t _exit_status; + uint32_t user_event_pending; + int ready_for_interrupt_injection; + int request_interrupt_window; + union { + struct { + /* 0: read, 1: write */ +#define HAX_EXIT_IO_IN 1 +#define HAX_EXIT_IO_OUT 0 + uint8_t _direction; + uint8_t _df; + uint16_t _size; + uint16_t _port; + uint16_t _count; + uint8_t _flags; + uint8_t _pad0; + uint16_t _pad1; + uint32_t _pad2; + uint64_t _vaddr; + } pio; + struct { + uint64_t gla; + } mmio; + struct { + } state; + }; +} __attribute__ ((__packed__)); + +struct hax_module_version { + uint32_t compat_version; + uint32_t cur_version; +} __attribute__ ((__packed__)); + +/* This interface is support only after API version 2 */ +struct hax_qemu_version { + /* Current API version in QEMU */ + uint32_t cur_version; + /* The minimum API version supported by QEMU */ + uint32_t min_version; +} __attribute__ ((__packed__)); + +/* The mac specfic interface to qemu, mostly is ioctl related */ +struct hax_tunnel_info { + uint64_t va; + uint64_t io_va; + uint16_t size; + uint16_t pad[3]; +} __attribute__ ((__packed__)); + +struct hax_alloc_ram_info { + uint32_t size; + uint32_t pad; + uint64_t va; +} __attribute__ ((__packed__)); +#define HAX_RAM_INFO_ROM 0x01 /* Read-Only */ +#define HAX_RAM_INFO_INVALID 0x80 /* Unmapped, usually used for MMIO */ +struct hax_set_ram_info { + uint64_t pa_start; + uint32_t size; + uint8_t flags; + uint8_t pad[3]; + uint64_t va; +} __attribute__ ((__packed__)); + +#define HAX_CAP_STATUS_WORKING 0x1 +#define HAX_CAP_STATUS_NOTWORKING 0x0 +#define HAX_CAP_WORKSTATUS_MASK 0x1 + +#define HAX_CAP_FAILREASON_VT 0x1 +#define HAX_CAP_FAILREASON_NX 0x2 + +#define HAX_CAP_MEMQUOTA 0x2 +#define HAX_CAP_UG 0x4 + +struct hax_capabilityinfo { + /* bit 0: 1 - working + * 0 - not working, possibly because NT/NX disabled + * bit 1: 1 - memory limitation working + * 0 - no memory limitation + */ + uint16_t wstatus; + /* valid when not working + * bit 0: VT not enabeld + * bit 1: NX not enabled*/ + uint16_t winfo; + uint32_t pad; + uint64_t mem_quota; +} __attribute__ ((__packed__)); + +struct hax_fastmmio { + uint64_t gpa; + union { + uint64_t value; + uint64_t gpa2; /* since HAX API v4 */ + }; + uint8_t size; + uint8_t direction; + uint16_t reg_index; + uint32_t pad0; + uint64_t _cr0; + uint64_t _cr2; + uint64_t _cr3; + uint64_t _cr4; +} __attribute__ ((__packed__)); +#endif diff --git a/target/i386/hax-mem.c b/target/i386/hax-mem.c new file mode 100644 index 0000000000..2884040021 --- /dev/null +++ b/target/i386/hax-mem.c @@ -0,0 +1,289 @@ +/* + * HAX memory mapping operations + * + * Copyright (c) 2015-16 Intel Corporation + * Copyright 2016 Google, Inc. + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" +#include "cpu.h" +#include "exec/address-spaces.h" +#include "exec/exec-all.h" + +#include "target/i386/hax-i386.h" +#include "qemu/queue.h" + +#define DEBUG_HAX_MEM 0 + +#define DPRINTF(fmt, ...) \ + do { \ + if (DEBUG_HAX_MEM) { \ + fprintf(stdout, fmt, ## __VA_ARGS__); \ + } \ + } while (0) + +/** + * HAXMapping: describes a pending guest physical memory mapping + * + * @start_pa: a guest physical address marking the start of the region; must be + * page-aligned + * @size: a guest physical address marking the end of the region; must be + * page-aligned + * @host_va: the host virtual address of the start of the mapping + * @flags: mapping parameters e.g. HAX_RAM_INFO_ROM or HAX_RAM_INFO_INVALID + * @entry: additional fields for linking #HAXMapping instances together + */ +typedef struct HAXMapping { + uint64_t start_pa; + uint32_t size; + uint64_t host_va; + int flags; + QTAILQ_ENTRY(HAXMapping) entry; +} HAXMapping; + +/* + * A doubly-linked list (actually a tail queue) of the pending page mappings + * for the ongoing memory transaction. + * + * It is used to optimize the number of page mapping updates done through the + * kernel module. For example, it's effective when a driver is digging an MMIO + * hole inside an existing memory mapping. It will get a deletion of the whole + * region, then the addition of the 2 remaining RAM areas around the hole and + * finally the memory transaction commit. During the commit, it will effectively + * send to the kernel only the removal of the pages from the MMIO hole after + * having computed locally the result of the deletion and additions. + */ +static QTAILQ_HEAD(HAXMappingListHead, HAXMapping) mappings = + QTAILQ_HEAD_INITIALIZER(mappings); + +/** + * hax_mapping_dump_list: dumps @mappings to stdout (for debugging) + */ +static void hax_mapping_dump_list(void) +{ + HAXMapping *entry; + + DPRINTF("%s updates:\n", __func__); + QTAILQ_FOREACH(entry, &mappings, entry) { + DPRINTF("\t%c 0x%016" PRIx64 "->0x%016" PRIx64 " VA 0x%016" PRIx64 + "%s\n", entry->flags & HAX_RAM_INFO_INVALID ? '-' : '+', + entry->start_pa, entry->start_pa + entry->size, entry->host_va, + entry->flags & HAX_RAM_INFO_ROM ? " ROM" : ""); + } +} + +static void hax_insert_mapping_before(HAXMapping *next, uint64_t start_pa, + uint32_t size, uint64_t host_va, + uint8_t flags) +{ + HAXMapping *entry; + + entry = g_malloc0(sizeof(*entry)); + entry->start_pa = start_pa; + entry->size = size; + entry->host_va = host_va; + entry->flags = flags; + if (!next) { + QTAILQ_INSERT_TAIL(&mappings, entry, entry); + } else { + QTAILQ_INSERT_BEFORE(next, entry, entry); + } +} + +static bool hax_mapping_is_opposite(HAXMapping *entry, uint64_t host_va, + uint8_t flags) +{ + /* removed then added without change for the read-only flag */ + bool nop_flags = (entry->flags ^ flags) == HAX_RAM_INFO_INVALID; + + return (entry->host_va == host_va) && nop_flags; +} + +static void hax_update_mapping(uint64_t start_pa, uint32_t size, + uint64_t host_va, uint8_t flags) +{ + uint64_t end_pa = start_pa + size; + uint32_t chunk_sz; + HAXMapping *entry, *next; + + QTAILQ_FOREACH_SAFE(entry, &mappings, entry, next) { + if (start_pa >= entry->start_pa + entry->size) { + continue; + } + if (start_pa < entry->start_pa) { + chunk_sz = end_pa <= entry->start_pa ? size + : entry->start_pa - start_pa; + hax_insert_mapping_before(entry, start_pa, chunk_sz, + host_va, flags); + start_pa += chunk_sz; + host_va += chunk_sz; + size -= chunk_sz; + } + chunk_sz = MIN(size, entry->size); + if (chunk_sz) { + bool nop = hax_mapping_is_opposite(entry, host_va, flags); + bool partial = chunk_sz < entry->size; + if (partial) { + /* remove the beginning of the existing chunk */ + entry->start_pa += chunk_sz; + entry->host_va += chunk_sz; + entry->size -= chunk_sz; + if (!nop) { + hax_insert_mapping_before(entry, start_pa, chunk_sz, + host_va, flags); + } + } else { /* affects the full mapping entry */ + if (nop) { /* no change to this mapping, remove it */ + QTAILQ_REMOVE(&mappings, entry, entry); + g_free(entry); + } else { /* update mapping properties */ + entry->host_va = host_va; + entry->flags = flags; + } + } + start_pa += chunk_sz; + host_va += chunk_sz; + size -= chunk_sz; + } + if (!size) { /* we are done */ + break; + } + } + if (size) { /* add the leftover */ + hax_insert_mapping_before(NULL, start_pa, size, host_va, flags); + } +} + +static void hax_process_section(MemoryRegionSection *section, uint8_t flags) +{ + MemoryRegion *mr = section->mr; + hwaddr start_pa = section->offset_within_address_space; + ram_addr_t size = int128_get64(section->size); + unsigned int delta; + uint64_t host_va; + + /* We only care about RAM pages */ + if (!memory_region_is_ram(mr)) { + return; + } + + /* Adjust start_pa and size so that they are page-aligned. (Cf + * kvm_set_phys_mem() in kvm-all.c). + */ + delta = qemu_real_host_page_size - (start_pa & ~qemu_real_host_page_mask); + delta &= ~qemu_real_host_page_mask; + if (delta > size) { + return; + } + start_pa += delta; + size -= delta; + size &= qemu_real_host_page_mask; + if (!size || (start_pa & ~qemu_real_host_page_mask)) { + return; + } + + host_va = (uintptr_t)memory_region_get_ram_ptr(mr) + + section->offset_within_region + delta; + if (memory_region_is_rom(section->mr)) { + flags |= HAX_RAM_INFO_ROM; + } + + /* the kernel module interface uses 32-bit sizes (but we could split...) */ + g_assert(size <= UINT32_MAX); + + hax_update_mapping(start_pa, size, host_va, flags); +} + +static void hax_region_add(MemoryListener *listener, + MemoryRegionSection *section) +{ + memory_region_ref(section->mr); + hax_process_section(section, 0); +} + +static void hax_region_del(MemoryListener *listener, + MemoryRegionSection *section) +{ + hax_process_section(section, HAX_RAM_INFO_INVALID); + memory_region_unref(section->mr); +} + +static void hax_transaction_begin(MemoryListener *listener) +{ + g_assert(QTAILQ_EMPTY(&mappings)); +} + +static void hax_transaction_commit(MemoryListener *listener) +{ + if (!QTAILQ_EMPTY(&mappings)) { + HAXMapping *entry, *next; + + if (DEBUG_HAX_MEM) { + hax_mapping_dump_list(); + } + QTAILQ_FOREACH_SAFE(entry, &mappings, entry, next) { + if (entry->flags & HAX_RAM_INFO_INVALID) { + /* for unmapping, put the values expected by the kernel */ + entry->flags = HAX_RAM_INFO_INVALID; + entry->host_va = 0; + } + if (hax_set_ram(entry->start_pa, entry->size, + entry->host_va, entry->flags)) { + fprintf(stderr, "%s: Failed mapping @0x%016" PRIx64 "+0x%" + PRIx32 " flags %02x\n", __func__, entry->start_pa, + entry->size, entry->flags); + } + QTAILQ_REMOVE(&mappings, entry, entry); + g_free(entry); + } + } +} + +/* currently we fake the dirty bitmap sync, always dirty */ +static void hax_log_sync(MemoryListener *listener, + MemoryRegionSection *section) +{ + MemoryRegion *mr = section->mr; + + if (!memory_region_is_ram(mr)) { + /* Skip MMIO regions */ + return; + } + + memory_region_set_dirty(mr, 0, int128_get64(section->size)); +} + +static MemoryListener hax_memory_listener = { + .begin = hax_transaction_begin, + .commit = hax_transaction_commit, + .region_add = hax_region_add, + .region_del = hax_region_del, + .log_sync = hax_log_sync, + .priority = 10, +}; + +static void hax_ram_block_added(RAMBlockNotifier *n, void *host, size_t size) +{ + /* + * In HAX, QEMU allocates the virtual address, and HAX kernel + * populates the memory with physical memory. Currently we have no + * paging, so user should make sure enough free memory in advance. + */ + if (hax_populate_ram((uint64_t)(uintptr_t)host, size) < 0) { + fprintf(stderr, "HAX failed to populate RAM"); + abort(); + } +} + +static struct RAMBlockNotifier hax_ram_notifier = { + .ram_block_added = hax_ram_block_added, +}; + +void hax_memory_init(void) +{ + ram_block_notifier_add(&hax_ram_notifier); + memory_listener_register(&hax_memory_listener, &address_space_memory); +} diff --git a/target/i386/hax-windows.c b/target/i386/hax-windows.c new file mode 100644 index 0000000000..15a180b646 --- /dev/null +++ b/target/i386/hax-windows.c @@ -0,0 +1,479 @@ +/* + * QEMU HAXM support + * + * Copyright (c) 2011 Intel Corporation + * Written by: + * Jiang Yunhong<yunhong.jiang@intel.com> + * + * 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 "cpu.h" +#include "exec/exec-all.h" +#include "hax-i386.h" + +/* + * return 0 when success, -1 when driver not loaded, + * other negative value for other failure + */ +static int hax_open_device(hax_fd *fd) +{ + uint32_t errNum = 0; + HANDLE hDevice; + + if (!fd) { + return -2; + } + + hDevice = CreateFile("\\\\.\\HAX", + GENERIC_READ | GENERIC_WRITE, + 0, NULL, CREATE_ALWAYS, FILE_ATTRIBUTE_NORMAL, NULL); + + if (hDevice == INVALID_HANDLE_VALUE) { + fprintf(stderr, "Failed to open the HAX device!\n"); + errNum = GetLastError(); + if (errNum == ERROR_FILE_NOT_FOUND) { + return -1; + } + return -2; + } + *fd = hDevice; + return 0; +} + +/* hax_fd hax_mod_open */ + hax_fd hax_mod_open(void) +{ + int ret; + hax_fd fd = NULL; + + ret = hax_open_device(&fd); + if (ret != 0) { + fprintf(stderr, "Open HAX device failed\n"); + } + + return fd; +} + +int hax_populate_ram(uint64_t va, uint32_t size) +{ + int ret; + struct hax_alloc_ram_info info; + HANDLE hDeviceVM; + DWORD dSize = 0; + + if (!hax_global.vm || !hax_global.vm->fd) { + fprintf(stderr, "Allocate memory before vm create?\n"); + return -EINVAL; + } + + info.size = size; + info.va = va; + + hDeviceVM = hax_global.vm->fd; + + ret = DeviceIoControl(hDeviceVM, + HAX_VM_IOCTL_ALLOC_RAM, + &info, sizeof(info), NULL, 0, &dSize, + (LPOVERLAPPED) NULL); + + if (!ret) { + fprintf(stderr, "Failed to allocate %x memory\n", size); + return ret; + } + + return 0; +} + +int hax_set_ram(uint64_t start_pa, uint32_t size, uint64_t host_va, int flags) +{ + struct hax_set_ram_info info; + HANDLE hDeviceVM = hax_global.vm->fd; + DWORD dSize = 0; + int ret; + + info.pa_start = start_pa; + info.size = size; + info.va = host_va; + info.flags = (uint8_t) flags; + + ret = DeviceIoControl(hDeviceVM, HAX_VM_IOCTL_SET_RAM, + &info, sizeof(info), NULL, 0, &dSize, + (LPOVERLAPPED) NULL); + + if (!ret) { + return -EFAULT; + } else { + return 0; + } +} + +int hax_capability(struct hax_state *hax, struct hax_capabilityinfo *cap) +{ + int ret; + HANDLE hDevice = hax->fd; /* handle to hax module */ + DWORD dSize = 0; + DWORD err = 0; + + if (hax_invalid_fd(hDevice)) { + fprintf(stderr, "Invalid fd for hax device!\n"); + return -ENODEV; + } + + ret = DeviceIoControl(hDevice, HAX_IOCTL_CAPABILITY, NULL, 0, cap, + sizeof(*cap), &dSize, (LPOVERLAPPED) NULL); + + if (!ret) { + err = GetLastError(); + if (err == ERROR_INSUFFICIENT_BUFFER || err == ERROR_MORE_DATA) { + fprintf(stderr, "hax capability is too long to hold.\n"); + } + fprintf(stderr, "Failed to get Hax capability:%luu\n", err); + return -EFAULT; + } else { + return 0; + } +} + +int hax_mod_version(struct hax_state *hax, struct hax_module_version *version) +{ + int ret; + HANDLE hDevice = hax->fd; /* handle to hax module */ + DWORD dSize = 0; + DWORD err = 0; + + if (hax_invalid_fd(hDevice)) { + fprintf(stderr, "Invalid fd for hax device!\n"); + return -ENODEV; + } + + ret = DeviceIoControl(hDevice, + HAX_IOCTL_VERSION, + NULL, 0, + version, sizeof(*version), &dSize, + (LPOVERLAPPED) NULL); + + if (!ret) { + err = GetLastError(); + if (err == ERROR_INSUFFICIENT_BUFFER || err == ERROR_MORE_DATA) { + fprintf(stderr, "hax module verion is too long to hold.\n"); + } + fprintf(stderr, "Failed to get Hax module version:%lu\n", err); + return -EFAULT; + } else { + return 0; + } +} + +static char *hax_vm_devfs_string(int vm_id) +{ + char *name; + + if (vm_id > MAX_VM_ID) { + fprintf(stderr, "Too big VM id\n"); + return NULL; + } + +#define HAX_VM_DEVFS "\\\\.\\hax_vmxx" + name = g_strdup(HAX_VM_DEVFS); + if (!name) { + return NULL; + } + + snprintf(name, sizeof HAX_VM_DEVFS, "\\\\.\\hax_vm%02d", vm_id); + return name; +} + +static char *hax_vcpu_devfs_string(int vm_id, int vcpu_id) +{ + char *name; + + if (vm_id > MAX_VM_ID || vcpu_id > MAX_VCPU_ID) { + fprintf(stderr, "Too big vm id %x or vcpu id %x\n", vm_id, vcpu_id); + return NULL; + } + +#define HAX_VCPU_DEVFS "\\\\.\\hax_vmxx_vcpuxx" + name = g_strdup(HAX_VCPU_DEVFS); + if (!name) { + return NULL; + } + + snprintf(name, sizeof HAX_VCPU_DEVFS, "\\\\.\\hax_vm%02d_vcpu%02d", + vm_id, vcpu_id); + return name; +} + +int hax_host_create_vm(struct hax_state *hax, int *vmid) +{ + int ret; + int vm_id = 0; + DWORD dSize = 0; + + if (hax_invalid_fd(hax->fd)) { + return -EINVAL; + } + + if (hax->vm) { + return 0; + } + + ret = DeviceIoControl(hax->fd, + HAX_IOCTL_CREATE_VM, + NULL, 0, &vm_id, sizeof(vm_id), &dSize, + (LPOVERLAPPED) NULL); + if (!ret) { + fprintf(stderr, "Failed to create VM. Error code: %lu\n", + GetLastError()); + return -1; + } + *vmid = vm_id; + return 0; +} + +hax_fd hax_host_open_vm(struct hax_state *hax, int vm_id) +{ + char *vm_name = NULL; + hax_fd hDeviceVM; + + vm_name = hax_vm_devfs_string(vm_id); + if (!vm_name) { + fprintf(stderr, "Failed to open VM. VM name is null\n"); + return INVALID_HANDLE_VALUE; + } + + hDeviceVM = CreateFile(vm_name, + GENERIC_READ | GENERIC_WRITE, + 0, NULL, CREATE_ALWAYS, FILE_ATTRIBUTE_NORMAL, NULL); + if (hDeviceVM == INVALID_HANDLE_VALUE) { + fprintf(stderr, "Open the vm device error:%s, ec:%lu\n", + vm_name, GetLastError()); + } + + g_free(vm_name); + return hDeviceVM; +} + +int hax_notify_qemu_version(hax_fd vm_fd, struct hax_qemu_version *qversion) +{ + int ret; + DWORD dSize = 0; + if (hax_invalid_fd(vm_fd)) { + return -EINVAL; + } + ret = DeviceIoControl(vm_fd, + HAX_VM_IOCTL_NOTIFY_QEMU_VERSION, + qversion, sizeof(struct hax_qemu_version), + NULL, 0, &dSize, (LPOVERLAPPED) NULL); + if (!ret) { + fprintf(stderr, "Failed to notify qemu API version\n"); + return -1; + } + return 0; +} + +int hax_host_create_vcpu(hax_fd vm_fd, int vcpuid) +{ + int ret; + DWORD dSize = 0; + + ret = DeviceIoControl(vm_fd, + HAX_VM_IOCTL_VCPU_CREATE, + &vcpuid, sizeof(vcpuid), NULL, 0, &dSize, + (LPOVERLAPPED) NULL); + if (!ret) { + fprintf(stderr, "Failed to create vcpu %x\n", vcpuid); + return -1; + } + + return 0; +} + +hax_fd hax_host_open_vcpu(int vmid, int vcpuid) +{ + char *devfs_path = NULL; + hax_fd hDeviceVCPU; + + devfs_path = hax_vcpu_devfs_string(vmid, vcpuid); + if (!devfs_path) { + fprintf(stderr, "Failed to get the devfs\n"); + return INVALID_HANDLE_VALUE; + } + + hDeviceVCPU = CreateFile(devfs_path, + GENERIC_READ | GENERIC_WRITE, + 0, NULL, CREATE_ALWAYS, FILE_ATTRIBUTE_NORMAL, + NULL); + + if (hDeviceVCPU == INVALID_HANDLE_VALUE) { + fprintf(stderr, "Failed to open the vcpu devfs\n"); + } + g_free(devfs_path); + return hDeviceVCPU; +} + +int hax_host_setup_vcpu_channel(struct hax_vcpu_state *vcpu) +{ + hax_fd hDeviceVCPU = vcpu->fd; + int ret; + struct hax_tunnel_info info; + DWORD dSize = 0; + + ret = DeviceIoControl(hDeviceVCPU, + HAX_VCPU_IOCTL_SETUP_TUNNEL, + NULL, 0, &info, sizeof(info), &dSize, + (LPOVERLAPPED) NULL); + if (!ret) { + fprintf(stderr, "Failed to setup the hax tunnel\n"); + return -1; + } + + if (!valid_hax_tunnel_size(info.size)) { + fprintf(stderr, "Invalid hax tunnel size %x\n", info.size); + ret = -EINVAL; + return ret; + } + vcpu->tunnel = (struct hax_tunnel *) (intptr_t) (info.va); + vcpu->iobuf = (unsigned char *) (intptr_t) (info.io_va); + return 0; +} + +int hax_vcpu_run(struct hax_vcpu_state *vcpu) +{ + int ret; + HANDLE hDeviceVCPU = vcpu->fd; + DWORD dSize = 0; + + ret = DeviceIoControl(hDeviceVCPU, + HAX_VCPU_IOCTL_RUN, + NULL, 0, NULL, 0, &dSize, (LPOVERLAPPED) NULL); + if (!ret) { + return -EFAULT; + } else { + return 0; + } +} + +int hax_sync_fpu(CPUArchState *env, struct fx_layout *fl, int set) +{ + int ret; + hax_fd fd; + HANDLE hDeviceVCPU; + DWORD dSize = 0; + + fd = hax_vcpu_get_fd(env); + if (hax_invalid_fd(fd)) { + return -1; + } + + hDeviceVCPU = fd; + + if (set) { + ret = DeviceIoControl(hDeviceVCPU, + HAX_VCPU_IOCTL_SET_FPU, + fl, sizeof(*fl), NULL, 0, &dSize, + (LPOVERLAPPED) NULL); + } else { + ret = DeviceIoControl(hDeviceVCPU, + HAX_VCPU_IOCTL_GET_FPU, + NULL, 0, fl, sizeof(*fl), &dSize, + (LPOVERLAPPED) NULL); + } + if (!ret) { + return -EFAULT; + } else { + return 0; + } +} + +int hax_sync_msr(CPUArchState *env, struct hax_msr_data *msrs, int set) +{ + int ret; + hax_fd fd; + HANDLE hDeviceVCPU; + DWORD dSize = 0; + + fd = hax_vcpu_get_fd(env); + if (hax_invalid_fd(fd)) { + return -1; + } + hDeviceVCPU = fd; + + if (set) { + ret = DeviceIoControl(hDeviceVCPU, + HAX_VCPU_IOCTL_SET_MSRS, + msrs, sizeof(*msrs), + msrs, sizeof(*msrs), &dSize, (LPOVERLAPPED) NULL); + } else { + ret = DeviceIoControl(hDeviceVCPU, + HAX_VCPU_IOCTL_GET_MSRS, + msrs, sizeof(*msrs), + msrs, sizeof(*msrs), &dSize, (LPOVERLAPPED) NULL); + } + if (!ret) { + return -EFAULT; + } else { + return 0; + } +} + +int hax_sync_vcpu_state(CPUArchState *env, struct vcpu_state_t *state, int set) +{ + int ret; + hax_fd fd; + HANDLE hDeviceVCPU; + DWORD dSize; + + fd = hax_vcpu_get_fd(env); + if (hax_invalid_fd(fd)) { + return -1; + } + + hDeviceVCPU = fd; + + if (set) { + ret = DeviceIoControl(hDeviceVCPU, + HAX_VCPU_SET_REGS, + state, sizeof(*state), + NULL, 0, &dSize, (LPOVERLAPPED) NULL); + } else { + ret = DeviceIoControl(hDeviceVCPU, + HAX_VCPU_GET_REGS, + NULL, 0, + state, sizeof(*state), &dSize, + (LPOVERLAPPED) NULL); + } + if (!ret) { + return -EFAULT; + } else { + return 0; + } +} + +int hax_inject_interrupt(CPUArchState *env, int vector) +{ + int ret; + hax_fd fd; + HANDLE hDeviceVCPU; + DWORD dSize; + + fd = hax_vcpu_get_fd(env); + if (hax_invalid_fd(fd)) { + return -1; + } + + hDeviceVCPU = fd; + + ret = DeviceIoControl(hDeviceVCPU, + HAX_VCPU_IOCTL_INTERRUPT, + &vector, sizeof(vector), NULL, 0, &dSize, + (LPOVERLAPPED) NULL); + if (!ret) { + return -EFAULT; + } else { + return 0; + } +} diff --git a/target/i386/hax-windows.h b/target/i386/hax-windows.h new file mode 100644 index 0000000000..1d8f68de91 --- /dev/null +++ b/target/i386/hax-windows.h @@ -0,0 +1,89 @@ +/* + * QEMU HAXM support + * + * Copyright IBM, Corp. 2008 + * + * Authors: + * Anthony Liguori <aliguori@us.ibm.com> + * + * Copyright (c) 2011 Intel Corporation + * Written by: + * Jiang Yunhong<yunhong.jiang@intel.com> + * Xin Xiaohui<xiaohui.xin@intel.com> + * Zhang Xiantao<xiantao.zhang@intel.com> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#ifndef TARGET_I386_HAX_WINDOWS_H +#define TARGET_I386_HAX_WINDOWS_H + +#include <windows.h> +#include <memory.h> +#include <malloc.h> +#include <winioctl.h> +#include <string.h> +#include <stdio.h> +#include <windef.h> + +#define HAX_INVALID_FD INVALID_HANDLE_VALUE + +static inline void hax_mod_close(struct hax_state *hax) +{ + CloseHandle(hax->fd); +} + +static inline void hax_close_fd(hax_fd fd) +{ + CloseHandle(fd); +} + +static inline int hax_invalid_fd(hax_fd fd) +{ + return (fd == INVALID_HANDLE_VALUE); +} + +#define HAX_DEVICE_TYPE 0x4000 + +#define HAX_IOCTL_VERSION CTL_CODE(HAX_DEVICE_TYPE, 0x900, \ + METHOD_BUFFERED, FILE_ANY_ACCESS) +#define HAX_IOCTL_CREATE_VM CTL_CODE(HAX_DEVICE_TYPE, 0x901, \ + METHOD_BUFFERED, FILE_ANY_ACCESS) +#define HAX_IOCTL_CAPABILITY CTL_CODE(HAX_DEVICE_TYPE, 0x910, \ + METHOD_BUFFERED, FILE_ANY_ACCESS) + +#define HAX_VM_IOCTL_VCPU_CREATE CTL_CODE(HAX_DEVICE_TYPE, 0x902, \ + METHOD_BUFFERED, FILE_ANY_ACCESS) +#define HAX_VM_IOCTL_ALLOC_RAM CTL_CODE(HAX_DEVICE_TYPE, 0x903, \ + METHOD_BUFFERED, FILE_ANY_ACCESS) +#define HAX_VM_IOCTL_SET_RAM CTL_CODE(HAX_DEVICE_TYPE, 0x904, \ + METHOD_BUFFERED, FILE_ANY_ACCESS) +#define HAX_VM_IOCTL_VCPU_DESTROY CTL_CODE(HAX_DEVICE_TYPE, 0x905, \ + METHOD_BUFFERED, FILE_ANY_ACCESS) + +#define HAX_VCPU_IOCTL_RUN CTL_CODE(HAX_DEVICE_TYPE, 0x906, \ + METHOD_BUFFERED, FILE_ANY_ACCESS) +#define HAX_VCPU_IOCTL_SET_MSRS CTL_CODE(HAX_DEVICE_TYPE, 0x907, \ + METHOD_BUFFERED, FILE_ANY_ACCESS) +#define HAX_VCPU_IOCTL_GET_MSRS CTL_CODE(HAX_DEVICE_TYPE, 0x908, \ + METHOD_BUFFERED, FILE_ANY_ACCESS) +#define HAX_VCPU_IOCTL_SET_FPU CTL_CODE(HAX_DEVICE_TYPE, 0x909, \ + METHOD_BUFFERED, FILE_ANY_ACCESS) +#define HAX_VCPU_IOCTL_GET_FPU CTL_CODE(HAX_DEVICE_TYPE, 0x90a, \ + METHOD_BUFFERED, FILE_ANY_ACCESS) + +#define HAX_VCPU_IOCTL_SETUP_TUNNEL CTL_CODE(HAX_DEVICE_TYPE, 0x90b, \ + METHOD_BUFFERED, FILE_ANY_ACCESS) +#define HAX_VCPU_IOCTL_INTERRUPT CTL_CODE(HAX_DEVICE_TYPE, 0x90c, \ + METHOD_BUFFERED, FILE_ANY_ACCESS) +#define HAX_VCPU_SET_REGS CTL_CODE(HAX_DEVICE_TYPE, 0x90d, \ + METHOD_BUFFERED, FILE_ANY_ACCESS) +#define HAX_VCPU_GET_REGS CTL_CODE(HAX_DEVICE_TYPE, 0x90e, \ + METHOD_BUFFERED, FILE_ANY_ACCESS) + +#define HAX_VM_IOCTL_NOTIFY_QEMU_VERSION CTL_CODE(HAX_DEVICE_TYPE, 0x910, \ + METHOD_BUFFERED, \ + FILE_ANY_ACCESS) +#endif /* TARGET_I386_HAX_WINDOWS_H */ diff --git a/target/i386/helper.c b/target/i386/helper.c index c86272efab..e2af3404f2 100644 --- a/target/i386/helper.c +++ b/target/i386/helper.c @@ -24,6 +24,7 @@ #include "kvm_i386.h" #ifndef CONFIG_USER_ONLY #include "sysemu/sysemu.h" +#include "sysemu/hw_accel.h" #include "monitor/monitor.h" #include "hw/i386/apic_internal.h" #endif diff --git a/target/i386/hyperv.c b/target/i386/hyperv.c index 39a230f119..8545574568 100644 --- a/target/i386/hyperv.c +++ b/target/i386/hyperv.c @@ -12,6 +12,7 @@ */ #include "qemu/osdep.h" +#include "qemu/main-loop.h" #include "hyperv.h" #include "standard-headers/asm-x86/hyperv.h" @@ -88,7 +89,7 @@ HvSintRoute *kvm_hv_sint_route_create(uint32_t vcpu_id, uint32_t sint, goto err_sint_set_notifier; } - event_notifier_set_handler(&sint_route->sint_ack_notifier, false, + event_notifier_set_handler(&sint_route->sint_ack_notifier, kvm_hv_sint_ack_handler); gsi = kvm_irqchip_add_hv_sint_route(kvm_state, vcpu_id, sint); @@ -112,7 +113,7 @@ HvSintRoute *kvm_hv_sint_route_create(uint32_t vcpu_id, uint32_t sint, err_irqfd: kvm_irqchip_release_virq(kvm_state, gsi); err_gsi: - event_notifier_set_handler(&sint_route->sint_ack_notifier, false, NULL); + event_notifier_set_handler(&sint_route->sint_ack_notifier, NULL); event_notifier_cleanup(&sint_route->sint_ack_notifier); err_sint_set_notifier: event_notifier_cleanup(&sint_route->sint_set_notifier); @@ -128,7 +129,7 @@ void kvm_hv_sint_route_destroy(HvSintRoute *sint_route) &sint_route->sint_set_notifier, sint_route->gsi); kvm_irqchip_release_virq(kvm_state, sint_route->gsi); - event_notifier_set_handler(&sint_route->sint_ack_notifier, false, NULL); + event_notifier_set_handler(&sint_route->sint_ack_notifier, NULL); event_notifier_cleanup(&sint_route->sint_ack_notifier); event_notifier_cleanup(&sint_route->sint_set_notifier); g_free(sint_route); diff --git a/target/i386/kvm.c b/target/i386/kvm.c index 10a9cd8f7f..e6c4f754ab 100644 --- a/target/i386/kvm.c +++ b/target/i386/kvm.c @@ -23,6 +23,7 @@ #include "qemu-common.h" #include "cpu.h" #include "sysemu/sysemu.h" +#include "sysemu/hw_accel.h" #include "sysemu/kvm_int.h" #include "kvm_i386.h" #include "hyperv.h" diff --git a/target/mips/kvm.c b/target/mips/kvm.c index dcf5fbba0c..998c3412c3 100644 --- a/target/mips/kvm.c +++ b/target/mips/kvm.c @@ -55,6 +55,11 @@ int kvm_arch_init(MachineState *ms, KVMState *s) return 0; } +int kvm_arch_irqchip_create(MachineState *ms, KVMState *s) +{ + return 0; +} + int kvm_arch_init_vcpu(CPUState *cs) { MIPSCPU *cpu = MIPS_CPU(cs); diff --git a/target/ppc/kvm.c b/target/ppc/kvm.c index 9c4834c4fc..ec92c64159 100644 --- a/target/ppc/kvm.c +++ b/target/ppc/kvm.c @@ -26,7 +26,7 @@ #include "cpu.h" #include "qemu/timer.h" #include "sysemu/sysemu.h" -#include "sysemu/kvm.h" +#include "sysemu/hw_accel.h" #include "sysemu/numa.h" #include "kvm_ppc.h" #include "sysemu/cpus.h" @@ -145,6 +145,11 @@ int kvm_arch_init(MachineState *ms, KVMState *s) return 0; } +int kvm_arch_irqchip_create(MachineState *ms, KVMState *s) +{ + return 0; +} + static int kvm_arch_sync_sregs(PowerPCCPU *cpu) { CPUPPCState *cenv = &cpu->env; diff --git a/target/ppc/kvm_ppc.h b/target/ppc/kvm_ppc.h index bd1d78bfbe..4b43283913 100644 --- a/target/ppc/kvm_ppc.h +++ b/target/ppc/kvm_ppc.h @@ -315,16 +315,4 @@ static inline void kvmppc_icbi_range(PowerPCCPU *cpu, uint8_t *addr, int len) #endif /* CONFIG_KVM */ -#ifndef KVM_INTERRUPT_SET -#define KVM_INTERRUPT_SET -1 -#endif - -#ifndef KVM_INTERRUPT_UNSET -#define KVM_INTERRUPT_UNSET -2 -#endif - -#ifndef KVM_INTERRUPT_SET_LEVEL -#define KVM_INTERRUPT_SET_LEVEL -3 -#endif - #endif /* KVM_PPC_H */ diff --git a/target/ppc/mmu-hash64.c b/target/ppc/mmu-hash64.c index fdb7a787bf..0efc8c63fa 100644 --- a/target/ppc/mmu-hash64.c +++ b/target/ppc/mmu-hash64.c @@ -23,7 +23,7 @@ #include "exec/exec-all.h" #include "exec/helper-proto.h" #include "qemu/error-report.h" -#include "sysemu/kvm.h" +#include "sysemu/hw_accel.h" #include "kvm_ppc.h" #include "mmu-hash64.h" #include "exec/log.h" diff --git a/target/ppc/translate_init.c b/target/ppc/translate_init.c index e6a835c14c..94dfcd7afc 100644 --- a/target/ppc/translate_init.c +++ b/target/ppc/translate_init.c @@ -21,10 +21,10 @@ #include "qemu/osdep.h" #include "disas/bfd.h" #include "exec/gdbstub.h" -#include "sysemu/kvm.h" #include "kvm_ppc.h" #include "sysemu/arch_init.h" #include "sysemu/cpus.h" +#include "sysemu/hw_accel.h" #include "cpu-models.h" #include "mmu-hash32.h" #include "mmu-hash64.h" diff --git a/target/s390x/gdbstub.c b/target/s390x/gdbstub.c index ea4dc22eeb..94ab74d58f 100644 --- a/target/s390x/gdbstub.c +++ b/target/s390x/gdbstub.c @@ -23,6 +23,7 @@ #include "exec/exec-all.h" #include "exec/gdbstub.h" #include "qemu/bitops.h" +#include "sysemu/hw_accel.h" int s390_cpu_gdb_read_register(CPUState *cs, uint8_t *mem_buf, int n) { diff --git a/target/s390x/kvm.c b/target/s390x/kvm.c index c47db9a884..3ac29f92b3 100644 --- a/target/s390x/kvm.c +++ b/target/s390x/kvm.c @@ -294,6 +294,11 @@ int kvm_arch_init(MachineState *ms, KVMState *s) return 0; } +int kvm_arch_irqchip_create(MachineState *ms, KVMState *s) +{ + return 0; +} + unsigned long kvm_arch_vcpu_id(CPUState *cpu) { return cpu->cpu_index; diff --git a/tests/Makefile.include b/tests/Makefile.include index 96f59703a1..22ea256e94 100644 --- a/tests/Makefile.include +++ b/tests/Makefile.include @@ -537,6 +537,7 @@ tests/test-qdev-global-props$(EXESUF): tests/test-qdev-global-props.o \ hw/core/bus.o \ hw/core/irq.o \ hw/core/fw-path-provider.o \ + hw/core/reset.o \ $(test-qapi-obj-y) tests/test-vmstate$(EXESUF): tests/test-vmstate.o \ migration/vmstate.o migration/qemu-file.o \ diff --git a/tests/device-introspect-test.c b/tests/device-introspect-test.c index 37debc11f9..c5637cc406 100644 --- a/tests/device-introspect-test.c +++ b/tests/device-introspect-test.c @@ -20,18 +20,24 @@ #include "qemu/osdep.h" #include "qemu-common.h" #include "qapi/qmp/qstring.h" +#include "qapi/qmp/qbool.h" +#include "qapi/qmp/qdict.h" #include "libqtest.h" const char common_args[] = "-nodefaults -machine none"; -static QList *device_type_list(bool abstract) +static QList *qom_list_types(const char *implements, bool abstract) { QDict *resp; QList *ret; + QDict *args = qdict_new(); + qdict_put(args, "abstract", qbool_from_bool(abstract)); + if (implements) { + qdict_put(args, "implements", qstring_from_str(implements)); + } resp = qmp("{'execute': 'qom-list-types'," - " 'arguments': {'implements': 'device', 'abstract': %i}}", - abstract); + " 'arguments': %p }", args); g_assert(qdict_haskey(resp, "return")); ret = qdict_get_qlist(resp, "return"); QINCREF(ret); @@ -39,6 +45,11 @@ static QList *device_type_list(bool abstract) return ret; } +static QList *device_type_list(bool abstract) +{ + return qom_list_types("device", abstract); +} + static void test_one_device(const char *type) { QDict *resp; @@ -110,6 +121,48 @@ static void test_device_intro_concrete(void) qtest_end(); } +static void test_abstract_interfaces(void) +{ + QList *all_types; + QList *obj_types; + QListEntry *ae; + + qtest_start(common_args); + /* qom-list-types implements=interface would return any type + * that implements _any_ interface (not just interface types), + * so use a trick to find the interface type names: + * - list all object types + * - list all types, and look for items that are not + * on the first list + */ + all_types = qom_list_types(NULL, false); + obj_types = qom_list_types("object", false); + + QLIST_FOREACH_ENTRY(all_types, ae) { + QDict *at = qobject_to_qdict(qlist_entry_obj(ae)); + const char *aname = qdict_get_str(at, "name"); + QListEntry *oe; + const char *found = NULL; + + QLIST_FOREACH_ENTRY(obj_types, oe) { + QDict *ot = qobject_to_qdict(qlist_entry_obj(oe)); + const char *oname = qdict_get_str(ot, "name"); + if (!strcmp(aname, oname)) { + found = oname; + break; + } + } + + /* Using g_assert_cmpstr() will give more useful failure + * messages than g_assert(found) */ + g_assert_cmpstr(aname, ==, found); + } + + QDECREF(all_types); + QDECREF(obj_types); + qtest_end(); +} + int main(int argc, char **argv) { g_test_init(&argc, &argv, NULL); @@ -118,6 +171,7 @@ int main(int argc, char **argv) qtest_add_func("device/introspect/none", test_device_intro_none); qtest_add_func("device/introspect/abstract", test_device_intro_abstract); qtest_add_func("device/introspect/concrete", test_device_intro_concrete); + qtest_add_func("device/introspect/abstract-interfaces", test_abstract_interfaces); return g_test_run(); } diff --git a/user-exec-stub.c b/user-exec-stub.c new file mode 100644 index 0000000000..dbcf1ade9c --- /dev/null +++ b/user-exec-stub.c @@ -0,0 +1,34 @@ +#include "qemu/osdep.h" +#include "qemu-common.h" +#include "qom/cpu.h" +#include "sysemu/replay.h" + +void cpu_resume(CPUState *cpu) +{ +} + +void qemu_init_vcpu(CPUState *cpu) +{ +} + +/* User mode emulation does not support record/replay yet. */ + +bool replay_exception(void) +{ + return true; +} + +bool replay_has_exception(void) +{ + return false; +} + +bool replay_interrupt(void) +{ + return true; +} + +bool replay_has_interrupt(void) +{ + return false; +} diff --git a/util/bitmap.c b/util/bitmap.c index 43ed011720..c1a84ca5e3 100644 --- a/util/bitmap.c +++ b/util/bitmap.c @@ -164,6 +164,8 @@ void bitmap_set(unsigned long *map, long start, long nr) int bits_to_set = BITS_PER_LONG - (start % BITS_PER_LONG); unsigned long mask_to_set = BITMAP_FIRST_WORD_MASK(start); + assert(start >= 0 && nr >= 0); + while (nr - bits_to_set >= 0) { *p |= mask_to_set; nr -= bits_to_set; @@ -184,6 +186,8 @@ void bitmap_set_atomic(unsigned long *map, long start, long nr) int bits_to_set = BITS_PER_LONG - (start % BITS_PER_LONG); unsigned long mask_to_set = BITMAP_FIRST_WORD_MASK(start); + assert(start >= 0 && nr >= 0); + /* First word */ if (nr - bits_to_set > 0) { atomic_or(p, mask_to_set); @@ -221,6 +225,8 @@ void bitmap_clear(unsigned long *map, long start, long nr) int bits_to_clear = BITS_PER_LONG - (start % BITS_PER_LONG); unsigned long mask_to_clear = BITMAP_FIRST_WORD_MASK(start); + assert(start >= 0 && nr >= 0); + while (nr - bits_to_clear >= 0) { *p &= ~mask_to_clear; nr -= bits_to_clear; @@ -243,6 +249,8 @@ bool bitmap_test_and_clear_atomic(unsigned long *map, long start, long nr) unsigned long dirty = 0; unsigned long old_bits; + assert(start >= 0 && nr >= 0); + /* First word */ if (nr - bits_to_clear > 0) { old_bits = atomic_fetch_and(p, ~mask_to_clear); diff --git a/util/event_notifier-posix.c b/util/event_notifier-posix.c index f2aacfc8b3..7e40252ade 100644 --- a/util/event_notifier-posix.c +++ b/util/event_notifier-posix.c @@ -90,15 +90,6 @@ int event_notifier_get_fd(const EventNotifier *e) return e->rfd; } -int event_notifier_set_handler(EventNotifier *e, - bool is_external, - EventNotifierHandler *handler) -{ - aio_set_fd_handler(iohandler_get_aio_context(), e->rfd, is_external, - (IOHandler *)handler, NULL, NULL, e); - return 0; -} - int event_notifier_set(EventNotifier *e) { static const uint64_t value = 1; diff --git a/util/event_notifier-win32.c b/util/event_notifier-win32.c index de87df02d6..519fb59123 100644 --- a/util/event_notifier-win32.c +++ b/util/event_notifier-win32.c @@ -32,18 +32,6 @@ HANDLE event_notifier_get_handle(EventNotifier *e) return e->event; } -int event_notifier_set_handler(EventNotifier *e, - bool is_external, - EventNotifierHandler *handler) -{ - if (handler) { - return qemu_add_wait_object(e->event, (IOHandler *)handler, e); - } else { - qemu_del_wait_object(e->event, (IOHandler *)handler, e); - return 0; - } -} - int event_notifier_set(EventNotifier *e) { SetEvent(e->event); diff --git a/util/qemu-thread-posix.c b/util/qemu-thread-posix.c index 37cd8ba3fe..73e3a0edf5 100644 --- a/util/qemu-thread-posix.c +++ b/util/qemu-thread-posix.c @@ -458,12 +458,6 @@ void qemu_thread_create(QemuThread *thread, const char *name, if (err) { error_exit(err, __func__); } - if (mode == QEMU_THREAD_DETACHED) { - err = pthread_attr_setdetachstate(&attr, PTHREAD_CREATE_DETACHED); - if (err) { - error_exit(err, __func__); - } - } /* Leave signal handling to the iothread. */ sigfillset(&set); @@ -476,6 +470,12 @@ void qemu_thread_create(QemuThread *thread, const char *name, qemu_thread_set_name(thread, name); } + if (mode == QEMU_THREAD_DETACHED) { + err = pthread_detach(thread->thread); + if (err) { + error_exit(err, __func__); + } + } pthread_sigmask(SIG_SETMASK, &oldset, NULL); pthread_attr_destroy(&attr); diff --git a/util/qemu-thread-win32.c b/util/qemu-thread-win32.c index 178e0168a1..29c3e4dd85 100644 --- a/util/qemu-thread-win32.c +++ b/util/qemu-thread-win32.c @@ -497,8 +497,8 @@ HANDLE qemu_thread_get_handle(QemuThread *thread) EnterCriticalSection(&data->cs); if (!data->exited) { - handle = OpenThread(SYNCHRONIZE | THREAD_SUSPEND_RESUME, FALSE, - thread->tid); + handle = OpenThread(SYNCHRONIZE | THREAD_SUSPEND_RESUME | + THREAD_SET_CONTEXT, FALSE, thread->tid); } else { handle = NULL; } @@ -65,6 +65,7 @@ int main(int argc, char **argv) #include "hw/bt.h" #include "sysemu/watchdog.h" #include "hw/smbios/smbios.h" +#include "hw/acpi/acpi.h" #include "hw/xen/xen.h" #include "hw/qdev.h" #include "hw/loader.h" @@ -92,6 +93,7 @@ int main(int argc, char **argv) #include "sysemu/cpus.h" #include "migration/colo.h" #include "sysemu/kvm.h" +#include "sysemu/hax.h" #include "qapi/qmp/qjson.h" #include "qemu/option.h" #include "qemu/config-file.h" @@ -1630,16 +1632,6 @@ void vm_state_notify(int running, RunState state) } } -/* reset/shutdown handler */ - -typedef struct QEMUResetEntry { - QTAILQ_ENTRY(QEMUResetEntry) entry; - QEMUResetHandler *func; - void *opaque; -} QEMUResetEntry; - -static QTAILQ_HEAD(reset_handlers, QEMUResetEntry) reset_handlers = - QTAILQ_HEAD_INITIALIZER(reset_handlers); static int reset_requested; static int shutdown_requested, shutdown_signal = -1; static pid_t shutdown_pid; @@ -1729,38 +1721,6 @@ static int qemu_debug_requested(void) return r; } -void qemu_register_reset(QEMUResetHandler *func, void *opaque) -{ - QEMUResetEntry *re = g_malloc0(sizeof(QEMUResetEntry)); - - re->func = func; - re->opaque = opaque; - QTAILQ_INSERT_TAIL(&reset_handlers, re, entry); -} - -void qemu_unregister_reset(QEMUResetHandler *func, void *opaque) -{ - QEMUResetEntry *re; - - QTAILQ_FOREACH(re, &reset_handlers, entry) { - if (re->func == func && re->opaque == opaque) { - QTAILQ_REMOVE(&reset_handlers, re, entry); - g_free(re); - return; - } - } -} - -void qemu_devices_reset(void) -{ - QEMUResetEntry *re, *nre; - - /* reset all devices */ - QTAILQ_FOREACH_SAFE(re, &reset_handlers, entry, nre) { - re->func(re->opaque); - } -} - void qemu_system_reset(bool report) { MachineClass *mc; @@ -1954,7 +1914,7 @@ static void main_loop(void) int64_t ti; #endif do { - nonblocking = !kvm_enabled() && !xen_enabled() && last_io > 0; + nonblocking = tcg_enabled() && last_io > 0; #ifdef CONFIG_PROFILER ti = profile_getclock(); #endif @@ -3699,7 +3659,7 @@ int main(int argc, char **argv, char **envp) if (!opts) { exit(1); } - do_acpitable_option(opts); + acpi_table_add(opts, &error_fatal); break; case QEMU_OPTION_smbios: opts = qemu_opts_parse_noisily(qemu_find_opts("smbios"), @@ -3707,7 +3667,7 @@ int main(int argc, char **argv, char **envp) if (!opts) { exit(1); } - do_smbios_option(opts); + smbios_entry_add(opts, &error_fatal); break; case QEMU_OPTION_fwcfg: opts = qemu_opts_parse_noisily(qemu_find_opts("fw_cfg"), @@ -3720,6 +3680,10 @@ int main(int argc, char **argv, char **envp) olist = qemu_find_opts("machine"); qemu_opts_parse_noisily(olist, "accel=kvm", false); break; + case QEMU_OPTION_enable_hax: + olist = qemu_find_opts("machine"); + qemu_opts_parse_noisily(olist, "accel=hax", false); + break; case QEMU_OPTION_M: case QEMU_OPTION_machine: olist = qemu_find_opts("machine"); @@ -4414,8 +4378,8 @@ int main(int argc, char **argv, char **envp) cpu_ticks_init(); if (icount_opts) { - if (kvm_enabled() || xen_enabled()) { - error_report("-icount is not allowed with kvm or xen"); + if (!tcg_enabled()) { + error_report("-icount is not allowed with hardware virtualization"); exit(1); } configure_icount(icount_opts, &error_abort); @@ -4551,6 +4515,10 @@ int main(int argc, char **argv, char **envp) numa_post_machine_init(); + if (hax_enabled()) { + hax_sync_vcpus(); + } + if (qemu_opts_foreach(qemu_find_opts("fw_cfg"), parse_fw_cfg, fw_cfg_find(), NULL) != 0) { exit(1); diff --git a/xen-mapcache.c b/xen-mapcache.c index 8f3a592013..31debdfb2c 100644 --- a/xen-mapcache.c +++ b/xen-mapcache.c @@ -163,6 +163,7 @@ static void xen_remap_bucket(MapCacheEntry *entry, err = g_malloc0(nb_pfn * sizeof (int)); if (entry->vaddr_base != NULL) { + ram_block_notify_remove(entry->vaddr_base, entry->size); if (munmap(entry->vaddr_base, entry->size) != 0) { perror("unmap fails"); exit(-1); @@ -188,6 +189,7 @@ static void xen_remap_bucket(MapCacheEntry *entry, entry->valid_mapping = (unsigned long *) g_malloc0(sizeof(unsigned long) * BITS_TO_LONGS(size >> XC_PAGE_SHIFT)); + ram_block_notify_add(entry->vaddr_base, entry->size); bitmap_zero(entry->valid_mapping, nb_pfn); for (i = 0; i < nb_pfn; i++) { if (!err[i]) { @@ -397,6 +399,7 @@ static void xen_invalidate_map_cache_entry_unlocked(uint8_t *buffer) } pentry->next = entry->next; + ram_block_notify_remove(entry->vaddr_base, entry->size); if (munmap(entry->vaddr_base, entry->size) != 0) { perror("unmap fails"); exit(-1); |