diff options
| -rw-r--r-- | docs/system/arm/xenpvh.rst | 34 | ||||
| -rw-r--r-- | docs/system/target-arm.rst | 1 | ||||
| -rw-r--r-- | hw/arm/meson.build | 2 | ||||
| -rw-r--r-- | hw/arm/xen_arm.c | 181 | ||||
| -rw-r--r-- | hw/i386/meson.build | 1 | ||||
| -rw-r--r-- | hw/i386/xen/meson.build | 1 | ||||
| -rw-r--r-- | hw/i386/xen/trace-events | 19 | ||||
| -rw-r--r-- | hw/i386/xen/xen-hvm.c | 1075 | ||||
| -rw-r--r-- | hw/xen/meson.build | 7 | ||||
| -rw-r--r-- | hw/xen/trace-events | 19 | ||||
| -rw-r--r-- | hw/xen/xen-hvm-common.c | 879 | ||||
| -rw-r--r-- | hw/xen/xen-mapcache.c (renamed from hw/i386/xen/xen-mapcache.c) | 0 | ||||
| -rw-r--r-- | include/hw/arm/xen_arch_hvm.h | 9 | ||||
| -rw-r--r-- | include/hw/i386/xen_arch_hvm.h | 11 | ||||
| -rw-r--r-- | include/hw/xen/arch_hvm.h | 5 | ||||
| -rw-r--r-- | include/hw/xen/xen-hvm-common.h | 99 | ||||
| -rw-r--r-- | include/hw/xen/xen_native.h | 8 | ||||
| -rw-r--r-- | meson.build | 4 | ||||
| -rw-r--r-- | tests/qtest/libqtest.c | 3 |
19 files changed, 1349 insertions, 1009 deletions
diff --git a/docs/system/arm/xenpvh.rst b/docs/system/arm/xenpvh.rst new file mode 100644 index 0000000..e1655c7 --- /dev/null +++ b/docs/system/arm/xenpvh.rst @@ -0,0 +1,34 @@ +XENPVH (``xenpvh``) +========================================= +This machine creates a IOREQ server to register/connect with Xen Hypervisor. + +When TPM is enabled, this machine also creates a tpm-tis-device at a user input +tpm base address, adds a TPM emulator and connects to a swtpm application +running on host machine via chardev socket. This enables xenpvh to support TPM +functionalities for a guest domain. + +More information about TPM use and installing swtpm linux application can be +found at: docs/specs/tpm.rst. + +Example for starting swtpm on host machine: +.. code-block:: console + + mkdir /tmp/vtpm2 + swtpm socket --tpmstate dir=/tmp/vtpm2 \ + --ctrl type=unixio,path=/tmp/vtpm2/swtpm-sock & + +Sample QEMU xenpvh commands for running and connecting with Xen: +.. code-block:: console + + qemu-system-aarch64 -xen-domid 1 \ + -chardev socket,id=libxl-cmd,path=qmp-libxl-1,server=on,wait=off \ + -mon chardev=libxl-cmd,mode=control \ + -chardev socket,id=libxenstat-cmd,path=qmp-libxenstat-1,server=on,wait=off \ + -mon chardev=libxenstat-cmd,mode=control \ + -xen-attach -name guest0 -vnc none -display none -nographic \ + -machine xenpvh -m 1301 \ + -chardev socket,id=chrtpm,path=tmp/vtpm2/swtpm-sock \ + -tpmdev emulator,id=tpm0,chardev=chrtpm -machine tpm-base-addr=0x0C000000 + +In above QEMU command, last two lines are for connecting xenpvh QEMU to swtpm +via chardev socket. diff --git a/docs/system/target-arm.rst b/docs/system/target-arm.rst index a12b6bc..790ac1b 100644 --- a/docs/system/target-arm.rst +++ b/docs/system/target-arm.rst @@ -107,6 +107,7 @@ undocumented; you can get a complete list by running arm/stm32 arm/virt arm/xlnx-versal-virt + arm/xenpvh Emulated CPU architecture support ================================= diff --git a/hw/arm/meson.build b/hw/arm/meson.build index 870ec67..4f94f82 100644 --- a/hw/arm/meson.build +++ b/hw/arm/meson.build @@ -63,6 +63,8 @@ arm_ss.add(when: 'CONFIG_FSL_IMX7', if_true: files('fsl-imx7.c', 'mcimx7d-sabre. arm_ss.add(when: 'CONFIG_ARM_SMMUV3', if_true: files('smmuv3.c')) arm_ss.add(when: 'CONFIG_FSL_IMX6UL', if_true: files('fsl-imx6ul.c', 'mcimx6ul-evk.c')) arm_ss.add(when: 'CONFIG_NRF51_SOC', if_true: files('nrf51_soc.c')) +arm_ss.add(when: 'CONFIG_XEN', if_true: files('xen_arm.c')) +arm_ss.add_all(xen_ss) softmmu_ss.add(when: 'CONFIG_ARM_SMMUV3', if_true: files('smmu-common.c')) softmmu_ss.add(when: 'CONFIG_EXYNOS4', if_true: files('exynos4_boards.c')) diff --git a/hw/arm/xen_arm.c b/hw/arm/xen_arm.c new file mode 100644 index 0000000..19b1cb8 --- /dev/null +++ b/hw/arm/xen_arm.c @@ -0,0 +1,181 @@ +/* + * QEMU ARM Xen PVH Machine + * + * + * 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/error-report.h" +#include "qapi/qapi-commands-migration.h" +#include "qapi/visitor.h" +#include "hw/boards.h" +#include "hw/sysbus.h" +#include "sysemu/block-backend.h" +#include "sysemu/tpm_backend.h" +#include "sysemu/sysemu.h" +#include "hw/xen/xen-hvm-common.h" +#include "sysemu/tpm.h" +#include "hw/xen/arch_hvm.h" + +#define TYPE_XEN_ARM MACHINE_TYPE_NAME("xenpvh") +OBJECT_DECLARE_SIMPLE_TYPE(XenArmState, XEN_ARM) + +static MemoryListener xen_memory_listener = { + .region_add = xen_region_add, + .region_del = xen_region_del, + .log_start = NULL, + .log_stop = NULL, + .log_sync = NULL, + .log_global_start = NULL, + .log_global_stop = NULL, + .priority = 10, +}; + +struct XenArmState { + /*< private >*/ + MachineState parent; + + XenIOState *state; + + struct { + uint64_t tpm_base_addr; + } cfg; +}; + +void arch_handle_ioreq(XenIOState *state, ioreq_t *req) +{ + hw_error("Invalid ioreq type 0x%x\n", req->type); + + return; +} + +void arch_xen_set_memory(XenIOState *state, MemoryRegionSection *section, + bool add) +{ +} + +void xen_hvm_modified_memory(ram_addr_t start, ram_addr_t length) +{ +} + +void qmp_xen_set_global_dirty_log(bool enable, Error **errp) +{ +} + +#ifdef CONFIG_TPM +static void xen_enable_tpm(XenArmState *xam) +{ + Error *errp = NULL; + DeviceState *dev; + SysBusDevice *busdev; + + TPMBackend *be = qemu_find_tpm_be("tpm0"); + if (be == NULL) { + DPRINTF("Couldn't fine the backend for tpm0\n"); + return; + } + dev = qdev_new(TYPE_TPM_TIS_SYSBUS); + object_property_set_link(OBJECT(dev), "tpmdev", OBJECT(be), &errp); + object_property_set_str(OBJECT(dev), "tpmdev", be->id, &errp); + busdev = SYS_BUS_DEVICE(dev); + sysbus_realize_and_unref(busdev, &error_fatal); + sysbus_mmio_map(busdev, 0, xam->cfg.tpm_base_addr); + + DPRINTF("Connected tpmdev at address 0x%lx\n", xam->cfg.tpm_base_addr); +} +#endif + +static void xen_arm_init(MachineState *machine) +{ + XenArmState *xam = XEN_ARM(machine); + + xam->state = g_new0(XenIOState, 1); + + xen_register_ioreq(xam->state, machine->smp.cpus, xen_memory_listener); + +#ifdef CONFIG_TPM + if (xam->cfg.tpm_base_addr) { + xen_enable_tpm(xam); + } else { + DPRINTF("tpm-base-addr is not provided. TPM will not be enabled\n"); + } +#endif +} + +#ifdef CONFIG_TPM +static void xen_arm_get_tpm_base_addr(Object *obj, Visitor *v, + const char *name, void *opaque, + Error **errp) +{ + XenArmState *xam = XEN_ARM(obj); + uint64_t value = xam->cfg.tpm_base_addr; + + visit_type_uint64(v, name, &value, errp); +} + +static void xen_arm_set_tpm_base_addr(Object *obj, Visitor *v, + const char *name, void *opaque, + Error **errp) +{ + XenArmState *xam = XEN_ARM(obj); + uint64_t value; + + if (!visit_type_uint64(v, name, &value, errp)) { + return; + } + + xam->cfg.tpm_base_addr = value; +} +#endif + +static void xen_arm_machine_class_init(ObjectClass *oc, void *data) +{ + + MachineClass *mc = MACHINE_CLASS(oc); + mc->desc = "Xen Para-virtualized PC"; + mc->init = xen_arm_init; + mc->max_cpus = 1; + mc->default_machine_opts = "accel=xen"; + +#ifdef CONFIG_TPM + object_class_property_add(oc, "tpm-base-addr", "uint64_t", + xen_arm_get_tpm_base_addr, + xen_arm_set_tpm_base_addr, + NULL, NULL); + object_class_property_set_description(oc, "tpm-base-addr", + "Set Base address for TPM device."); + + machine_class_allow_dynamic_sysbus_dev(mc, TYPE_TPM_TIS_SYSBUS); +#endif +} + +static const TypeInfo xen_arm_machine_type = { + .name = TYPE_XEN_ARM, + .parent = TYPE_MACHINE, + .class_init = xen_arm_machine_class_init, + .instance_size = sizeof(XenArmState), +}; + +static void xen_arm_machine_register_types(void) +{ + type_register_static(&xen_arm_machine_type); +} + +type_init(xen_arm_machine_register_types) diff --git a/hw/i386/meson.build b/hw/i386/meson.build index 213e2e8..cfdbfdc 100644 --- a/hw/i386/meson.build +++ b/hw/i386/meson.build @@ -33,5 +33,6 @@ subdir('kvm') subdir('xen') i386_ss.add_all(xenpv_ss) +i386_ss.add_all(xen_ss) hw_arch += {'i386': i386_ss} diff --git a/hw/i386/xen/meson.build b/hw/i386/xen/meson.build index 2e64a34..3dc4c4f 100644 --- a/hw/i386/xen/meson.build +++ b/hw/i386/xen/meson.build @@ -1,6 +1,5 @@ i386_ss.add(when: 'CONFIG_XEN', if_true: files( 'xen-hvm.c', - 'xen-mapcache.c', 'xen_apic.c', 'xen_pvdevice.c', )) diff --git a/hw/i386/xen/trace-events b/hw/i386/xen/trace-events index 5d6be61..5d0a8d6 100644 --- a/hw/i386/xen/trace-events +++ b/hw/i386/xen/trace-events @@ -7,22 +7,3 @@ xen_platform_log(char *s) "xen platform: %s" xen_pv_mmio_read(uint64_t addr) "WARNING: read from Xen PV Device MMIO space (address 0x%"PRIx64")" xen_pv_mmio_write(uint64_t addr) "WARNING: write to Xen PV Device MMIO space (address 0x%"PRIx64")" -# xen-hvm.c -xen_ram_alloc(unsigned long ram_addr, unsigned long size) "requested: 0x%lx, size 0x%lx" -xen_client_set_memory(uint64_t start_addr, unsigned long size, bool log_dirty) "0x%"PRIx64" size 0x%lx, log_dirty %i" -handle_ioreq(void *req, uint32_t type, uint32_t dir, uint32_t df, uint32_t data_is_ptr, uint64_t addr, uint64_t data, uint32_t count, uint32_t size) "I/O=%p type=%d dir=%d df=%d ptr=%d port=0x%"PRIx64" data=0x%"PRIx64" count=%d size=%d" -handle_ioreq_read(void *req, uint32_t type, uint32_t df, uint32_t data_is_ptr, uint64_t addr, uint64_t data, uint32_t count, uint32_t size) "I/O=%p read type=%d df=%d ptr=%d port=0x%"PRIx64" data=0x%"PRIx64" count=%d size=%d" -handle_ioreq_write(void *req, uint32_t type, uint32_t df, uint32_t data_is_ptr, uint64_t addr, uint64_t data, uint32_t count, uint32_t size) "I/O=%p write type=%d df=%d ptr=%d port=0x%"PRIx64" data=0x%"PRIx64" count=%d size=%d" -cpu_ioreq_pio(void *req, uint32_t dir, uint32_t df, uint32_t data_is_ptr, uint64_t addr, uint64_t data, uint32_t count, uint32_t size) "I/O=%p pio dir=%d df=%d ptr=%d port=0x%"PRIx64" data=0x%"PRIx64" count=%d size=%d" -cpu_ioreq_pio_read_reg(void *req, uint64_t data, uint64_t addr, uint32_t size) "I/O=%p pio read reg data=0x%"PRIx64" port=0x%"PRIx64" size=%d" -cpu_ioreq_pio_write_reg(void *req, uint64_t data, uint64_t addr, uint32_t size) "I/O=%p pio write reg data=0x%"PRIx64" port=0x%"PRIx64" size=%d" -cpu_ioreq_move(void *req, uint32_t dir, uint32_t df, uint32_t data_is_ptr, uint64_t addr, uint64_t data, uint32_t count, uint32_t size) "I/O=%p copy dir=%d df=%d ptr=%d port=0x%"PRIx64" data=0x%"PRIx64" count=%d size=%d" -xen_map_resource_ioreq(uint32_t id, void *addr) "id: %u addr: %p" -cpu_ioreq_config_read(void *req, uint32_t sbdf, uint32_t reg, uint32_t size, uint32_t data) "I/O=%p sbdf=0x%x reg=%u size=%u data=0x%x" -cpu_ioreq_config_write(void *req, uint32_t sbdf, uint32_t reg, uint32_t size, uint32_t data) "I/O=%p sbdf=0x%x reg=%u size=%u data=0x%x" - -# xen-mapcache.c -xen_map_cache(uint64_t phys_addr) "want 0x%"PRIx64 -xen_remap_bucket(uint64_t index) "index 0x%"PRIx64 -xen_map_cache_return(void* ptr) "%p" - diff --git a/hw/i386/xen/xen-hvm.c b/hw/i386/xen/xen-hvm.c index ab8f1b6..5dc5e80 100644 --- a/hw/i386/xen/xen-hvm.c +++ b/hw/i386/xen/xen-hvm.c @@ -10,43 +10,21 @@ #include "qemu/osdep.h" #include "qemu/units.h" +#include "qapi/error.h" +#include "qapi/qapi-commands-migration.h" +#include "trace.h" -#include "cpu.h" -#include "hw/pci/pci.h" -#include "hw/pci/pci_host.h" #include "hw/i386/pc.h" #include "hw/irq.h" -#include "hw/hw.h" #include "hw/i386/apic-msidef.h" -#include "hw/xen/xen_native.h" -#include "hw/xen/xen-legacy-backend.h" -#include "hw/xen/xen-bus.h" #include "hw/xen/xen-x86.h" -#include "qapi/error.h" -#include "qapi/qapi-commands-migration.h" -#include "qemu/error-report.h" -#include "qemu/main-loop.h" #include "qemu/range.h" -#include "sysemu/runstate.h" -#include "sysemu/sysemu.h" -#include "sysemu/xen.h" -#include "sysemu/xen-mapcache.h" -#include "trace.h" -#include <xen/hvm/ioreq.h> +#include "hw/xen/xen-hvm-common.h" +#include "hw/xen/arch_hvm.h" #include <xen/hvm/e820.h> -//#define DEBUG_XEN_HVM - -#ifdef DEBUG_XEN_HVM -#define DPRINTF(fmt, ...) \ - do { fprintf(stderr, "xen: " fmt, ## __VA_ARGS__); } while (0) -#else -#define DPRINTF(fmt, ...) \ - do { } while (0) -#endif - -static MemoryRegion ram_memory, ram_640k, ram_lo, ram_hi; +static MemoryRegion ram_640k, ram_lo, ram_hi; static MemoryRegion *framebuffer; static bool xen_in_migration; @@ -75,66 +53,14 @@ struct shared_vmport_iopage { typedef struct shared_vmport_iopage shared_vmport_iopage_t; #endif -static inline uint32_t xen_vcpu_eport(shared_iopage_t *shared_page, int i) -{ - return shared_page->vcpu_ioreq[i].vp_eport; -} -static inline ioreq_t *xen_vcpu_ioreq(shared_iopage_t *shared_page, int vcpu) -{ - return &shared_page->vcpu_ioreq[vcpu]; -} - -#define BUFFER_IO_MAX_DELAY 100 - -typedef struct XenPhysmap { - hwaddr start_addr; - ram_addr_t size; - const char *name; - hwaddr phys_offset; - - QLIST_ENTRY(XenPhysmap) list; -} XenPhysmap; +static shared_vmport_iopage_t *shared_vmport_page; static QLIST_HEAD(, XenPhysmap) xen_physmap; - -typedef struct XenPciDevice { - PCIDevice *pci_dev; - uint32_t sbdf; - QLIST_ENTRY(XenPciDevice) entry; -} XenPciDevice; - -typedef struct XenIOState { - ioservid_t ioservid; - shared_iopage_t *shared_page; - shared_vmport_iopage_t *shared_vmport_page; - buffered_iopage_t *buffered_io_page; - xenforeignmemory_resource_handle *fres; - QEMUTimer *buffered_io_timer; - CPUState **cpu_by_vcpu_id; - /* the evtchn port for polling the notification, */ - evtchn_port_t *ioreq_local_port; - /* evtchn remote and local ports for buffered io */ - evtchn_port_t bufioreq_remote_port; - evtchn_port_t bufioreq_local_port; - /* the evtchn fd for polling */ - xenevtchn_handle *xce_handle; - /* which vcpu we are serving */ - int send_vcpu; - - struct xs_handle *xenstore; - MemoryListener memory_listener; - MemoryListener io_listener; - QLIST_HEAD(, XenPciDevice) dev_list; - DeviceListener device_listener; - hwaddr free_phys_offset; - const XenPhysmap *log_for_dirtybit; - /* Buffer used by xen_sync_dirty_bitmap */ - unsigned long *dirty_bitmap; - - Notifier exit; - Notifier suspend; - Notifier wakeup; -} XenIOState; +static const XenPhysmap *log_for_dirtybit; +/* Buffer used by xen_sync_dirty_bitmap */ +static unsigned long *dirty_bitmap; +static Notifier suspend; +static Notifier wakeup; /* Xen specific function for piix pci */ @@ -248,42 +174,6 @@ static void xen_ram_init(PCMachineState *pcms, } } -void xen_ram_alloc(ram_addr_t ram_addr, ram_addr_t size, MemoryRegion *mr, - Error **errp) -{ - unsigned long nr_pfn; - xen_pfn_t *pfn_list; - int i; - - if (runstate_check(RUN_STATE_INMIGRATE)) { - /* RAM already populated in Xen */ - fprintf(stderr, "%s: do not alloc "RAM_ADDR_FMT - " bytes of ram at "RAM_ADDR_FMT" when runstate is INMIGRATE\n", - __func__, size, ram_addr); - return; - } - - if (mr == &ram_memory) { - return; - } - - trace_xen_ram_alloc(ram_addr, size); - - nr_pfn = size >> TARGET_PAGE_BITS; - pfn_list = g_malloc(sizeof (*pfn_list) * nr_pfn); - - for (i = 0; i < nr_pfn; i++) { - pfn_list[i] = (ram_addr >> TARGET_PAGE_BITS) + i; - } - - if (xc_domain_populate_physmap_exact(xen_xc, xen_domid, nr_pfn, 0, 0, pfn_list)) { - error_setg(errp, "xen: failed to populate ram at " RAM_ADDR_FMT, - ram_addr); - } - - g_free(pfn_list); -} - static XenPhysmap *get_physmapping(hwaddr start_addr, ram_addr_t size) { XenPhysmap *physmap = NULL; @@ -463,154 +353,16 @@ static int xen_remove_from_physmap(XenIOState *state, } QLIST_REMOVE(physmap, list); - if (state->log_for_dirtybit == physmap) { - state->log_for_dirtybit = NULL; - g_free(state->dirty_bitmap); - state->dirty_bitmap = NULL; + if (log_for_dirtybit == physmap) { + log_for_dirtybit = NULL; + g_free(dirty_bitmap); + dirty_bitmap = NULL; } g_free(physmap); return 0; } -static void xen_set_memory(struct MemoryListener *listener, - MemoryRegionSection *section, - bool add) -{ - XenIOState *state = container_of(listener, XenIOState, memory_listener); - hwaddr start_addr = section->offset_within_address_space; - ram_addr_t size = int128_get64(section->size); - bool log_dirty = memory_region_is_logging(section->mr, DIRTY_MEMORY_VGA); - hvmmem_type_t mem_type; - - if (section->mr == &ram_memory) { - return; - } else { - if (add) { - xen_map_memory_section(xen_domid, state->ioservid, - section); - } else { - xen_unmap_memory_section(xen_domid, state->ioservid, - section); - } - } - - if (!memory_region_is_ram(section->mr)) { - return; - } - - if (log_dirty != add) { - return; - } - - trace_xen_client_set_memory(start_addr, size, log_dirty); - - start_addr &= TARGET_PAGE_MASK; - size = TARGET_PAGE_ALIGN(size); - - if (add) { - if (!memory_region_is_rom(section->mr)) { - xen_add_to_physmap(state, start_addr, size, - section->mr, section->offset_within_region); - } else { - mem_type = HVMMEM_ram_ro; - if (xen_set_mem_type(xen_domid, mem_type, - start_addr >> TARGET_PAGE_BITS, - size >> TARGET_PAGE_BITS)) { - DPRINTF("xen_set_mem_type error, addr: "HWADDR_FMT_plx"\n", - start_addr); - } - } - } else { - if (xen_remove_from_physmap(state, start_addr, size) < 0) { - DPRINTF("physmapping does not exist at "HWADDR_FMT_plx"\n", start_addr); - } - } -} - -static void xen_region_add(MemoryListener *listener, - MemoryRegionSection *section) -{ - memory_region_ref(section->mr); - xen_set_memory(listener, section, true); -} - -static void xen_region_del(MemoryListener *listener, - MemoryRegionSection *section) -{ - xen_set_memory(listener, section, false); - memory_region_unref(section->mr); -} - -static void xen_io_add(MemoryListener *listener, - MemoryRegionSection *section) -{ - XenIOState *state = container_of(listener, XenIOState, io_listener); - MemoryRegion *mr = section->mr; - - if (mr->ops == &unassigned_io_ops) { - return; - } - - memory_region_ref(mr); - - xen_map_io_section(xen_domid, state->ioservid, section); -} - -static void xen_io_del(MemoryListener *listener, - MemoryRegionSection *section) -{ - XenIOState *state = container_of(listener, XenIOState, io_listener); - MemoryRegion *mr = section->mr; - - if (mr->ops == &unassigned_io_ops) { - return; - } - - xen_unmap_io_section(xen_domid, state->ioservid, section); - - memory_region_unref(mr); -} - -static void xen_device_realize(DeviceListener *listener, - DeviceState *dev) -{ - XenIOState *state = container_of(listener, XenIOState, device_listener); - - if (object_dynamic_cast(OBJECT(dev), TYPE_PCI_DEVICE)) { - PCIDevice *pci_dev = PCI_DEVICE(dev); - XenPciDevice *xendev = g_new(XenPciDevice, 1); - - xendev->pci_dev = pci_dev; - xendev->sbdf = PCI_BUILD_BDF(pci_dev_bus_num(pci_dev), - pci_dev->devfn); - QLIST_INSERT_HEAD(&state->dev_list, xendev, entry); - - xen_map_pcidev(xen_domid, state->ioservid, pci_dev); - } -} - -static void xen_device_unrealize(DeviceListener *listener, - DeviceState *dev) -{ - XenIOState *state = container_of(listener, XenIOState, device_listener); - - if (object_dynamic_cast(OBJECT(dev), TYPE_PCI_DEVICE)) { - PCIDevice *pci_dev = PCI_DEVICE(dev); - XenPciDevice *xendev, *next; - - xen_unmap_pcidev(xen_domid, state->ioservid, pci_dev); - - QLIST_FOREACH_SAFE(xendev, &state->dev_list, entry, next) { - if (xendev->pci_dev == pci_dev) { - QLIST_REMOVE(xendev, entry); - g_free(xendev); - break; - } - } - } -} - static void xen_sync_dirty_bitmap(XenIOState *state, hwaddr start_addr, ram_addr_t size) @@ -627,16 +379,16 @@ static void xen_sync_dirty_bitmap(XenIOState *state, return; } - if (state->log_for_dirtybit == NULL) { - state->log_for_dirtybit = physmap; - state->dirty_bitmap = g_new(unsigned long, bitmap_size); - } else if (state->log_for_dirtybit != physmap) { + if (log_for_dirtybit == NULL) { + log_for_dirtybit = physmap; + dirty_bitmap = g_new(unsigned long, bitmap_size); + } else if (log_for_dirtybit != physmap) { /* Only one range for dirty bitmap can be tracked. */ return; } rc = xen_track_dirty_vram(xen_domid, start_addr >> TARGET_PAGE_BITS, - npages, state->dirty_bitmap); + npages, dirty_bitmap); if (rc < 0) { #ifndef ENODATA #define ENODATA ENOENT @@ -651,7 +403,7 @@ static void xen_sync_dirty_bitmap(XenIOState *state, } for (i = 0; i < bitmap_size; i++) { - unsigned long map = state->dirty_bitmap[i]; + unsigned long map = dirty_bitmap[i]; while (map != 0) { j = ctzl(map); map &= ~(1ul << j); @@ -677,12 +429,10 @@ static void xen_log_start(MemoryListener *listener, static void xen_log_stop(MemoryListener *listener, MemoryRegionSection *section, int old, int new) { - XenIOState *state = container_of(listener, XenIOState, memory_listener); - if (old & ~new & (1 << DIRTY_MEMORY_VGA)) { - state->log_for_dirtybit = NULL; - g_free(state->dirty_bitmap); - state->dirty_bitmap = NULL; + log_for_dirtybit = NULL; + g_free(dirty_bitmap); + dirty_bitmap = NULL; /* Disable dirty bit tracking */ xen_track_dirty_vram(xen_domid, 0, 0, NULL); } @@ -720,277 +470,6 @@ static MemoryListener xen_memory_listener = { .priority = 10, }; -static MemoryListener xen_io_listener = { - .name = "xen-io", - .region_add = xen_io_add, - .region_del = xen_io_del, - .priority = 10, -}; - -static DeviceListener xen_device_listener = { - .realize = xen_device_realize, - .unrealize = xen_device_unrealize, -}; - -/* get the ioreq packets from share mem */ -static ioreq_t *cpu_get_ioreq_from_shared_memory(XenIOState *state, int vcpu) -{ - ioreq_t *req = xen_vcpu_ioreq(state->shared_page, vcpu); - - if (req->state != STATE_IOREQ_READY) { - DPRINTF("I/O request not ready: " - "%x, ptr: %x, port: %"PRIx64", " - "data: %"PRIx64", count: %u, size: %u\n", - req->state, req->data_is_ptr, req->addr, - req->data, req->count, req->size); - return NULL; - } - - xen_rmb(); /* see IOREQ_READY /then/ read contents of ioreq */ - - req->state = STATE_IOREQ_INPROCESS; - return req; -} - -/* use poll to get the port notification */ -/* ioreq_vec--out,the */ -/* retval--the number of ioreq packet */ -static ioreq_t *cpu_get_ioreq(XenIOState *state) -{ - MachineState *ms = MACHINE(qdev_get_machine()); - unsigned int max_cpus = ms->smp.max_cpus; - int i; - evtchn_port_t port; - - port = qemu_xen_evtchn_pending(state->xce_handle); - if (port == state->bufioreq_local_port) { - timer_mod(state->buffered_io_timer, - BUFFER_IO_MAX_DELAY + qemu_clock_get_ms(QEMU_CLOCK_REALTIME)); - return NULL; - } - - if (port != -1) { - for (i = 0; i < max_cpus; i++) { - if (state->ioreq_local_port[i] == port) { - break; - } - } - - if (i == max_cpus) { - hw_error("Fatal error while trying to get io event!\n"); - } - - /* unmask the wanted port again */ - qemu_xen_evtchn_unmask(state->xce_handle, port); - - /* get the io packet from shared memory */ - state->send_vcpu = i; - return cpu_get_ioreq_from_shared_memory(state, i); - } - - /* read error or read nothing */ - return NULL; -} - -static uint32_t do_inp(uint32_t addr, unsigned long size) -{ - switch (size) { - case 1: - return cpu_inb(addr); - case 2: - return cpu_inw(addr); - case 4: - return cpu_inl(addr); - default: - hw_error("inp: bad size: %04x %lx", addr, size); - } -} - -static void do_outp(uint32_t addr, - unsigned long size, uint32_t val) -{ - switch (size) { - case 1: - return cpu_outb(addr, val); - case 2: - return cpu_outw(addr, val); - case 4: - return cpu_outl(addr, val); - default: - hw_error("outp: bad size: %04x %lx", addr, size); - } -} - -/* - * Helper functions which read/write an object from/to physical guest - * memory, as part of the implementation of an ioreq. - * - * Equivalent to - * cpu_physical_memory_rw(addr + (req->df ? -1 : +1) * req->size * i, - * val, req->size, 0/1) - * except without the integer overflow problems. - */ -static void rw_phys_req_item(hwaddr addr, - ioreq_t *req, uint32_t i, void *val, int rw) -{ - /* Do everything unsigned so overflow just results in a truncated result - * and accesses to undesired parts of guest memory, which is up - * to the guest */ - hwaddr offset = (hwaddr)req->size * i; - if (req->df) { - addr -= offset; - } else { - addr += offset; - } - cpu_physical_memory_rw(addr, val, req->size, rw); -} - -static inline void read_phys_req_item(hwaddr addr, - ioreq_t *req, uint32_t i, void *val) -{ - rw_phys_req_item(addr, req, i, val, 0); -} -static inline void write_phys_req_item(hwaddr addr, - ioreq_t *req, uint32_t i, void *val) -{ - rw_phys_req_item(addr, req, i, val, 1); -} - - -static void cpu_ioreq_pio(ioreq_t *req) -{ - uint32_t i; - - trace_cpu_ioreq_pio(req, req->dir, req->df, req->data_is_ptr, req->addr, - req->data, req->count, req->size); - - if (req->size > sizeof(uint32_t)) { - hw_error("PIO: bad size (%u)", req->size); - } - - if (req->dir == IOREQ_READ) { - if (!req->data_is_ptr) { - req->data = do_inp(req->addr, req->size); - trace_cpu_ioreq_pio_read_reg(req, req->data, req->addr, - req->size); - } else { - uint32_t tmp; - - for (i = 0; i < req->count; i++) { - tmp = do_inp(req->addr, req->size); - write_phys_req_item(req->data, req, i, &tmp); - } - } - } else if (req->dir == IOREQ_WRITE) { - if (!req->data_is_ptr) { - trace_cpu_ioreq_pio_write_reg(req, req->data, req->addr, - req->size); - do_outp(req->addr, req->size, req->data); - } else { - for (i = 0; i < req->count; i++) { - uint32_t tmp = 0; - - read_phys_req_item(req->data, req, i, &tmp); - do_outp(req->addr, req->size, tmp); - } - } - } -} - -static void cpu_ioreq_move(ioreq_t *req) -{ - uint32_t i; - - trace_cpu_ioreq_move(req, req->dir, req->df, req->data_is_ptr, req->addr, - req->data, req->count, req->size); - - if (req->size > sizeof(req->data)) { - hw_error("MMIO: bad size (%u)", req->size); - } - - if (!req->data_is_ptr) { - if (req->dir == IOREQ_READ) { - for (i = 0; i < req->count; i++) { - read_phys_req_item(req->addr, req, i, &req->data); - } - } else if (req->dir == IOREQ_WRITE) { - for (i = 0; i < req->count; i++) { - write_phys_req_item(req->addr, req, i, &req->data); - } - } - } else { - uint64_t tmp; - - if (req->dir == IOREQ_READ) { - for (i = 0; i < req->count; i++) { - read_phys_req_item(req->addr, req, i, &tmp); - write_phys_req_item(req->data, req, i, &tmp); - } - } else if (req->dir == IOREQ_WRITE) { - for (i = 0; i < req->count; i++) { - read_phys_req_item(req->data, req, i, &tmp); - write_phys_req_item(req->addr, req, i, &tmp); - } - } - } -} - -static void cpu_ioreq_config(XenIOState *state, ioreq_t *req) -{ - uint32_t sbdf = req->addr >> 32; - uint32_t reg = req->addr; - XenPciDevice *xendev; - - if (req->size != sizeof(uint8_t) && req->size != sizeof(uint16_t) && - req->size != sizeof(uint32_t)) { - hw_error("PCI config access: bad size (%u)", req->size); - } - - if (req->count != 1) { - hw_error("PCI config access: bad count (%u)", req->count); - } - - QLIST_FOREACH(xendev, &state->dev_list, entry) { - if (xendev->sbdf != sbdf) { - continue; - } - - if (!req->data_is_ptr) { - if (req->dir == IOREQ_READ) { - req->data = pci_host_config_read_common( - xendev->pci_dev, reg, PCI_CONFIG_SPACE_SIZE, - req->size); - trace_cpu_ioreq_config_read(req, xendev->sbdf, reg, - req->size, req->data); - } else if (req->dir == IOREQ_WRITE) { - trace_cpu_ioreq_config_write(req, xendev->sbdf, reg, - req->size, req->data); - pci_host_config_write_common( - xendev->pci_dev, reg, PCI_CONFIG_SPACE_SIZE, - req->data, req->size); - } - } else { - uint32_t tmp; - - if (req->dir == IOREQ_READ) { - tmp = pci_host_config_read_common( - xendev->pci_dev, reg, PCI_CONFIG_SPACE_SIZE, - req->size); - trace_cpu_ioreq_config_read(req, xendev->sbdf, reg, - req->size, tmp); - write_phys_req_item(req->data, req, 0, &tmp); - } else if (req->dir == IOREQ_WRITE) { - read_phys_req_item(req->data, req, 0, &tmp); - trace_cpu_ioreq_config_write(req, xendev->sbdf, reg, - req->size, tmp); - pci_host_config_write_common( - xendev->pci_dev, reg, PCI_CONFIG_SPACE_SIZE, - tmp, req->size); - } - } - } -} - static void regs_to_cpu(vmware_regs_t *vmport_regs, ioreq_t *req) { X86CPU *cpu; @@ -1022,9 +501,9 @@ static void handle_vmport_ioreq(XenIOState *state, ioreq_t *req) { vmware_regs_t *vmport_regs; - assert(state->shared_vmport_page); + assert(shared_vmport_page); vmport_regs = - &state->shared_vmport_page->vcpu_vmport_regs[state->send_vcpu]; + &shared_vmport_page->vcpu_vmport_regs[state->send_vcpu]; QEMU_BUILD_BUG_ON(sizeof(*req) < sizeof(*vmport_regs)); current_cpu = state->cpu_by_vcpu_id[state->send_vcpu]; @@ -1034,226 +513,6 @@ static void handle_vmport_ioreq(XenIOState *state, ioreq_t *req) current_cpu = NULL; } -static void handle_ioreq(XenIOState *state, ioreq_t *req) -{ - trace_handle_ioreq(req, req->type, req->dir, req->df, req->data_is_ptr, - req->addr, req->data, req->count, req->size); - - if (!req->data_is_ptr && (req->dir == IOREQ_WRITE) && - (req->size < sizeof (target_ulong))) { - req->data &= ((target_ulong) 1 << (8 * req->size)) - 1; - } - - if (req->dir == IOREQ_WRITE) - trace_handle_ioreq_write(req, req->type, req->df, req->data_is_ptr, - req->addr, req->data, req->count, req->size); - - switch (req->type) { - case IOREQ_TYPE_PIO: - cpu_ioreq_pio(req); - break; - case IOREQ_TYPE_COPY: - cpu_ioreq_move(req); - break; - case IOREQ_TYPE_VMWARE_PORT: - handle_vmport_ioreq(state, req); - break; - case IOREQ_TYPE_TIMEOFFSET: - break; - case IOREQ_TYPE_INVALIDATE: - xen_invalidate_map_cache(); - break; - case IOREQ_TYPE_PCI_CONFIG: - cpu_ioreq_config(state, req); - break; - default: - hw_error("Invalid ioreq type 0x%x\n", req->type); - } - if (req->dir == IOREQ_READ) { - trace_handle_ioreq_read(req, req->type, req->df, req->data_is_ptr, - req->addr, req->data, req->count, req->size); - } -} - -static bool handle_buffered_iopage(XenIOState *state) -{ - buffered_iopage_t *buf_page = state->buffered_io_page; - buf_ioreq_t *buf_req = NULL; - bool handled_ioreq = false; - ioreq_t req; - int qw; - - if (!buf_page) { - return 0; - } - - memset(&req, 0x00, sizeof(req)); - req.state = STATE_IOREQ_READY; - req.count = 1; - req.dir = IOREQ_WRITE; - - for (;;) { - uint32_t rdptr = buf_page->read_pointer, wrptr; - - xen_rmb(); - wrptr = buf_page->write_pointer; - xen_rmb(); - if (rdptr != buf_page->read_pointer) { - continue; - } - if (rdptr == wrptr) { - break; - } - buf_req = &buf_page->buf_ioreq[rdptr % IOREQ_BUFFER_SLOT_NUM]; - req.size = 1U << buf_req->size; - req.addr = buf_req->addr; - req.data = buf_req->data; - req.type = buf_req->type; - xen_rmb(); - qw = (req.size == 8); - if (qw) { - if (rdptr + 1 == wrptr) { - hw_error("Incomplete quad word buffered ioreq"); - } - buf_req = &buf_page->buf_ioreq[(rdptr + 1) % - IOREQ_BUFFER_SLOT_NUM]; - req.data |= ((uint64_t)buf_req->data) << 32; - xen_rmb(); - } - - handle_ioreq(state, &req); - - /* Only req.data may get updated by handle_ioreq(), albeit even that - * should not happen as such data would never make it to the guest (we - * can only usefully see writes here after all). - */ - assert(req.state == STATE_IOREQ_READY); - assert(req.count == 1); - assert(req.dir == IOREQ_WRITE); - assert(!req.data_is_ptr); - - qatomic_add(&buf_page->read_pointer, qw + 1); - handled_ioreq = true; - } - - return handled_ioreq; -} - -static void handle_buffered_io(void *opaque) -{ - XenIOState *state = opaque; - - if (handle_buffered_iopage(state)) { - timer_mod(state->buffered_io_timer, - BUFFER_IO_MAX_DELAY + qemu_clock_get_ms(QEMU_CLOCK_REALTIME)); - } else { - timer_del(state->buffered_io_timer); - qemu_xen_evtchn_unmask(state->xce_handle, state->bufioreq_local_port); - } -} - -static void cpu_handle_ioreq(void *opaque) -{ - XenIOState *state = opaque; - ioreq_t *req = cpu_get_ioreq(state); - - handle_buffered_iopage(state); - if (req) { - ioreq_t copy = *req; - - xen_rmb(); - handle_ioreq(state, ©); - req->data = copy.data; - - if (req->state != STATE_IOREQ_INPROCESS) { - fprintf(stderr, "Badness in I/O request ... not in service?!: " - "%x, ptr: %x, port: %"PRIx64", " - "data: %"PRIx64", count: %u, size: %u, type: %u\n", - req->state, req->data_is_ptr, req->addr, - req->data, req->count, req->size, req->type); - destroy_hvm_domain(false); - return; - } - - xen_wmb(); /* Update ioreq contents /then/ update state. */ - - /* - * We do this before we send the response so that the tools - * have the opportunity to pick up on the reset before the - * guest resumes and does a hlt with interrupts disabled which - * causes Xen to powerdown the domain. - */ - if (runstate_is_running()) { - ShutdownCause request; - - if (qemu_shutdown_requested_get()) { - destroy_hvm_domain(false); - } - request = qemu_reset_requested_get(); - if (request) { - qemu_system_reset(request); - destroy_hvm_domain(true); - } - } - - req->state = STATE_IORESP_READY; - qemu_xen_evtchn_notify(state->xce_handle, - state->ioreq_local_port[state->send_vcpu]); - } -} - -static void xen_main_loop_prepare(XenIOState *state) -{ - int evtchn_fd = -1; - - if (state->xce_handle != NULL) { - evtchn_fd = qemu_xen_evtchn_fd(state->xce_handle); - } - - state->buffered_io_timer = timer_new_ms(QEMU_CLOCK_REALTIME, handle_buffered_io, - state); - - if (evtchn_fd != -1) { - CPUState *cpu_state; - - DPRINTF("%s: Init cpu_by_vcpu_id\n", __func__); - CPU_FOREACH(cpu_state) { - DPRINTF("%s: cpu_by_vcpu_id[%d]=%p\n", - __func__, cpu_state->cpu_index, cpu_state); - state->cpu_by_vcpu_id[cpu_state->cpu_index] = cpu_state; - } - qemu_set_fd_handler(evtchn_fd, cpu_handle_ioreq, NULL, state); - } -} - - -static void xen_hvm_change_state_handler(void *opaque, bool running, - RunState rstate) -{ - XenIOState *state = opaque; - - if (running) { - xen_main_loop_prepare(state); - } - - xen_set_ioreq_server_state(xen_domid, - state->ioservid, - (rstate == RUN_STATE_RUNNING)); -} - -static void xen_exit_notifier(Notifier *n, void *data) -{ - XenIOState *state = container_of(n, XenIOState, exit); - - xen_destroy_ioreq_server(xen_domid, state->ioservid); - if (state->fres != NULL) { - xenforeignmemory_unmap_resource(xen_fmem, state->fres); - } - - qemu_xen_evtchn_close(state->xce_handle); - xs_daemon_close(state->xenstore); -} - #ifdef XEN_COMPAT_PHYSMAP static void xen_read_physmap(XenIOState *state) { @@ -1313,135 +572,34 @@ static void xen_wakeup_notifier(Notifier *notifier, void *data) xc_set_hvm_param(xen_xc, xen_domid, HVM_PARAM_ACPI_S_STATE, 0); } -static int xen_map_ioreq_server(XenIOState *state) -{ - void *addr = NULL; - xen_pfn_t ioreq_pfn; - xen_pfn_t bufioreq_pfn; - evtchn_port_t bufioreq_evtchn; - int rc; - - /* - * Attempt to map using the resource API and fall back to normal - * foreign mapping if this is not supported. - */ - QEMU_BUILD_BUG_ON(XENMEM_resource_ioreq_server_frame_bufioreq != 0); - QEMU_BUILD_BUG_ON(XENMEM_resource_ioreq_server_frame_ioreq(0) != 1); - state->fres = xenforeignmemory_map_resource(xen_fmem, xen_domid, - XENMEM_resource_ioreq_server, - state->ioservid, 0, 2, - &addr, - PROT_READ | PROT_WRITE, 0); - if (state->fres != NULL) { - trace_xen_map_resource_ioreq(state->ioservid, addr); - state->buffered_io_page = addr; - state->shared_page = addr + TARGET_PAGE_SIZE; - } else if (errno != EOPNOTSUPP) { - error_report("failed to map ioreq server resources: error %d handle=%p", - errno, xen_xc); - return -1; - } - - rc = xen_get_ioreq_server_info(xen_domid, state->ioservid, - (state->shared_page == NULL) ? - &ioreq_pfn : NULL, - (state->buffered_io_page == NULL) ? - &bufioreq_pfn : NULL, - &bufioreq_evtchn); - if (rc < 0) { - error_report("failed to get ioreq server info: error %d handle=%p", - errno, xen_xc); - return rc; - } - - if (state->shared_page == NULL) { - DPRINTF("shared page at pfn %lx\n", ioreq_pfn); - - state->shared_page = xenforeignmemory_map(xen_fmem, xen_domid, - PROT_READ | PROT_WRITE, - 1, &ioreq_pfn, NULL); - if (state->shared_page == NULL) { - error_report("map shared IO page returned error %d handle=%p", - errno, xen_xc); - } - } - - if (state->buffered_io_page == NULL) { - DPRINTF("buffered io page at pfn %lx\n", bufioreq_pfn); - - state->buffered_io_page = xenforeignmemory_map(xen_fmem, xen_domid, - PROT_READ | PROT_WRITE, - 1, &bufioreq_pfn, - NULL); - if (state->buffered_io_page == NULL) { - error_report("map buffered IO page returned error %d", errno); - return -1; - } - } - - if (state->shared_page == NULL || state->buffered_io_page == NULL) { - return -1; - } - - DPRINTF("buffered io evtchn is %x\n", bufioreq_evtchn); - - state->bufioreq_remote_port = bufioreq_evtchn; - - return 0; -} - void xen_hvm_init_pc(PCMachineState *pcms, MemoryRegion **ram_memory) { MachineState *ms = MACHINE(pcms); unsigned int max_cpus = ms->smp.max_cpus; - int i, rc; + int rc; xen_pfn_t ioreq_pfn; XenIOState *state; - setup_xen_backend_ops(); - state = g_new0(XenIOState, 1); - state->xce_handle = qemu_xen_evtchn_open(); - if (state->xce_handle == NULL) { - perror("xen: event channel open"); - goto err; - } - - state->xenstore = xs_daemon_open(); - if (state->xenstore == NULL) { - perror("xen: xenstore open"); - goto err; - } - - xen_create_ioreq_server(xen_domid, &state->ioservid); - - state->exit.notify = xen_exit_notifier; - qemu_add_exit_notifier(&state->exit); + xen_register_ioreq(state, max_cpus, xen_memory_listener); - state->suspend.notify = xen_suspend_notifier; - qemu_register_suspend_notifier(&state->suspend); + QLIST_INIT(&xen_physmap); + xen_read_physmap(state); - state->wakeup.notify = xen_wakeup_notifier; - qemu_register_wakeup_notifier(&state->wakeup); + suspend.notify = xen_suspend_notifier; + qemu_register_suspend_notifier(&suspend); - /* - * Register wake-up support in QMP query-current-machine API - */ - qemu_register_wakeup_support(); - - rc = xen_map_ioreq_server(state); - if (rc < 0) { - goto err; - } + wakeup.notify = xen_wakeup_notifier; + qemu_register_wakeup_notifier(&wakeup); rc = xen_get_vmport_regs_pfn(xen_xc, xen_domid, &ioreq_pfn); if (!rc) { DPRINTF("shared vmport page at pfn %lx\n", ioreq_pfn); - state->shared_vmport_page = + shared_vmport_page = xenforeignmemory_map(xen_fmem, xen_domid, PROT_READ|PROT_WRITE, 1, &ioreq_pfn, NULL); - if (state->shared_vmport_page == NULL) { + if (shared_vmport_page == NULL) { error_report("map shared vmport IO page returned error %d handle=%p", errno, xen_xc); goto err; @@ -1452,65 +610,8 @@ void xen_hvm_init_pc(PCMachineState *pcms, MemoryRegion **ram_memory) goto err; } - /* Note: cpus is empty at this point in init */ - state->cpu_by_vcpu_id = g_new0(CPUState *, max_cpus); - - rc = xen_set_ioreq_server_state(xen_domid, state->ioservid, true); - if (rc < 0) { - error_report("failed to enable ioreq server info: error %d handle=%p", - errno, xen_xc); - goto err; - } - - state->ioreq_local_port = g_new0(evtchn_port_t, max_cpus); - - /* FIXME: how about if we overflow the page here? */ - for (i = 0; i < max_cpus; i++) { - rc = qemu_xen_evtchn_bind_interdomain(state->xce_handle, xen_domid, - xen_vcpu_eport(state->shared_page, - i)); - if (rc == -1) { - error_report("shared evtchn %d bind error %d", i, errno); - goto err; - } - state->ioreq_local_port[i] = rc; - } - - rc = qemu_xen_evtchn_bind_interdomain(state->xce_handle, xen_domid, - state->bufioreq_remote_port); - if (rc == -1) { - error_report("buffered evtchn bind error %d", errno); - goto err; - } - state->bufioreq_local_port = rc; - - /* Init RAM management */ -#ifdef XEN_COMPAT_PHYSMAP - xen_map_cache_init(xen_phys_offset_to_gaddr, state); -#else - xen_map_cache_init(NULL, state); -#endif xen_ram_init(pcms, ms->ram_size, ram_memory); - qemu_add_vm_change_state_handler(xen_hvm_change_state_handler, state); - - state->memory_listener = xen_memory_listener; - memory_listener_register(&state->memory_listener, &address_space_memory); - state->log_for_dirtybit = NULL; - - state->io_listener = xen_io_listener; - memory_listener_register(&state->io_listener, &address_space_io); - - state->device_listener = xen_device_listener; - QLIST_INIT(&state->dev_list); - device_listener_register(&state->device_listener); - - xen_bus_init(); - xen_be_init(); - - QLIST_INIT(&xen_physmap); - xen_read_physmap(state); - /* Disable ACPI build because Xen handles it */ pcms->acpi_build_enabled = false; @@ -1521,59 +622,11 @@ err: exit(1); } -void destroy_hvm_domain(bool reboot) -{ - xc_interface *xc_handle; - int sts; - int rc; - - unsigned int reason = reboot ? SHUTDOWN_reboot : SHUTDOWN_poweroff; - - if (xen_dmod) { - rc = xendevicemodel_shutdown(xen_dmod, xen_domid, reason); - if (!rc) { - return; - } - if (errno != ENOTTY /* old Xen */) { - perror("xendevicemodel_shutdown failed"); - } - /* well, try the old thing then */ - } - - xc_handle = xc_interface_open(0, 0, 0); - if (xc_handle == NULL) { - fprintf(stderr, "Cannot acquire xenctrl handle\n"); - } else { - sts = xc_domain_shutdown(xc_handle, xen_domid, reason); - if (sts != 0) { - fprintf(stderr, "xc_domain_shutdown failed to issue %s, " - "sts %d, %s\n", reboot ? "reboot" : "poweroff", - sts, strerror(errno)); - } else { - fprintf(stderr, "Issued domain %d %s\n", xen_domid, - reboot ? "reboot" : "poweroff"); - } - xc_interface_close(xc_handle); - } -} - void xen_register_framebuffer(MemoryRegion *mr) { framebuffer = mr; } -void xen_shutdown_fatal_error(const char *fmt, ...) -{ - va_list ap; - - va_start(ap, fmt); - vfprintf(stderr, fmt, ap); - va_end(ap); - fprintf(stderr, "Will destroy the domain.\n"); - /* destroy the domain */ - qemu_system_shutdown_request(SHUTDOWN_CAUSE_HOST_ERROR); -} - void xen_hvm_modified_memory(ram_addr_t start, ram_addr_t length) { if (unlikely(xen_in_migration)) { @@ -1605,3 +658,57 @@ void qmp_xen_set_global_dirty_log(bool enable, Error **errp) memory_global_dirty_log_stop(GLOBAL_DIRTY_MIGRATION); } } + +void arch_xen_set_memory(XenIOState *state, MemoryRegionSection *section, + bool add) +{ + hwaddr start_addr = section->offset_within_address_space; + ram_addr_t size = int128_get64(section->size); + bool log_dirty = memory_region_is_logging(section->mr, DIRTY_MEMORY_VGA); + hvmmem_type_t mem_type; + + if (!memory_region_is_ram(section->mr)) { + return; + } + + if (log_dirty != add) { + return; + } + + trace_xen_client_set_memory(start_addr, size, log_dirty); + + start_addr &= TARGET_PAGE_MASK; + size = TARGET_PAGE_ALIGN(size); + + if (add) { + if (!memory_region_is_rom(section->mr)) { + xen_add_to_physmap(state, start_addr, size, + section->mr, section->offset_within_region); + } else { + mem_type = HVMMEM_ram_ro; + if (xen_set_mem_type(xen_domid, mem_type, + start_addr >> TARGET_PAGE_BITS, + size >> TARGET_PAGE_BITS)) { + DPRINTF("xen_set_mem_type error, addr: "HWADDR_FMT_plx"\n", + start_addr); + } + } + } else { + if (xen_remove_from_physmap(state, start_addr, size) < 0) { + DPRINTF("physmapping does not exist at "HWADDR_FMT_plx"\n", start_addr); + } + } +} + +void arch_handle_ioreq(XenIOState *state, ioreq_t *req) +{ + switch (req->type) { + case IOREQ_TYPE_VMWARE_PORT: + handle_vmport_ioreq(state, req); + break; + default: + hw_error("Invalid ioreq type 0x%x\n", req->type); + } + + return; +} diff --git a/hw/xen/meson.build b/hw/xen/meson.build index 19c6aab..afd2075 100644 --- a/hw/xen/meson.build +++ b/hw/xen/meson.build @@ -26,3 +26,10 @@ else endif specific_ss.add_all(when: ['CONFIG_XEN', xen], if_true: xen_specific_ss) + +xen_ss = ss.source_set() + +xen_ss.add(when: 'CONFIG_XEN', if_true: files( + 'xen-mapcache.c', + 'xen-hvm-common.c', +)) diff --git a/hw/xen/trace-events b/hw/xen/trace-events index 55c9e1d..67a6c41 100644 --- a/hw/xen/trace-events +++ b/hw/xen/trace-events @@ -41,3 +41,22 @@ xs_node_vprintf(char *path, char *value) "%s %s" xs_node_vscanf(char *path, char *value) "%s %s" xs_node_watch(char *path) "%s" xs_node_unwatch(char *path) "%s" + +# xen-hvm.c +xen_ram_alloc(unsigned long ram_addr, unsigned long size) "requested: 0x%lx, size 0x%lx" +xen_client_set_memory(uint64_t start_addr, unsigned long size, bool log_dirty) "0x%"PRIx64" size 0x%lx, log_dirty %i" +handle_ioreq(void *req, uint32_t type, uint32_t dir, uint32_t df, uint32_t data_is_ptr, uint64_t addr, uint64_t data, uint32_t count, uint32_t size) "I/O=%p type=%d dir=%d df=%d ptr=%d port=0x%"PRIx64" data=0x%"PRIx64" count=%d size=%d" +handle_ioreq_read(void *req, uint32_t type, uint32_t df, uint32_t data_is_ptr, uint64_t addr, uint64_t data, uint32_t count, uint32_t size) "I/O=%p read type=%d df=%d ptr=%d port=0x%"PRIx64" data=0x%"PRIx64" count=%d size=%d" +handle_ioreq_write(void *req, uint32_t type, uint32_t df, uint32_t data_is_ptr, uint64_t addr, uint64_t data, uint32_t count, uint32_t size) "I/O=%p write type=%d df=%d ptr=%d port=0x%"PRIx64" data=0x%"PRIx64" count=%d size=%d" +cpu_ioreq_pio(void *req, uint32_t dir, uint32_t df, uint32_t data_is_ptr, uint64_t addr, uint64_t data, uint32_t count, uint32_t size) "I/O=%p pio dir=%d df=%d ptr=%d port=0x%"PRIx64" data=0x%"PRIx64" count=%d size=%d" +cpu_ioreq_pio_read_reg(void *req, uint64_t data, uint64_t addr, uint32_t size) "I/O=%p pio read reg data=0x%"PRIx64" port=0x%"PRIx64" size=%d" +cpu_ioreq_pio_write_reg(void *req, uint64_t data, uint64_t addr, uint32_t size) "I/O=%p pio write reg data=0x%"PRIx64" port=0x%"PRIx64" size=%d" +cpu_ioreq_move(void *req, uint32_t dir, uint32_t df, uint32_t data_is_ptr, uint64_t addr, uint64_t data, uint32_t count, uint32_t size) "I/O=%p copy dir=%d df=%d ptr=%d port=0x%"PRIx64" data=0x%"PRIx64" count=%d size=%d" +xen_map_resource_ioreq(uint32_t id, void *addr) "id: %u addr: %p" +cpu_ioreq_config_read(void *req, uint32_t sbdf, uint32_t reg, uint32_t size, uint32_t data) "I/O=%p sbdf=0x%x reg=%u size=%u data=0x%x" +cpu_ioreq_config_write(void *req, uint32_t sbdf, uint32_t reg, uint32_t size, uint32_t data) "I/O=%p sbdf=0x%x reg=%u size=%u data=0x%x" + +# xen-mapcache.c +xen_map_cache(uint64_t phys_addr) "want 0x%"PRIx64 +xen_remap_bucket(uint64_t index) "index 0x%"PRIx64 +xen_map_cache_return(void* ptr) "%p" diff --git a/hw/xen/xen-hvm-common.c b/hw/xen/xen-hvm-common.c new file mode 100644 index 0000000..42339c9 --- /dev/null +++ b/hw/xen/xen-hvm-common.c @@ -0,0 +1,879 @@ +#include "qemu/osdep.h" +#include "qemu/units.h" +#include "qapi/error.h" +#include "trace.h" + +#include "hw/pci/pci_host.h" +#include "hw/xen/xen-hvm-common.h" +#include "hw/xen/xen-bus.h" +#include "hw/boards.h" +#include "hw/xen/arch_hvm.h" + +MemoryRegion ram_memory; + +void xen_ram_alloc(ram_addr_t ram_addr, ram_addr_t size, MemoryRegion *mr, + Error **errp) +{ + unsigned long nr_pfn; + xen_pfn_t *pfn_list; + int i; + + if (runstate_check(RUN_STATE_INMIGRATE)) { + /* RAM already populated in Xen */ + fprintf(stderr, "%s: do not alloc "RAM_ADDR_FMT + " bytes of ram at "RAM_ADDR_FMT" when runstate is INMIGRATE\n", + __func__, size, ram_addr); + return; + } + + if (mr == &ram_memory) { + return; + } + + trace_xen_ram_alloc(ram_addr, size); + + nr_pfn = size >> TARGET_PAGE_BITS; + pfn_list = g_new(xen_pfn_t, nr_pfn); + + for (i = 0; i < nr_pfn; i++) { + pfn_list[i] = (ram_addr >> TARGET_PAGE_BITS) + i; + } + + if (xc_domain_populate_physmap_exact(xen_xc, xen_domid, nr_pfn, 0, 0, pfn_list)) { + error_setg(errp, "xen: failed to populate ram at " RAM_ADDR_FMT, + ram_addr); + } + + g_free(pfn_list); +} + +static void xen_set_memory(struct MemoryListener *listener, + MemoryRegionSection *section, + bool add) +{ + XenIOState *state = container_of(listener, XenIOState, memory_listener); + + if (section->mr == &ram_memory) { + return; + } else { + if (add) { + xen_map_memory_section(xen_domid, state->ioservid, + section); + } else { + xen_unmap_memory_section(xen_domid, state->ioservid, + section); + } + } + + arch_xen_set_memory(state, section, add); +} + +void xen_region_add(MemoryListener *listener, + MemoryRegionSection *section) +{ + memory_region_ref(section->mr); + xen_set_memory(listener, section, true); +} + +void xen_region_del(MemoryListener *listener, + MemoryRegionSection *section) +{ + xen_set_memory(listener, section, false); + memory_region_unref(section->mr); +} + +void xen_io_add(MemoryListener *listener, + MemoryRegionSection *section) +{ + XenIOState *state = container_of(listener, XenIOState, io_listener); + MemoryRegion *mr = section->mr; + + if (mr->ops == &unassigned_io_ops) { + return; + } + + memory_region_ref(mr); + + xen_map_io_section(xen_domid, state->ioservid, section); +} + +void xen_io_del(MemoryListener *listener, + MemoryRegionSection *section) +{ + XenIOState *state = container_of(listener, XenIOState, io_listener); + MemoryRegion *mr = section->mr; + + if (mr->ops == &unassigned_io_ops) { + return; + } + + xen_unmap_io_section(xen_domid, state->ioservid, section); + + memory_region_unref(mr); +} + +void xen_device_realize(DeviceListener *listener, + DeviceState *dev) +{ + XenIOState *state = container_of(listener, XenIOState, device_listener); + + if (object_dynamic_cast(OBJECT(dev), TYPE_PCI_DEVICE)) { + PCIDevice *pci_dev = PCI_DEVICE(dev); + XenPciDevice *xendev = g_new(XenPciDevice, 1); + + xendev->pci_dev = pci_dev; + xendev->sbdf = PCI_BUILD_BDF(pci_dev_bus_num(pci_dev), + pci_dev->devfn); + QLIST_INSERT_HEAD(&state->dev_list, xendev, entry); + + xen_map_pcidev(xen_domid, state->ioservid, pci_dev); + } +} + +void xen_device_unrealize(DeviceListener *listener, + DeviceState *dev) +{ + XenIOState *state = container_of(listener, XenIOState, device_listener); + + if (object_dynamic_cast(OBJECT(dev), TYPE_PCI_DEVICE)) { + PCIDevice *pci_dev = PCI_DEVICE(dev); + XenPciDevice *xendev, *next; + + xen_unmap_pcidev(xen_domid, state->ioservid, pci_dev); + + QLIST_FOREACH_SAFE(xendev, &state->dev_list, entry, next) { + if (xendev->pci_dev == pci_dev) { + QLIST_REMOVE(xendev, entry); + g_free(xendev); + break; + } + } + } +} + +MemoryListener xen_io_listener = { + .name = "xen-io", + .region_add = xen_io_add, + .region_del = xen_io_del, + .priority = 10, +}; + +DeviceListener xen_device_listener = { + .realize = xen_device_realize, + .unrealize = xen_device_unrealize, +}; + +/* get the ioreq packets from share mem */ +static ioreq_t *cpu_get_ioreq_from_shared_memory(XenIOState *state, int vcpu) +{ + ioreq_t *req = xen_vcpu_ioreq(state->shared_page, vcpu); + + if (req->state != STATE_IOREQ_READY) { + DPRINTF("I/O request not ready: " + "%x, ptr: %x, port: %"PRIx64", " + "data: %"PRIx64", count: %u, size: %u\n", + req->state, req->data_is_ptr, req->addr, + req->data, req->count, req->size); + return NULL; + } + + xen_rmb(); /* see IOREQ_READY /then/ read contents of ioreq */ + + req->state = STATE_IOREQ_INPROCESS; + return req; +} + +/* use poll to get the port notification */ +/* ioreq_vec--out,the */ +/* retval--the number of ioreq packet */ +static ioreq_t *cpu_get_ioreq(XenIOState *state) +{ + MachineState *ms = MACHINE(qdev_get_machine()); + unsigned int max_cpus = ms->smp.max_cpus; + int i; + evtchn_port_t port; + + port = qemu_xen_evtchn_pending(state->xce_handle); + if (port == state->bufioreq_local_port) { + timer_mod(state->buffered_io_timer, + BUFFER_IO_MAX_DELAY + qemu_clock_get_ms(QEMU_CLOCK_REALTIME)); + return NULL; + } + + if (port != -1) { + for (i = 0; i < max_cpus; i++) { + if (state->ioreq_local_port[i] == port) { + break; + } + } + + if (i == max_cpus) { + hw_error("Fatal error while trying to get io event!\n"); + } + + /* unmask the wanted port again */ + qemu_xen_evtchn_unmask(state->xce_handle, port); + + /* get the io packet from shared memory */ + state->send_vcpu = i; + return cpu_get_ioreq_from_shared_memory(state, i); + } + + /* read error or read nothing */ + return NULL; +} + +static uint32_t do_inp(uint32_t addr, unsigned long size) +{ + switch (size) { + case 1: + return cpu_inb(addr); + case 2: + return cpu_inw(addr); + case 4: + return cpu_inl(addr); + default: + hw_error("inp: bad size: %04x %lx", addr, size); + } +} + +static void do_outp(uint32_t addr, + unsigned long size, uint32_t val) +{ + switch (size) { + case 1: + return cpu_outb(addr, val); + case 2: + return cpu_outw(addr, val); + case 4: + return cpu_outl(addr, val); + default: + hw_error("outp: bad size: %04x %lx", addr, size); + } +} + +/* + * Helper functions which read/write an object from/to physical guest + * memory, as part of the implementation of an ioreq. + * + * Equivalent to + * cpu_physical_memory_rw(addr + (req->df ? -1 : +1) * req->size * i, + * val, req->size, 0/1) + * except without the integer overflow problems. + */ +static void rw_phys_req_item(hwaddr addr, + ioreq_t *req, uint32_t i, void *val, int rw) +{ + /* Do everything unsigned so overflow just results in a truncated result + * and accesses to undesired parts of guest memory, which is up + * to the guest */ + hwaddr offset = (hwaddr)req->size * i; + if (req->df) { + addr -= offset; + } else { + addr += offset; + } + cpu_physical_memory_rw(addr, val, req->size, rw); +} + +static inline void read_phys_req_item(hwaddr addr, + ioreq_t *req, uint32_t i, void *val) +{ + rw_phys_req_item(addr, req, i, val, 0); +} +static inline void write_phys_req_item(hwaddr addr, + ioreq_t *req, uint32_t i, void *val) +{ + rw_phys_req_item(addr, req, i, val, 1); +} + + +void cpu_ioreq_pio(ioreq_t *req) +{ + uint32_t i; + + trace_cpu_ioreq_pio(req, req->dir, req->df, req->data_is_ptr, req->addr, + req->data, req->count, req->size); + + if (req->size > sizeof(uint32_t)) { + hw_error("PIO: bad size (%u)", req->size); + } + + if (req->dir == IOREQ_READ) { + if (!req->data_is_ptr) { + req->data = do_inp(req->addr, req->size); + trace_cpu_ioreq_pio_read_reg(req, req->data, req->addr, + req->size); + } else { + uint32_t tmp; + + for (i = 0; i < req->count; i++) { + tmp = do_inp(req->addr, req->size); + write_phys_req_item(req->data, req, i, &tmp); + } + } + } else if (req->dir == IOREQ_WRITE) { + if (!req->data_is_ptr) { + trace_cpu_ioreq_pio_write_reg(req, req->data, req->addr, + req->size); + do_outp(req->addr, req->size, req->data); + } else { + for (i = 0; i < req->count; i++) { + uint32_t tmp = 0; + + read_phys_req_item(req->data, req, i, &tmp); + do_outp(req->addr, req->size, tmp); + } + } + } +} + +static void cpu_ioreq_move(ioreq_t *req) +{ + uint32_t i; + + trace_cpu_ioreq_move(req, req->dir, req->df, req->data_is_ptr, req->addr, + req->data, req->count, req->size); + + if (req->size > sizeof(req->data)) { + hw_error("MMIO: bad size (%u)", req->size); + } + + if (!req->data_is_ptr) { + if (req->dir == IOREQ_READ) { + for (i = 0; i < req->count; i++) { + read_phys_req_item(req->addr, req, i, &req->data); + } + } else if (req->dir == IOREQ_WRITE) { + for (i = 0; i < req->count; i++) { + write_phys_req_item(req->addr, req, i, &req->data); + } + } + } else { + uint64_t tmp; + + if (req->dir == IOREQ_READ) { + for (i = 0; i < req->count; i++) { + read_phys_req_item(req->addr, req, i, &tmp); + write_phys_req_item(req->data, req, i, &tmp); + } + } else if (req->dir == IOREQ_WRITE) { + for (i = 0; i < req->count; i++) { + read_phys_req_item(req->data, req, i, &tmp); + write_phys_req_item(req->addr, req, i, &tmp); + } + } + } +} + +static void cpu_ioreq_config(XenIOState *state, ioreq_t *req) +{ + uint32_t sbdf = req->addr >> 32; + uint32_t reg = req->addr; + XenPciDevice *xendev; + + if (req->size != sizeof(uint8_t) && req->size != sizeof(uint16_t) && + req->size != sizeof(uint32_t)) { + hw_error("PCI config access: bad size (%u)", req->size); + } + + if (req->count != 1) { + hw_error("PCI config access: bad count (%u)", req->count); + } + + QLIST_FOREACH(xendev, &state->dev_list, entry) { + if (xendev->sbdf != sbdf) { + continue; + } + + if (!req->data_is_ptr) { + if (req->dir == IOREQ_READ) { + req->data = pci_host_config_read_common( + xendev->pci_dev, reg, PCI_CONFIG_SPACE_SIZE, + req->size); + trace_cpu_ioreq_config_read(req, xendev->sbdf, reg, + req->size, req->data); + } else if (req->dir == IOREQ_WRITE) { + trace_cpu_ioreq_config_write(req, xendev->sbdf, reg, + req->size, req->data); + pci_host_config_write_common( + xendev->pci_dev, reg, PCI_CONFIG_SPACE_SIZE, + req->data, req->size); + } + } else { + uint32_t tmp; + + if (req->dir == IOREQ_READ) { + tmp = pci_host_config_read_common( + xendev->pci_dev, reg, PCI_CONFIG_SPACE_SIZE, + req->size); + trace_cpu_ioreq_config_read(req, xendev->sbdf, reg, + req->size, tmp); + write_phys_req_item(req->data, req, 0, &tmp); + } else if (req->dir == IOREQ_WRITE) { + read_phys_req_item(req->data, req, 0, &tmp); + trace_cpu_ioreq_config_write(req, xendev->sbdf, reg, + req->size, tmp); + pci_host_config_write_common( + xendev->pci_dev, reg, PCI_CONFIG_SPACE_SIZE, + tmp, req->size); + } + } + } +} + +static void handle_ioreq(XenIOState *state, ioreq_t *req) +{ + trace_handle_ioreq(req, req->type, req->dir, req->df, req->data_is_ptr, + req->addr, req->data, req->count, req->size); + + if (!req->data_is_ptr && (req->dir == IOREQ_WRITE) && + (req->size < sizeof (target_ulong))) { + req->data &= ((target_ulong) 1 << (8 * req->size)) - 1; + } + + if (req->dir == IOREQ_WRITE) + trace_handle_ioreq_write(req, req->type, req->df, req->data_is_ptr, + req->addr, req->data, req->count, req->size); + + switch (req->type) { + case IOREQ_TYPE_PIO: + cpu_ioreq_pio(req); + break; + case IOREQ_TYPE_COPY: + cpu_ioreq_move(req); + break; + case IOREQ_TYPE_TIMEOFFSET: + break; + case IOREQ_TYPE_INVALIDATE: + xen_invalidate_map_cache(); + break; + case IOREQ_TYPE_PCI_CONFIG: + cpu_ioreq_config(state, req); + break; + default: + arch_handle_ioreq(state, req); + } + if (req->dir == IOREQ_READ) { + trace_handle_ioreq_read(req, req->type, req->df, req->data_is_ptr, + req->addr, req->data, req->count, req->size); + } +} + +static bool handle_buffered_iopage(XenIOState *state) +{ + buffered_iopage_t *buf_page = state->buffered_io_page; + buf_ioreq_t *buf_req = NULL; + bool handled_ioreq = false; + ioreq_t req; + int qw; + + if (!buf_page) { + return 0; + } + + memset(&req, 0x00, sizeof(req)); + req.state = STATE_IOREQ_READY; + req.count = 1; + req.dir = IOREQ_WRITE; + + for (;;) { + uint32_t rdptr = buf_page->read_pointer, wrptr; + + xen_rmb(); + wrptr = buf_page->write_pointer; + xen_rmb(); + if (rdptr != buf_page->read_pointer) { + continue; + } + if (rdptr == wrptr) { + break; + } + buf_req = &buf_page->buf_ioreq[rdptr % IOREQ_BUFFER_SLOT_NUM]; + req.size = 1U << buf_req->size; + req.addr = buf_req->addr; + req.data = buf_req->data; + req.type = buf_req->type; + xen_rmb(); + qw = (req.size == 8); + if (qw) { + if (rdptr + 1 == wrptr) { + hw_error("Incomplete quad word buffered ioreq"); + } + buf_req = &buf_page->buf_ioreq[(rdptr + 1) % + IOREQ_BUFFER_SLOT_NUM]; + req.data |= ((uint64_t)buf_req->data) << 32; + xen_rmb(); + } + + handle_ioreq(state, &req); + + /* Only req.data may get updated by handle_ioreq(), albeit even that + * should not happen as such data would never make it to the guest (we + * can only usefully see writes here after all). + */ + assert(req.state == STATE_IOREQ_READY); + assert(req.count == 1); + assert(req.dir == IOREQ_WRITE); + assert(!req.data_is_ptr); + + qatomic_add(&buf_page->read_pointer, qw + 1); + handled_ioreq = true; + } + + return handled_ioreq; +} + +static void handle_buffered_io(void *opaque) +{ + XenIOState *state = opaque; + + if (handle_buffered_iopage(state)) { + timer_mod(state->buffered_io_timer, + BUFFER_IO_MAX_DELAY + qemu_clock_get_ms(QEMU_CLOCK_REALTIME)); + } else { + timer_del(state->buffered_io_timer); + qemu_xen_evtchn_unmask(state->xce_handle, state->bufioreq_local_port); + } +} + +static void cpu_handle_ioreq(void *opaque) +{ + XenIOState *state = opaque; + ioreq_t *req = cpu_get_ioreq(state); + + handle_buffered_iopage(state); + if (req) { + ioreq_t copy = *req; + + xen_rmb(); + handle_ioreq(state, ©); + req->data = copy.data; + + if (req->state != STATE_IOREQ_INPROCESS) { + fprintf(stderr, "Badness in I/O request ... not in service?!: " + "%x, ptr: %x, port: %"PRIx64", " + "data: %"PRIx64", count: %u, size: %u, type: %u\n", + req->state, req->data_is_ptr, req->addr, + req->data, req->count, req->size, req->type); + destroy_hvm_domain(false); + return; + } + + xen_wmb(); /* Update ioreq contents /then/ update state. */ + + /* + * We do this before we send the response so that the tools + * have the opportunity to pick up on the reset before the + * guest resumes and does a hlt with interrupts disabled which + * causes Xen to powerdown the domain. + */ + if (runstate_is_running()) { + ShutdownCause request; + + if (qemu_shutdown_requested_get()) { + destroy_hvm_domain(false); + } + request = qemu_reset_requested_get(); + if (request) { + qemu_system_reset(request); + destroy_hvm_domain(true); + } + } + + req->state = STATE_IORESP_READY; + qemu_xen_evtchn_notify(state->xce_handle, + state->ioreq_local_port[state->send_vcpu]); + } +} + +static void xen_main_loop_prepare(XenIOState *state) +{ + int evtchn_fd = -1; + + if (state->xce_handle != NULL) { + evtchn_fd = qemu_xen_evtchn_fd(state->xce_handle); + } + + state->buffered_io_timer = timer_new_ms(QEMU_CLOCK_REALTIME, handle_buffered_io, + state); + + if (evtchn_fd != -1) { + CPUState *cpu_state; + + DPRINTF("%s: Init cpu_by_vcpu_id\n", __func__); + CPU_FOREACH(cpu_state) { + DPRINTF("%s: cpu_by_vcpu_id[%d]=%p\n", + __func__, cpu_state->cpu_index, cpu_state); + state->cpu_by_vcpu_id[cpu_state->cpu_index] = cpu_state; + } + qemu_set_fd_handler(evtchn_fd, cpu_handle_ioreq, NULL, state); + } +} + + +void xen_hvm_change_state_handler(void *opaque, bool running, + RunState rstate) +{ + XenIOState *state = opaque; + + if (running) { + xen_main_loop_prepare(state); + } + + xen_set_ioreq_server_state(xen_domid, + state->ioservid, + (rstate == RUN_STATE_RUNNING)); +} + +void xen_exit_notifier(Notifier *n, void *data) +{ + XenIOState *state = container_of(n, XenIOState, exit); + + xen_destroy_ioreq_server(xen_domid, state->ioservid); + if (state->fres != NULL) { + xenforeignmemory_unmap_resource(xen_fmem, state->fres); + } + + qemu_xen_evtchn_close(state->xce_handle); + xs_daemon_close(state->xenstore); +} + +static int xen_map_ioreq_server(XenIOState *state) +{ + void *addr = NULL; + xen_pfn_t ioreq_pfn; + xen_pfn_t bufioreq_pfn; + evtchn_port_t bufioreq_evtchn; + int rc; + + /* + * Attempt to map using the resource API and fall back to normal + * foreign mapping if this is not supported. + */ + QEMU_BUILD_BUG_ON(XENMEM_resource_ioreq_server_frame_bufioreq != 0); + QEMU_BUILD_BUG_ON(XENMEM_resource_ioreq_server_frame_ioreq(0) != 1); + state->fres = xenforeignmemory_map_resource(xen_fmem, xen_domid, + XENMEM_resource_ioreq_server, + state->ioservid, 0, 2, + &addr, + PROT_READ | PROT_WRITE, 0); + if (state->fres != NULL) { + trace_xen_map_resource_ioreq(state->ioservid, addr); + state->buffered_io_page = addr; + state->shared_page = addr + XC_PAGE_SIZE; + } else if (errno != EOPNOTSUPP) { + error_report("failed to map ioreq server resources: error %d handle=%p", + errno, xen_xc); + return -1; + } + + rc = xen_get_ioreq_server_info(xen_domid, state->ioservid, + (state->shared_page == NULL) ? + &ioreq_pfn : NULL, + (state->buffered_io_page == NULL) ? + &bufioreq_pfn : NULL, + &bufioreq_evtchn); + if (rc < 0) { + error_report("failed to get ioreq server info: error %d handle=%p", + errno, xen_xc); + return rc; + } + + if (state->shared_page == NULL) { + DPRINTF("shared page at pfn %lx\n", ioreq_pfn); + + state->shared_page = xenforeignmemory_map(xen_fmem, xen_domid, + PROT_READ | PROT_WRITE, + 1, &ioreq_pfn, NULL); + if (state->shared_page == NULL) { + error_report("map shared IO page returned error %d handle=%p", + errno, xen_xc); + } + } + + if (state->buffered_io_page == NULL) { + DPRINTF("buffered io page at pfn %lx\n", bufioreq_pfn); + + state->buffered_io_page = xenforeignmemory_map(xen_fmem, xen_domid, + PROT_READ | PROT_WRITE, + 1, &bufioreq_pfn, + NULL); + if (state->buffered_io_page == NULL) { + error_report("map buffered IO page returned error %d", errno); + return -1; + } + } + + if (state->shared_page == NULL || state->buffered_io_page == NULL) { + return -1; + } + + DPRINTF("buffered io evtchn is %x\n", bufioreq_evtchn); + + state->bufioreq_remote_port = bufioreq_evtchn; + + return 0; +} + +void destroy_hvm_domain(bool reboot) +{ + xc_interface *xc_handle; + int sts; + int rc; + + unsigned int reason = reboot ? SHUTDOWN_reboot : SHUTDOWN_poweroff; + + if (xen_dmod) { + rc = xendevicemodel_shutdown(xen_dmod, xen_domid, reason); + if (!rc) { + return; + } + if (errno != ENOTTY /* old Xen */) { + error_report("xendevicemodel_shutdown failed with error %d", errno); + } + /* well, try the old thing then */ + } + + xc_handle = xc_interface_open(0, 0, 0); + if (xc_handle == NULL) { + fprintf(stderr, "Cannot acquire xenctrl handle\n"); + } else { + sts = xc_domain_shutdown(xc_handle, xen_domid, reason); + if (sts != 0) { + fprintf(stderr, "xc_domain_shutdown failed to issue %s, " + "sts %d, %s\n", reboot ? "reboot" : "poweroff", + sts, strerror(errno)); + } else { + fprintf(stderr, "Issued domain %d %s\n", xen_domid, + reboot ? "reboot" : "poweroff"); + } + xc_interface_close(xc_handle); + } +} + +void xen_shutdown_fatal_error(const char *fmt, ...) +{ + va_list ap; + + va_start(ap, fmt); + vfprintf(stderr, fmt, ap); + va_end(ap); + fprintf(stderr, "Will destroy the domain.\n"); + /* destroy the domain */ + qemu_system_shutdown_request(SHUTDOWN_CAUSE_HOST_ERROR); +} + +static void xen_do_ioreq_register(XenIOState *state, + unsigned int max_cpus, + MemoryListener xen_memory_listener) +{ + int i, rc; + + state->exit.notify = xen_exit_notifier; + qemu_add_exit_notifier(&state->exit); + + /* + * Register wake-up support in QMP query-current-machine API + */ + qemu_register_wakeup_support(); + + rc = xen_map_ioreq_server(state); + if (rc < 0) { + goto err; + } + + /* Note: cpus is empty at this point in init */ + state->cpu_by_vcpu_id = g_new0(CPUState *, max_cpus); + + rc = xen_set_ioreq_server_state(xen_domid, state->ioservid, true); + if (rc < 0) { + error_report("failed to enable ioreq server info: error %d handle=%p", + errno, xen_xc); + goto err; + } + + state->ioreq_local_port = g_new0(evtchn_port_t, max_cpus); + + /* FIXME: how about if we overflow the page here? */ + for (i = 0; i < max_cpus; i++) { + rc = qemu_xen_evtchn_bind_interdomain(state->xce_handle, xen_domid, + xen_vcpu_eport(state->shared_page, + i)); + if (rc == -1) { + error_report("shared evtchn %d bind error %d", i, errno); + goto err; + } + state->ioreq_local_port[i] = rc; + } + + rc = qemu_xen_evtchn_bind_interdomain(state->xce_handle, xen_domid, + state->bufioreq_remote_port); + if (rc == -1) { + error_report("buffered evtchn bind error %d", errno); + goto err; + } + state->bufioreq_local_port = rc; + + /* Init RAM management */ +#ifdef XEN_COMPAT_PHYSMAP + xen_map_cache_init(xen_phys_offset_to_gaddr, state); +#else + xen_map_cache_init(NULL, state); +#endif + + qemu_add_vm_change_state_handler(xen_hvm_change_state_handler, state); + + state->memory_listener = xen_memory_listener; + memory_listener_register(&state->memory_listener, &address_space_memory); + + state->io_listener = xen_io_listener; + memory_listener_register(&state->io_listener, &address_space_io); + + state->device_listener = xen_device_listener; + QLIST_INIT(&state->dev_list); + device_listener_register(&state->device_listener); + + return; + +err: + error_report("xen hardware virtual machine initialisation failed"); + exit(1); +} + +void xen_register_ioreq(XenIOState *state, unsigned int max_cpus, + MemoryListener xen_memory_listener) +{ + int rc; + + setup_xen_backend_ops(); + + state->xce_handle = qemu_xen_evtchn_open(); + if (state->xce_handle == NULL) { + error_report("xen: event channel open failed with error %d", errno); + goto err; + } + + state->xenstore = xs_daemon_open(); + if (state->xenstore == NULL) { + error_report("xen: xenstore open failed with error %d", errno); + goto err; + } + + rc = xen_create_ioreq_server(xen_domid, &state->ioservid); + if (!rc) { + xen_do_ioreq_register(state, max_cpus, xen_memory_listener); + } else { + warn_report("xen: failed to create ioreq server"); + } + + xen_bus_init(); + + xen_be_init(); + + return; + +err: + error_report("xen hardware virtual machine backend registration failed"); + exit(1); +} diff --git a/hw/i386/xen/xen-mapcache.c b/hw/xen/xen-mapcache.c index f7d9746..f7d9746 100644 --- a/hw/i386/xen/xen-mapcache.c +++ b/hw/xen/xen-mapcache.c diff --git a/include/hw/arm/xen_arch_hvm.h b/include/hw/arm/xen_arch_hvm.h new file mode 100644 index 0000000..8fd645e --- /dev/null +++ b/include/hw/arm/xen_arch_hvm.h @@ -0,0 +1,9 @@ +#ifndef HW_XEN_ARCH_ARM_HVM_H +#define HW_XEN_ARCH_ARM_HVM_H + +#include <xen/hvm/ioreq.h> +void arch_handle_ioreq(XenIOState *state, ioreq_t *req); +void arch_xen_set_memory(XenIOState *state, + MemoryRegionSection *section, + bool add); +#endif diff --git a/include/hw/i386/xen_arch_hvm.h b/include/hw/i386/xen_arch_hvm.h new file mode 100644 index 0000000..1000f8f --- /dev/null +++ b/include/hw/i386/xen_arch_hvm.h @@ -0,0 +1,11 @@ +#ifndef HW_XEN_ARCH_I386_HVM_H +#define HW_XEN_ARCH_I386_HVM_H + +#include <xen/hvm/ioreq.h> +#include "hw/xen/xen-hvm-common.h" + +void arch_handle_ioreq(XenIOState *state, ioreq_t *req); +void arch_xen_set_memory(XenIOState *state, + MemoryRegionSection *section, + bool add); +#endif diff --git a/include/hw/xen/arch_hvm.h b/include/hw/xen/arch_hvm.h new file mode 100644 index 0000000..c7c5152 --- /dev/null +++ b/include/hw/xen/arch_hvm.h @@ -0,0 +1,5 @@ +#if defined(TARGET_I386) || defined(TARGET_X86_64) +#include "hw/i386/xen_arch_hvm.h" +#elif defined(TARGET_ARM) || defined(TARGET_ARM_64) +#include "hw/arm/xen_arch_hvm.h" +#endif diff --git a/include/hw/xen/xen-hvm-common.h b/include/hw/xen/xen-hvm-common.h new file mode 100644 index 0000000..f9559e2 --- /dev/null +++ b/include/hw/xen/xen-hvm-common.h @@ -0,0 +1,99 @@ +#ifndef HW_XEN_HVM_COMMON_H +#define HW_XEN_HVM_COMMON_H + +#include "qemu/osdep.h" +#include "qemu/units.h" + +#include "cpu.h" +#include "hw/pci/pci.h" +#include "hw/hw.h" +#include "hw/xen/xen_native.h" +#include "hw/xen/xen-legacy-backend.h" +#include "sysemu/runstate.h" +#include "sysemu/sysemu.h" +#include "sysemu/xen.h" +#include "sysemu/xen-mapcache.h" +#include "qemu/error-report.h" +#include <xen/hvm/ioreq.h> + +extern MemoryRegion ram_memory; +extern MemoryListener xen_io_listener; +extern DeviceListener xen_device_listener; + +//#define DEBUG_XEN_HVM + +#ifdef DEBUG_XEN_HVM +#define DPRINTF(fmt, ...) \ + do { fprintf(stderr, "xen: " fmt, ## __VA_ARGS__); } while (0) +#else +#define DPRINTF(fmt, ...) \ + do { } while (0) +#endif + +static inline uint32_t xen_vcpu_eport(shared_iopage_t *shared_page, int i) +{ + return shared_page->vcpu_ioreq[i].vp_eport; +} +static inline ioreq_t *xen_vcpu_ioreq(shared_iopage_t *shared_page, int vcpu) +{ + return &shared_page->vcpu_ioreq[vcpu]; +} + +#define BUFFER_IO_MAX_DELAY 100 + +typedef struct XenPhysmap { + hwaddr start_addr; + ram_addr_t size; + const char *name; + hwaddr phys_offset; + + QLIST_ENTRY(XenPhysmap) list; +} XenPhysmap; + +typedef struct XenPciDevice { + PCIDevice *pci_dev; + uint32_t sbdf; + QLIST_ENTRY(XenPciDevice) entry; +} XenPciDevice; + +typedef struct XenIOState { + ioservid_t ioservid; + shared_iopage_t *shared_page; + buffered_iopage_t *buffered_io_page; + xenforeignmemory_resource_handle *fres; + QEMUTimer *buffered_io_timer; + CPUState **cpu_by_vcpu_id; + /* the evtchn port for polling the notification, */ + evtchn_port_t *ioreq_local_port; + /* evtchn remote and local ports for buffered io */ + evtchn_port_t bufioreq_remote_port; + evtchn_port_t bufioreq_local_port; + /* the evtchn fd for polling */ + xenevtchn_handle *xce_handle; + /* which vcpu we are serving */ + int send_vcpu; + + struct xs_handle *xenstore; + MemoryListener memory_listener; + MemoryListener io_listener; + QLIST_HEAD(, XenPciDevice) dev_list; + DeviceListener device_listener; + + Notifier exit; +} XenIOState; + +void xen_exit_notifier(Notifier *n, void *data); + +void xen_region_add(MemoryListener *listener, MemoryRegionSection *section); +void xen_region_del(MemoryListener *listener, MemoryRegionSection *section); +void xen_io_add(MemoryListener *listener, MemoryRegionSection *section); +void xen_io_del(MemoryListener *listener, MemoryRegionSection *section); +void xen_device_realize(DeviceListener *listener, DeviceState *dev); +void xen_device_unrealize(DeviceListener *listener, DeviceState *dev); + +void xen_hvm_change_state_handler(void *opaque, bool running, RunState rstate); +void xen_register_ioreq(XenIOState *state, unsigned int max_cpus, + MemoryListener xen_memory_listener); + +void cpu_ioreq_pio(ioreq_t *req); +#endif /* HW_XEN_HVM_COMMON_H */ diff --git a/include/hw/xen/xen_native.h b/include/hw/xen/xen_native.h index f11eb42..4dce905 100644 --- a/include/hw/xen/xen_native.h +++ b/include/hw/xen/xen_native.h @@ -463,8 +463,8 @@ static inline void xen_unmap_pcidev(domid_t dom, PCI_FUNC(pci_dev->devfn)); } -static inline void xen_create_ioreq_server(domid_t dom, - ioservid_t *ioservid) +static inline int xen_create_ioreq_server(domid_t dom, + ioservid_t *ioservid) { int rc = xendevicemodel_create_ioreq_server(xen_dmod, dom, HVM_IOREQSRV_BUFIOREQ_ATOMIC, @@ -472,12 +472,14 @@ static inline void xen_create_ioreq_server(domid_t dom, if (rc == 0) { trace_xen_ioreq_server_create(*ioservid); - return; + return rc; } *ioservid = 0; use_default_ioreq_server = true; trace_xen_default_ioreq_server(); + + return rc; } static inline void xen_destroy_ioreq_server(domid_t dom, diff --git a/meson.build b/meson.build index 34306a6..cfa98e9 100644 --- a/meson.build +++ b/meson.build @@ -136,7 +136,7 @@ endif if cpu in ['x86', 'x86_64', 'arm', 'aarch64'] # i386 emulator provides xenpv machine type for multiple architectures accelerator_targets += { - 'CONFIG_XEN': ['i386-softmmu', 'x86_64-softmmu'], + 'CONFIG_XEN': ['i386-softmmu', 'x86_64-softmmu', 'aarch64-softmmu'], } endif if cpu in ['x86', 'x86_64'] @@ -1726,6 +1726,8 @@ have_xen_pci_passthrough = get_option('xen_pci_passthrough') \ error_message: 'Xen PCI passthrough requested but Xen not enabled') \ .require(targetos == 'linux', error_message: 'Xen PCI passthrough not available on this platform') \ + .require(cpu == 'x86' or cpu == 'x86_64', + error_message: 'Xen PCI passthrough not available on this platform') \ .allowed() diff --git a/tests/qtest/libqtest.c b/tests/qtest/libqtest.c index 77de162..de03ef5 100644 --- a/tests/qtest/libqtest.c +++ b/tests/qtest/libqtest.c @@ -1465,7 +1465,8 @@ void qtest_cb_for_every_machine(void (*cb)(const char *machine), for (i = 0; machines[i].name != NULL; i++) { /* Ignore machines that cannot be used for qtests */ if (!strncmp("xenfv", machines[i].name, 5) || - g_str_equal("xenpv", machines[i].name)) { + g_str_equal("xenpv", machines[i].name) || + g_str_equal("xenpvh", machines[i].name)) { continue; } if (!skip_old_versioned || |