diff options
Diffstat (limited to 'hw/acpi')
| -rw-r--r-- | hw/acpi/Kconfig | 5 | ||||
| -rw-r--r-- | hw/acpi/cpu.c | 43 | ||||
| -rw-r--r-- | hw/acpi/generic_event_device.c | 4 | ||||
| -rw-r--r-- | hw/acpi/ghes-stub.c | 2 | ||||
| -rw-r--r-- | hw/acpi/ghes.c | 242 | ||||
| -rw-r--r-- | hw/acpi/meson.build | 1 | ||||
| -rw-r--r-- | hw/acpi/vmclock.c | 179 |
7 files changed, 362 insertions, 114 deletions
diff --git a/hw/acpi/Kconfig b/hw/acpi/Kconfig index e07d3204eb..1d4e9f0845 100644 --- a/hw/acpi/Kconfig +++ b/hw/acpi/Kconfig @@ -60,6 +60,11 @@ config ACPI_VMGENID default y depends on PC +config ACPI_VMCLOCK + bool + default y + depends on PC + config ACPI_VIOT bool depends on ACPI diff --git a/hw/acpi/cpu.c b/hw/acpi/cpu.c index 9d530a24da..f70a2c045e 100644 --- a/hw/acpi/cpu.c +++ b/hw/acpi/cpu.c @@ -327,6 +327,7 @@ const VMStateDescription vmstate_cpu_hotplug = { #define CPU_EJECT_METHOD "CEJ0" #define CPU_OST_METHOD "COST" #define CPU_ADDED_LIST "CNEW" +#define CPU_EJ_LIST "CEJL" #define CPU_ENABLED "CPEN" #define CPU_SELECTOR "CSEL" @@ -488,7 +489,6 @@ void build_cpus_aml(Aml *table, MachineState *machine, CPUHotplugFeatures opts, method = aml_method(CPU_SCAN_METHOD, 0, AML_SERIALIZED); { const uint8_t max_cpus_per_pass = 255; - Aml *else_ctx; Aml *while_ctx, *while_ctx2; Aml *has_event = aml_local(0); Aml *dev_chk = aml_int(1); @@ -499,6 +499,8 @@ void build_cpus_aml(Aml *table, MachineState *machine, CPUHotplugFeatures opts, Aml *uid = aml_local(3); Aml *has_job = aml_local(4); Aml *new_cpus = aml_name(CPU_ADDED_LIST); + Aml *ej_cpus = aml_name(CPU_EJ_LIST); + Aml *num_ej_cpus = aml_local(5); aml_append(method, aml_acquire(ctrl_lock, 0xFFFF)); @@ -513,6 +515,8 @@ void build_cpus_aml(Aml *table, MachineState *machine, CPUHotplugFeatures opts, */ aml_append(method, aml_name_decl(CPU_ADDED_LIST, aml_package(max_cpus_per_pass))); + aml_append(method, aml_name_decl(CPU_EJ_LIST, + aml_package(max_cpus_per_pass))); aml_append(method, aml_store(zero, uid)); aml_append(method, aml_store(one, has_job)); @@ -527,6 +531,7 @@ void build_cpus_aml(Aml *table, MachineState *machine, CPUHotplugFeatures opts, aml_append(while_ctx2, aml_store(one, has_event)); aml_append(while_ctx2, aml_store(zero, num_added_cpus)); + aml_append(while_ctx2, aml_store(zero, num_ej_cpus)); /* * Scan CPUs, till there are CPUs with events or @@ -559,8 +564,10 @@ void build_cpus_aml(Aml *table, MachineState *machine, CPUHotplugFeatures opts, * if CPU_ADDED_LIST is full, exit inner loop and process * collected CPUs */ - ifctx = aml_if( - aml_equal(num_added_cpus, aml_int(max_cpus_per_pass))); + ifctx = aml_if(aml_lor( + aml_equal(num_added_cpus, aml_int(max_cpus_per_pass)), + aml_equal(num_ej_cpus, aml_int(max_cpus_per_pass)) + )); { aml_append(ifctx, aml_store(one, has_job)); aml_append(ifctx, aml_break()); @@ -577,16 +584,16 @@ void build_cpus_aml(Aml *table, MachineState *machine, CPUHotplugFeatures opts, aml_append(ifctx, aml_store(one, has_event)); } aml_append(while_ctx, ifctx); - else_ctx = aml_else(); + ifctx = aml_if(aml_equal(rm_evt, one)); { - aml_append(ifctx, - aml_call2(CPU_NOTIFY_METHOD, uid, eject_req)); - aml_append(ifctx, aml_store(one, rm_evt)); + /* cache to be removed CPUs to Notify later */ + aml_append(ifctx, aml_store(uid, + aml_index(ej_cpus, num_ej_cpus))); + aml_append(ifctx, aml_increment(num_ej_cpus)); aml_append(ifctx, aml_store(one, has_event)); } - aml_append(else_ctx, ifctx); - aml_append(while_ctx, else_ctx); + aml_append(while_ctx, ifctx); aml_append(while_ctx, aml_increment(uid)); } aml_append(while_ctx2, while_ctx); @@ -620,6 +627,24 @@ void build_cpus_aml(Aml *table, MachineState *machine, CPUHotplugFeatures opts, aml_append(while_ctx, aml_increment(cpu_idx)); } aml_append(while_ctx2, while_ctx); + + /* + * Notify OSPM about to be removed CPUs and clear remove flag + */ + aml_append(while_ctx2, aml_store(zero, cpu_idx)); + while_ctx = aml_while(aml_lless(cpu_idx, num_ej_cpus)); + { + aml_append(while_ctx, + aml_store(aml_derefof(aml_index(ej_cpus, cpu_idx)), + uid)); + aml_append(while_ctx, + aml_call2(CPU_NOTIFY_METHOD, uid, eject_req)); + aml_append(while_ctx, aml_store(uid, cpu_selector)); + aml_append(while_ctx, aml_store(one, rm_evt)); + aml_append(while_ctx, aml_increment(cpu_idx)); + } + aml_append(while_ctx2, while_ctx); + /* * If another batch is needed, then it will resume scanning * exactly at -- and not after -- the last CPU that's currently diff --git a/hw/acpi/generic_event_device.c b/hw/acpi/generic_event_device.c index 58540c0aaf..c85d97ca37 100644 --- a/hw/acpi/generic_event_device.c +++ b/hw/acpi/generic_event_device.c @@ -363,7 +363,7 @@ static const VMStateDescription vmstate_ghes = { .version_id = 1, .minimum_version_id = 1, .fields = (const VMStateField[]) { - VMSTATE_UINT64(ghes_addr_le, AcpiGhesState), + VMSTATE_UINT64(hw_error_le, AcpiGhesState), VMSTATE_END_OF_LIST() }, }; @@ -371,7 +371,7 @@ static const VMStateDescription vmstate_ghes = { static bool ghes_needed(void *opaque) { AcpiGedState *s = opaque; - return s->ghes_state.ghes_addr_le; + return s->ghes_state.hw_error_le; } static const VMStateDescription vmstate_ghes_state = { diff --git a/hw/acpi/ghes-stub.c b/hw/acpi/ghes-stub.c index c315de1802..7cec1812da 100644 --- a/hw/acpi/ghes-stub.c +++ b/hw/acpi/ghes-stub.c @@ -11,7 +11,7 @@ #include "qemu/osdep.h" #include "hw/acpi/ghes.h" -int acpi_ghes_record_errors(uint8_t source_id, uint64_t physical_address) +int acpi_ghes_memory_errors(uint16_t source_id, uint64_t physical_address) { return -1; } diff --git a/hw/acpi/ghes.c b/hw/acpi/ghes.c index e9511d9b8f..b709c177cd 100644 --- a/hw/acpi/ghes.c +++ b/hw/acpi/ghes.c @@ -28,15 +28,12 @@ #include "hw/nvram/fw_cfg.h" #include "qemu/uuid.h" -#define ACPI_GHES_ERRORS_FW_CFG_FILE "etc/hardware_errors" -#define ACPI_GHES_DATA_ADDR_FW_CFG_FILE "etc/hardware_errors_addr" +#define ACPI_HW_ERROR_FW_CFG_FILE "etc/hardware_errors" +#define ACPI_HW_ERROR_ADDR_FW_CFG_FILE "etc/hardware_errors_addr" /* The max size in bytes for one error block */ #define ACPI_GHES_MAX_RAW_DATA_LENGTH (1 * KiB) -/* Now only support ARMv8 SEA notification type error source */ -#define ACPI_GHES_ERROR_SOURCE_COUNT 1 - /* Generic Hardware Error Source version 2 */ #define ACPI_GHES_SOURCE_GENERIC_ERROR_V2 10 @@ -184,51 +181,24 @@ static void acpi_ghes_build_append_mem_cper(GArray *table, build_append_int_noprefix(table, 0, 7); } -static int acpi_ghes_record_mem_error(uint64_t error_block_address, - uint64_t error_physical_addr) +static void +ghes_gen_err_data_uncorrectable_recoverable(GArray *block, + const uint8_t *section_type, + int data_length) { - GArray *block; - - /* Memory Error Section Type */ - const uint8_t uefi_cper_mem_sec[] = - UUID_LE(0xA5BC1114, 0x6F64, 0x4EDE, 0xB8, 0x63, 0x3E, 0x83, \ - 0xED, 0x7C, 0x83, 0xB1); - /* invalid fru id: ACPI 4.0: 17.3.2.6.1 Generic Error Data, * Table 17-13 Generic Error Data Entry */ QemuUUID fru_id = {}; - uint32_t data_length; - - block = g_array_new(false, true /* clear */, 1); - - /* This is the length if adding a new generic error data entry*/ - data_length = ACPI_GHES_DATA_LENGTH + ACPI_GHES_MEM_CPER_LENGTH; - /* - * It should not run out of the preallocated memory if adding a new generic - * error data entry - */ - assert((data_length + ACPI_GHES_GESB_SIZE) <= - ACPI_GHES_MAX_RAW_DATA_LENGTH); /* Build the new generic error status block header */ acpi_ghes_generic_error_status(block, ACPI_GEBS_UNCORRECTABLE, 0, 0, data_length, ACPI_CPER_SEV_RECOVERABLE); /* Build this new generic error data entry header */ - acpi_ghes_generic_error_data(block, uefi_cper_mem_sec, + acpi_ghes_generic_error_data(block, section_type, ACPI_CPER_SEV_RECOVERABLE, 0, 0, ACPI_GHES_MEM_CPER_LENGTH, fru_id, 0); - - /* Build the memory section CPER for above new generic error data entry */ - acpi_ghes_build_append_mem_cper(block, error_physical_addr); - - /* Write the generic error data entry into guest memory */ - cpu_physical_memory_write(error_block_address, block->data, block->len); - - g_array_free(block, true); - - return 0; } /* @@ -236,7 +206,7 @@ static int acpi_ghes_record_mem_error(uint64_t error_block_address, * Initialize "etc/hardware_errors" and "etc/hardware_errors_addr" fw_cfg blobs. * See docs/specs/acpi_hest_ghes.rst for blobs format. */ -void build_ghes_error_table(GArray *hardware_errors, BIOSLinker *linker) +static void build_ghes_error_table(GArray *hardware_errors, BIOSLinker *linker) { int i, error_status_block_offset; @@ -264,7 +234,7 @@ void build_ghes_error_table(GArray *hardware_errors, BIOSLinker *linker) ACPI_GHES_MAX_RAW_DATA_LENGTH * ACPI_GHES_ERROR_SOURCE_COUNT); /* Tell guest firmware to place hardware_errors blob into RAM */ - bios_linker_loader_alloc(linker, ACPI_GHES_ERRORS_FW_CFG_FILE, + bios_linker_loader_alloc(linker, ACPI_HW_ERROR_FW_CFG_FILE, hardware_errors, sizeof(uint64_t), false); for (i = 0; i < ACPI_GHES_ERROR_SOURCE_COUNT; i++) { @@ -273,23 +243,31 @@ void build_ghes_error_table(GArray *hardware_errors, BIOSLinker *linker) * corresponding "Generic Error Status Block" */ bios_linker_loader_add_pointer(linker, - ACPI_GHES_ERRORS_FW_CFG_FILE, sizeof(uint64_t) * i, - sizeof(uint64_t), ACPI_GHES_ERRORS_FW_CFG_FILE, - error_status_block_offset + i * ACPI_GHES_MAX_RAW_DATA_LENGTH); + ACPI_HW_ERROR_FW_CFG_FILE, + sizeof(uint64_t) * i, + sizeof(uint64_t), + ACPI_HW_ERROR_FW_CFG_FILE, + error_status_block_offset + + i * ACPI_GHES_MAX_RAW_DATA_LENGTH); } /* * tell firmware to write hardware_errors GPA into * hardware_errors_addr fw_cfg, once the former has been initialized. */ - bios_linker_loader_write_pointer(linker, ACPI_GHES_DATA_ADDR_FW_CFG_FILE, - 0, sizeof(uint64_t), ACPI_GHES_ERRORS_FW_CFG_FILE, 0); + bios_linker_loader_write_pointer(linker, ACPI_HW_ERROR_ADDR_FW_CFG_FILE, 0, + sizeof(uint64_t), + ACPI_HW_ERROR_FW_CFG_FILE, 0); } /* Build Generic Hardware Error Source version 2 (GHESv2) */ -static void build_ghes_v2(GArray *table_data, int source_id, BIOSLinker *linker) +static void build_ghes_v2(GArray *table_data, + BIOSLinker *linker, + enum AcpiGhesNotifyType notify, + uint16_t source_id) { uint64_t address_offset; + /* * Type: * Generic Hardware Error Source version 2(GHESv2 - Type 10) @@ -316,21 +294,13 @@ static void build_ghes_v2(GArray *table_data, int source_id, BIOSLinker *linker) build_append_gas(table_data, AML_AS_SYSTEM_MEMORY, 0x40, 0, 4 /* QWord access */, 0); bios_linker_loader_add_pointer(linker, ACPI_BUILD_TABLE_FILE, - address_offset + GAS_ADDR_OFFSET, sizeof(uint64_t), - ACPI_GHES_ERRORS_FW_CFG_FILE, source_id * sizeof(uint64_t)); + address_offset + GAS_ADDR_OFFSET, + sizeof(uint64_t), + ACPI_HW_ERROR_FW_CFG_FILE, + source_id * sizeof(uint64_t)); - switch (source_id) { - case ACPI_HEST_SRC_ID_SEA: - /* - * Notification Structure - * Now only enable ARMv8 SEA notification type - */ - build_ghes_hw_error_notification(table_data, ACPI_GHES_NOTIFY_SEA); - break; - default: - error_report("Not support this error source"); - abort(); - } + /* Notification Structure */ + build_ghes_hw_error_notification(table_data, notify); /* Error Status Block Length */ build_append_int_noprefix(table_data, ACPI_GHES_MAX_RAW_DATA_LENGTH, 4); @@ -344,9 +314,11 @@ static void build_ghes_v2(GArray *table_data, int source_id, BIOSLinker *linker) build_append_gas(table_data, AML_AS_SYSTEM_MEMORY, 0x40, 0, 4 /* QWord access */, 0); bios_linker_loader_add_pointer(linker, ACPI_BUILD_TABLE_FILE, - address_offset + GAS_ADDR_OFFSET, - sizeof(uint64_t), ACPI_GHES_ERRORS_FW_CFG_FILE, - (ACPI_GHES_ERROR_SOURCE_COUNT + source_id) * sizeof(uint64_t)); + address_offset + GAS_ADDR_OFFSET, + sizeof(uint64_t), + ACPI_HW_ERROR_FW_CFG_FILE, + (ACPI_GHES_ERROR_SOURCE_COUNT + source_id) + * sizeof(uint64_t)); /* * Read Ack Preserve field @@ -359,17 +331,21 @@ static void build_ghes_v2(GArray *table_data, int source_id, BIOSLinker *linker) } /* Build Hardware Error Source Table */ -void acpi_build_hest(GArray *table_data, BIOSLinker *linker, +void acpi_build_hest(GArray *table_data, GArray *hardware_errors, + BIOSLinker *linker, const char *oem_id, const char *oem_table_id) { AcpiTable table = { .sig = "HEST", .rev = 1, .oem_id = oem_id, .oem_table_id = oem_table_id }; + build_ghes_error_table(hardware_errors, linker); + acpi_table_begin(&table, table_data); /* Error Source Count */ build_append_int_noprefix(table_data, ACPI_GHES_ERROR_SOURCE_COUNT, 4); - build_ghes_v2(table_data, ACPI_HEST_SRC_ID_SEA, linker); + build_ghes_v2(table_data, linker, + ACPI_GHES_NOTIFY_SEA, ACPI_HEST_SRC_ID_SEA); acpi_table_end(linker, &table); } @@ -378,70 +354,132 @@ void acpi_ghes_add_fw_cfg(AcpiGhesState *ags, FWCfgState *s, GArray *hardware_error) { /* Create a read-only fw_cfg file for GHES */ - fw_cfg_add_file(s, ACPI_GHES_ERRORS_FW_CFG_FILE, hardware_error->data, + fw_cfg_add_file(s, ACPI_HW_ERROR_FW_CFG_FILE, hardware_error->data, hardware_error->len); /* Create a read-write fw_cfg file for Address */ - fw_cfg_add_file_callback(s, ACPI_GHES_DATA_ADDR_FW_CFG_FILE, NULL, NULL, - NULL, &(ags->ghes_addr_le), sizeof(ags->ghes_addr_le), false); + fw_cfg_add_file_callback(s, ACPI_HW_ERROR_ADDR_FW_CFG_FILE, NULL, NULL, + NULL, &(ags->hw_error_le), sizeof(ags->hw_error_le), false); ags->present = true; } -int acpi_ghes_record_errors(uint8_t source_id, uint64_t physical_address) +static void get_hw_error_offsets(uint64_t ghes_addr, + uint64_t *cper_addr, + uint64_t *read_ack_register_addr) { - uint64_t error_block_addr, read_ack_register_addr, read_ack_register = 0; - uint64_t start_addr; - bool ret = -1; + if (!ghes_addr) { + return; + } + + /* + * non-HEST version supports only one source, so no need to change + * the start offset based on the source ID. Also, we can't validate + * the source ID, as it is stored inside the HEST table. + */ + + cpu_physical_memory_read(ghes_addr, cper_addr, + sizeof(*cper_addr)); + + *cper_addr = le64_to_cpu(*cper_addr); + + /* + * As the current version supports only one source, the ack offset is + * just sizeof(uint64_t). + */ + *read_ack_register_addr = ghes_addr + sizeof(uint64_t); +} + +void ghes_record_cper_errors(const void *cper, size_t len, + uint16_t source_id, Error **errp) +{ + uint64_t cper_addr = 0, read_ack_register_addr = 0, read_ack_register; AcpiGedState *acpi_ged_state; AcpiGhesState *ags; - assert(source_id < ACPI_HEST_SRC_ID_RESERVED); + if (len > ACPI_GHES_MAX_RAW_DATA_LENGTH) { + error_setg(errp, "GHES CPER record is too big: %zd", len); + return; + } acpi_ged_state = ACPI_GED(object_resolve_path_type("", TYPE_ACPI_GED, NULL)); - g_assert(acpi_ged_state); + if (!acpi_ged_state) { + error_setg(errp, "Can't find ACPI_GED object"); + return; + } ags = &acpi_ged_state->ghes_state; - start_addr = le64_to_cpu(ags->ghes_addr_le); + assert(ACPI_GHES_ERROR_SOURCE_COUNT == 1); + get_hw_error_offsets(le64_to_cpu(ags->hw_error_le), + &cper_addr, &read_ack_register_addr); + + if (!cper_addr) { + error_setg(errp, "can not find Generic Error Status Block"); + return; + } + + cpu_physical_memory_read(read_ack_register_addr, + &read_ack_register, sizeof(read_ack_register)); + + /* zero means OSPM does not acknowledge the error */ + if (!read_ack_register) { + error_setg(errp, + "OSPM does not acknowledge previous error," + " so can not record CPER for current error anymore"); + return; + } + + read_ack_register = cpu_to_le64(0); + /* + * Clear the Read Ack Register, OSPM will write 1 to this register when + * it acknowledges the error. + */ + cpu_physical_memory_write(read_ack_register_addr, + &read_ack_register, sizeof(uint64_t)); + + /* Write the generic error data entry into guest memory */ + cpu_physical_memory_write(cper_addr, cper, len); + + return; +} - if (physical_address) { +int acpi_ghes_memory_errors(uint16_t source_id, uint64_t physical_address) +{ + /* Memory Error Section Type */ + const uint8_t guid[] = + UUID_LE(0xA5BC1114, 0x6F64, 0x4EDE, 0xB8, 0x63, 0x3E, 0x83, \ + 0xED, 0x7C, 0x83, 0xB1); + Error *errp = NULL; + int data_length; + GArray *block; - if (source_id < ACPI_HEST_SRC_ID_RESERVED) { - start_addr += source_id * sizeof(uint64_t); - } + block = g_array_new(false, true /* clear */, 1); - cpu_physical_memory_read(start_addr, &error_block_addr, - sizeof(error_block_addr)); + data_length = ACPI_GHES_DATA_LENGTH + ACPI_GHES_MEM_CPER_LENGTH; + /* + * It should not run out of the preallocated memory if adding a new generic + * error data entry + */ + assert((data_length + ACPI_GHES_GESB_SIZE) <= + ACPI_GHES_MAX_RAW_DATA_LENGTH); - error_block_addr = le64_to_cpu(error_block_addr); + ghes_gen_err_data_uncorrectable_recoverable(block, guid, data_length); - read_ack_register_addr = start_addr + - ACPI_GHES_ERROR_SOURCE_COUNT * sizeof(uint64_t); + /* Build the memory section CPER for above new generic error data entry */ + acpi_ghes_build_append_mem_cper(block, physical_address); - cpu_physical_memory_read(read_ack_register_addr, - &read_ack_register, sizeof(read_ack_register)); + /* Report the error */ + ghes_record_cper_errors(block->data, block->len, source_id, &errp); - /* zero means OSPM does not acknowledge the error */ - if (!read_ack_register) { - error_report("OSPM does not acknowledge previous error," - " so can not record CPER for current error anymore"); - } else if (error_block_addr) { - read_ack_register = cpu_to_le64(0); - /* - * Clear the Read Ack Register, OSPM will write it to 1 when - * it acknowledges this error. - */ - cpu_physical_memory_write(read_ack_register_addr, - &read_ack_register, sizeof(uint64_t)); + g_array_free(block, true); - ret = acpi_ghes_record_mem_error(error_block_addr, - physical_address); - } else - error_report("can not find Generic Error Status Block"); + if (errp) { + error_report_err(errp); + return -1; } - return ret; + return 0; } bool acpi_ghes_present(void) diff --git a/hw/acpi/meson.build b/hw/acpi/meson.build index c8854f4d48..73f02b9691 100644 --- a/hw/acpi/meson.build +++ b/hw/acpi/meson.build @@ -15,6 +15,7 @@ acpi_ss.add(when: 'CONFIG_ACPI_NVDIMM', if_false: files('acpi-nvdimm-stub.c')) acpi_ss.add(when: 'CONFIG_ACPI_PCI', if_true: files('pci.c')) acpi_ss.add(when: 'CONFIG_ACPI_CXL', if_true: files('cxl.c'), if_false: files('cxl-stub.c')) acpi_ss.add(when: 'CONFIG_ACPI_VMGENID', if_true: files('vmgenid.c')) +acpi_ss.add(when: 'CONFIG_ACPI_VMCLOCK', if_true: files('vmclock.c')) acpi_ss.add(when: 'CONFIG_ACPI_HW_REDUCED', if_true: files('generic_event_device.c')) acpi_ss.add(when: 'CONFIG_ACPI_HMAT', if_true: files('hmat.c')) acpi_ss.add(when: 'CONFIG_ACPI_APEI', if_true: files('ghes.c'), if_false: files('ghes-stub.c')) diff --git a/hw/acpi/vmclock.c b/hw/acpi/vmclock.c new file mode 100644 index 0000000000..7387e5c9ca --- /dev/null +++ b/hw/acpi/vmclock.c @@ -0,0 +1,179 @@ +/* + * Virtual Machine Clock Device + * + * Copyright © 2024 Amazon.com, Inc. or its affiliates. All Rights Reserved. + * + * Authors: David Woodhouse <dwmw2@infradead.org> + * + * 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 "qapi/error.h" +#include "qemu/module.h" +#include "hw/i386/e820_memory_layout.h" +#include "hw/acpi/acpi.h" +#include "hw/acpi/aml-build.h" +#include "hw/acpi/vmclock.h" +#include "hw/nvram/fw_cfg.h" +#include "hw/qdev-properties.h" +#include "hw/qdev-properties-system.h" +#include "migration/vmstate.h" +#include "system/reset.h" + +#include "standard-headers/linux/vmclock-abi.h" + +void vmclock_build_acpi(VmclockState *vms, GArray *table_data, + BIOSLinker *linker, const char *oem_id) +{ + Aml *ssdt, *dev, *scope, *crs; + AcpiTable table = { .sig = "SSDT", .rev = 1, + .oem_id = oem_id, .oem_table_id = "VMCLOCK" }; + + /* Put VMCLOCK into a separate SSDT table */ + acpi_table_begin(&table, table_data); + ssdt = init_aml_allocator(); + + scope = aml_scope("\\_SB"); + dev = aml_device("VCLK"); + aml_append(dev, aml_name_decl("_HID", aml_string("AMZNC10C"))); + aml_append(dev, aml_name_decl("_CID", aml_string("VMCLOCK"))); + aml_append(dev, aml_name_decl("_DDN", aml_string("VMCLOCK"))); + + /* Simple status method */ + aml_append(dev, aml_name_decl("_STA", aml_int(0xf))); + + crs = aml_resource_template(); + aml_append(crs, aml_qword_memory(AML_POS_DECODE, + AML_MIN_FIXED, AML_MAX_FIXED, + AML_CACHEABLE, AML_READ_ONLY, + 0xffffffffffffffffULL, + vms->physaddr, + vms->physaddr + VMCLOCK_SIZE - 1, + 0, VMCLOCK_SIZE)); + aml_append(dev, aml_name_decl("_CRS", crs)); + aml_append(scope, dev); + aml_append(ssdt, scope); + + g_array_append_vals(table_data, ssdt->buf->data, ssdt->buf->len); + acpi_table_end(linker, &table); + free_aml_allocator(); +} + +static void vmclock_update_guest(VmclockState *vms) +{ + uint64_t disruption_marker; + uint32_t seq_count; + + if (!vms->clk) { + return; + } + + seq_count = le32_to_cpu(vms->clk->seq_count) | 1; + vms->clk->seq_count = cpu_to_le32(seq_count); + /* These barriers pair with read barriers in the guest */ + smp_wmb(); + + disruption_marker = le64_to_cpu(vms->clk->disruption_marker); + disruption_marker++; + vms->clk->disruption_marker = cpu_to_le64(disruption_marker); + + /* These barriers pair with read barriers in the guest */ + smp_wmb(); + vms->clk->seq_count = cpu_to_le32(seq_count + 1); +} + +/* + * After restoring an image, we need to update the guest memory to notify + * it of clock disruption. + */ +static int vmclock_post_load(void *opaque, int version_id) +{ + VmclockState *vms = opaque; + + vmclock_update_guest(vms); + return 0; +} + +static const VMStateDescription vmstate_vmclock = { + .name = "vmclock", + .version_id = 1, + .minimum_version_id = 1, + .post_load = vmclock_post_load, + .fields = (const VMStateField[]) { + VMSTATE_UINT64(physaddr, VmclockState), + VMSTATE_END_OF_LIST() + }, +}; + +static void vmclock_handle_reset(void *opaque) +{ + VmclockState *vms = VMCLOCK(opaque); + + if (!memory_region_is_mapped(&vms->clk_page)) { + memory_region_add_subregion_overlap(get_system_memory(), + vms->physaddr, + &vms->clk_page, 0); + } +} + +static void vmclock_realize(DeviceState *dev, Error **errp) +{ + VmclockState *vms = VMCLOCK(dev); + + /* + * Given that this function is executing, there is at least one VMCLOCK + * device. Check if there are several. + */ + if (!find_vmclock_dev()) { + error_setg(errp, "at most one %s device is permitted", TYPE_VMCLOCK); + return; + } + + vms->physaddr = VMCLOCK_ADDR; + + e820_add_entry(vms->physaddr, VMCLOCK_SIZE, E820_RESERVED); + + memory_region_init_ram(&vms->clk_page, OBJECT(dev), "vmclock_page", + VMCLOCK_SIZE, &error_abort); + memory_region_set_enabled(&vms->clk_page, true); + vms->clk = memory_region_get_ram_ptr(&vms->clk_page); + memset(vms->clk, 0, VMCLOCK_SIZE); + + vms->clk->magic = cpu_to_le32(VMCLOCK_MAGIC); + vms->clk->size = cpu_to_le16(VMCLOCK_SIZE); + vms->clk->version = cpu_to_le16(1); + + /* These are all zero and thus default, but be explicit */ + vms->clk->clock_status = VMCLOCK_STATUS_UNKNOWN; + vms->clk->counter_id = VMCLOCK_COUNTER_INVALID; + + qemu_register_reset(vmclock_handle_reset, vms); + + vmclock_update_guest(vms); +} + +static void vmclock_device_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->vmsd = &vmstate_vmclock; + dc->realize = vmclock_realize; + dc->hotpluggable = false; + set_bit(DEVICE_CATEGORY_MISC, dc->categories); +} + +static const TypeInfo vmclock_device_info = { + .name = TYPE_VMCLOCK, + .parent = TYPE_DEVICE, + .instance_size = sizeof(VmclockState), + .class_init = vmclock_device_class_init, +}; + +static void vmclock_register_types(void) +{ + type_register_static(&vmclock_device_info); +} + +type_init(vmclock_register_types) |