In the ARMv8 platform, the CPU error type are synchronous external abort(SEA) and SError Interrupt (SEI). If exception happens to guest, sometimes guest itself do the recovery is better, because host does not know guest's detailed information. For example, if a guest user-space application happen exception, host does not which application encounter errors. For the ARMv8 SEA/SEI, KVM or host kernel delivers SIGBUS to notify user space. After user space gets the notification, it will record the CPER to guest GHES buffer for guest and inject a exception or IRQ to guest. In the current implement, if the SIGBUS is BUS_MCEERR_AR, we will treat it as synchronous exception, and use ARMv8 SEA notification type to notify guest after recording CPER for guest; This series patches are based on Qemu 4.0, which have two parts: 1. Generate APEI/GHES table. 2. Handle the SIGBUS signal, record the CPER in runtime and fill into guest memory, then according to SIGBUS type to notify guest. Whole solution was suggested by James(james.morse@arm.com); APEI part solution is suggested by Laszlo(lersek@redhat.com). Shown some discussion in [1]. This series patches have already tested on ARM64 platform with RAS feature enabled: Show the APEI part verification result in [2] Show the BUS_MCEERR_AR SIGBUS handling verification result in [3] --- Change since v15: 1. Add a doc-comment in the proper format for 'include/exec/ram_addr.h' 2. Remove write_part_cpustate_to_list() because there is another bug fix patch has been merged "arm: Allow system registers for KVM guests to be changed by QEMU code" 3. Add some comments for kvm_inject_arm_sea() in 'target/arm/kvm64.c' 4. Compare the arm_current_el() return value to 0,1,2,3, not to PSTATE_MODE_* constants. 5. Change the RAS support wasn't introduced before 4.1 QEMU version. 6. Move the no_ras flag patch to begin in this series Change since v14: 1. Remove the BUS_MCEERR_AO handling logic because this asynchronous signal was masked by main thread 2. Address some Igor Mammedov's comments(ACPI part) 1) change the comments for the enum AcpiHestNotifyType definition and remove ditto in patch 1 2) change some patch commit messages and separate "APEI GHES table generation" patch to more patches. 3. Address some peter's comments(arm64 Synchronous External Abort injection) 1) change some code notes 2) using arm_current_el() for current EL 2) use the helper functions for those (syn_data_abort_*). Change since v13: 1. Move the patches that set guest ESR and inject virtual SError out of this series 2. Clean and optimize the APEI part patches 3. Update the commit messages and add some comments for the code Change since v12: 1. Address Paolo's comments to move HWPoisonPage definition to accel/kvm/kvm-all.c 2. Only call kvm_cpu_synchronize_state() when get the BUS_MCEERR_AR signal 3. Only add and enable GPIO-Signal and ARMv8 SEA two hardware error sources 4. Address Michael's comments to not sync SPDX from Linux kernel header file Change since v11: Address James's comments(james.morse@arm.com) 1. Check whether KVM has the capability to to set ESR instead of detecting host CPU RAS capability 2. For SIGBUS_MCEERR_AR SIGBUS, use Synchronous-External-Abort(SEA) notification type for SIGBUS_MCEERR_AO SIGBUS, use GPIO-Signal notification Address Shannon's comments(for ACPI part): 1. Unify hest_ghes.c and hest_ghes.h license declaration 2. Remove unnecessary including "qmp-commands.h" in hest_ghes.c 3. Unconditionally add guest APEI table based on James's comments(james.morse@arm.com) 4. Add a option to virt machine for migration compatibility. On new virt machine it's on by default while off for old ones, we enabled it since 2.12 5. Refer to the ACPI spec version which introduces Hardware Error Notification first time 6. Add ACPI_HEST_NOTIFY_RESERVED notification type Address Igor's comments(for ACPI part): 1. Add doc patch first which will describe how it's supposed to work between QEMU/firmware/guest OS with expected flows. 2. Move APEI diagrams into doc/spec patch 3. Remove redundant g_malloc in ghes_record_cper() 4. Use build_append_int_noprefix() API to compose whole error status block and whole APEI table, and try to get rid of most structures in patch 1, as they will be left unused after that 5. Reuse something like https://github.com/imammedo/qemu/commit/3d2fd6d13a3ea298d2ee814835495ce6241d085c to build GAS 6. Remove much offsetof() in the function 7. Build independent tables first and only then build dependent tables passing to it pointers to previously build table if necessary. 8. Redefine macro GHES_ACPI_HEST_NOTIFY_RESERVED to ACPI_HEST_ERROR_SOURCE_COUNT to avoid confusion Address Peter Maydell's comments 1. linux-headers is done as a patch of their own created using scripts/update-linux-headers.sh run against a mainline kernel tree 2. Tested whether this patchset builds OK on aarch32 3. Abstract Hwpoison page adding code out properly into a cpu-independent source file from target/i386/kvm.c, such as kvm-all.c 4. Add doc-comment formatted documentation comment for new globally-visible function prototype in a header --- [1]: https://lkml.org/lkml/2017/2/27/246 https://patchwork.kernel.org/patch/9633105/ https://patchwork.kernel.org/patch/9925227/ [2]: Note: the UEFI(QEMU_EFI.fd) is needed if guest want to use ACPI table. After guest boot up, dump the APEI table, then can see the initialized table (1) # iasl -p ./HEST -d /sys/firmware/acpi/tables/HEST (2) # cat HEST.dsl /* * Intel ACPI Component Architecture * AML/ASL+ Disassembler version 20170728 (64-bit version) * Copyright (c) 2000 - 2017 Intel Corporation * * Disassembly of /sys/firmware/acpi/tables/HEST, Mon Sep 5 07:59:17 2016 * * ACPI Data Table [HEST] * * Format: [HexOffset DecimalOffset ByteLength] FieldName : FieldValue */ .................................................................................. [308h 0776 2] Subtable Type : 000A [Generic Hardware Error Source V2] [30Ah 0778 2] Source Id : 0001 [30Ch 0780 2] Related Source Id : FFFF [30Eh 0782 1] Reserved : 00 [30Fh 0783 1] Enabled : 01 [310h 0784 4] Records To Preallocate : 00000001 [314h 0788 4] Max Sections Per Record : 00000001 [318h 0792 4] Max Raw Data Length : 00001000 [31Ch 0796 12] Error Status Address : [Generic Address Structure] [31Ch 0796 1] Space ID : 00 [SystemMemory] [31Dh 0797 1] Bit Width : 40 [31Eh 0798 1] Bit Offset : 00 [31Fh 0799 1] Encoded Access Width : 04 [QWord Access:64] [320h 0800 8] Address : 00000000785D0040 [328h 0808 28] Notify : [Hardware Error Notification Structure] [328h 0808 1] Notify Type : 08 [SEA] [329h 0809 1] Notify Length : 1C [32Ah 0810 2] Configuration Write Enable : 0000 [32Ch 0812 4] PollInterval : 00000000 [330h 0816 4] Vector : 00000000 [334h 0820 4] Polling Threshold Value : 00000000 [338h 0824 4] Polling Threshold Window : 00000000 [33Ch 0828 4] Error Threshold Value : 00000000 [340h 0832 4] Error Threshold Window : 00000000 [344h 0836 4] Error Status Block Length : 00001000 [348h 0840 12] Read Ack Register : [Generic Address Structure] [348h 0840 1] Space ID : 00 [SystemMemory] [349h 0841 1] Bit Width : 40 [34Ah 0842 1] Bit Offset : 00 [34Bh 0843 1] Encoded Access Width : 04 [QWord Access:64] [34Ch 0844 8] Address : 00000000785D0098 [354h 0852 8] Read Ack Preserve : 00000000FFFFFFFE [35Ch 0860 8] Read Ack Write : 0000000000000001 ..................................................................................... (3) After a synchronous external abort(SEA) happen, Qemu receive a SIGBUS and filled the CPER into guest GHES memory. For example, according to above table, the address that contains the physical address of a block of memory that holds the error status data for this abort is 0x00000000785D0040 (4) the address for SEA notification error source is 0x785d80b0 (qemu) xp /1 0x00000000785D0040 00000000785d0040: 0x785d80b0 (5) check the content of generic error status block and generic error data entry (qemu) xp /100x 0x785d80b0 00000000785d80b0: 0x00000001 0x00000000 0x00000000 0x00000098 00000000785d80c0: 0x00000000 0xa5bc1114 0x4ede6f64 0x833e63b8 00000000785d80d0: 0xb1837ced 0x00000000 0x00000300 0x00000050 00000000785d80e0: 0x00000000 0x00000000 0x00000000 0x00000000 00000000785d80f0: 0x00000000 0x00000000 0x00000000 0x00000000 00000000785d8100: 0x00000000 0x00000000 0x00000000 0x00004002 (6) check the OSPM's ACK value(for example SEA) /* Before OSPM acknowledges the error, check the ACK value */ (qemu) xp /1 0x00000000785D0098 00000000785d00f0: 0x00000000 /* After OSPM acknowledges the error, check the ACK value, it change to 1 from 0 */ (qemu) xp /1 0x00000000785D0098 00000000785d00f0: 0x00000001 [3]: KVM deliver "BUS_MCEERR_AR" to Qemu, Qemu record the guest CPER and inject synchronous external abort to notify guest, then guest do the recovery. [ 1552.516170] Synchronous External Abort: synchronous external abort (0x92000410) at 0x000000003751c6b4 [ 1553.074073] {1}[Hardware Error]: Hardware error from APEI Generic Hardware Error Source: 8 [ 1553.081654] {1}[Hardware Error]: event severity: recoverable [ 1554.034191] {1}[Hardware Error]: Error 0, type: recoverable [ 1554.037934] {1}[Hardware Error]: section_type: memory error [ 1554.513261] {1}[Hardware Error]: physical_address: 0x0000000040fa6000 [ 1554.513944] {1}[Hardware Error]: error_type: 0, unknown [ 1555.041451] Memory failure: 0x40fa6: Killing mca-recover:1296 due to hardware memory corruption [ 1555.373116] Memory failure: 0x40fa6: recovery action for dirty LRU page: Recovered Dongjiu Geng (10): hw/arm/virt: Add RAS platform version for migration ACPI: add some GHES structures and macros definition acpi: add build_append_ghes_notify() helper for Hardware Error Notification acpi: add build_append_ghes_generic_data() helper for Generic Error Data Entry acpi: add build_append_ghes_generic_status() helper for Generic Error Status Block docs: APEI GHES generation and CPER record description ACPI: Add APEI GHES table generation support KVM: Move related hwpoison page functions to accel/kvm/ folder target-arm: kvm64: inject synchronous External Abort target-arm: kvm64: handle SIGBUS signal from kernel or KVM accel/kvm/kvm-all.c | 33 ++++ default-configs/arm-softmmu.mak | 1 + docs/specs/acpi_hest_ghes.txt | 97 +++++++++++ hw/acpi/Kconfig | 4 + hw/acpi/Makefile.objs | 1 + hw/acpi/acpi_ghes.c | 348 ++++++++++++++++++++++++++++++++++++++++ hw/acpi/aml-build.c | 70 ++++++++ hw/arm/virt-acpi-build.c | 12 ++ hw/arm/virt.c | 6 + include/exec/ram_addr.h | 24 +++ include/hw/acpi/acpi-defs.h | 52 ++++++ include/hw/acpi/acpi_ghes.h | 83 ++++++++++ include/hw/acpi/aml-build.h | 21 +++ include/hw/arm/virt.h | 1 + include/sysemu/kvm.h | 2 +- target/arm/internals.h | 5 +- target/arm/kvm.c | 3 + target/arm/kvm64.c | 74 +++++++++ target/arm/op_helper.c | 2 +- target/i386/kvm.c | 34 +--- 20 files changed, 836 insertions(+), 37 deletions(-) create mode 100644 docs/specs/acpi_hest_ghes.txt create mode 100644 hw/acpi/acpi_ghes.c create mode 100644 include/hw/acpi/acpi_ghes.h -- 1.8.3.1 Support this feature since version 4.1, disable it by default in the old version. Signed-off-by: Dongjiu Geng <gengdongjiu@huawei.com> --- hw/arm/virt.c | 6 ++++++ include/hw/arm/virt.h | 1 + 2 files changed, 7 insertions(+) diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ DEFINE_VIRT_MACHINE_AS_LATEST(4, 1) static void virt_machine_4_0_options(MachineClass *mc) { + VirtMachineClass *vmc = VIRT_MACHINE_CLASS(OBJECT_CLASS(mc)); + virt_machine_4_1_options(mc); compat_props_add(mc->compat_props, hw_compat_4_0, hw_compat_4_0_len); + /* Disable memory recovery feature for 4.0 as RAS support was + * introduced with 4.1. + */ + vmc->no_ras = true; } DEFINE_VIRT_MACHINE(4, 0) diff --git a/include/hw/arm/virt.h b/include/hw/arm/virt.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/virt.h +++ b/include/hw/arm/virt.h @@ -XXX,XX +XXX,XX @@ typedef struct { bool disallow_affinity_adjustment; bool no_its; bool no_pmu; + bool no_ras; bool claim_edge_triggered_timers; bool smbios_old_sys_ver; bool no_highmem_ecam; -- 1.8.3.1 Add Generic Error Status Block structures and some macros definitions, which is referred to the ACPI 4.0 or ACPI 6.2. The HEST table generation and CPER record will use them. Signed-off-by: Dongjiu Geng <gengdongjiu@huawei.com> --- include/hw/acpi/acpi-defs.h | 52 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 52 insertions(+) diff --git a/include/hw/acpi/acpi-defs.h b/include/hw/acpi/acpi-defs.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/acpi/acpi-defs.h +++ b/include/hw/acpi/acpi-defs.h @@ -XXX,XX +XXX,XX @@ typedef struct AcpiMultipleApicTable AcpiMultipleApicTable; #define ACPI_APIC_RESERVED 16 /* 16 and greater are reserved */ /* + * Values for Hardware Error Notification Type field + */ +enum AcpiHestNotifyType { + ACPI_HEST_NOTIFY_POLLED = 0, + ACPI_HEST_NOTIFY_EXTERNAL = 1, + ACPI_HEST_NOTIFY_LOCAL = 2, + ACPI_HEST_NOTIFY_SCI = 3, + ACPI_HEST_NOTIFY_NMI = 4, + ACPI_HEST_NOTIFY_CMCI = 5, /* ACPI 5.0: 18.3.2.7, Table 18-290 */ + ACPI_HEST_NOTIFY_MCE = 6, /* ACPI 5.0: 18.3.2.7, Table 18-290 */ + ACPI_HEST_NOTIFY_GPIO = 7, /* ACPI 6.0: 18.3.2.7, Table 18-332 */ + ACPI_HEST_NOTIFY_SEA = 8, /* ACPI 6.1: 18.3.2.9, Table 18-345 */ + ACPI_HEST_NOTIFY_SEI = 9, /* ACPI 6.1: 18.3.2.9, Table 18-345 */ + ACPI_HEST_NOTIFY_GSIV = 10, /* ACPI 6.1: 18.3.2.9, Table 18-345 */ + ACPI_HEST_NOTIFY_SDEI = 11, /* ACPI 6.2: 18.3.2.9, Table 18-383 */ + ACPI_HEST_NOTIFY_RESERVED = 12 /* 12 and greater are reserved */ +}; + +/* * MADT sub-structures (Follow MULTIPLE_APIC_DESCRIPTION_TABLE) */ #define ACPI_SUB_HEADER_DEF /* Common ACPI sub-structure header */\ @@ -XXX,XX +XXX,XX @@ struct AcpiSystemResourceAffinityTable { } QEMU_PACKED; typedef struct AcpiSystemResourceAffinityTable AcpiSystemResourceAffinityTable; +/* + * Generic Error Status Block + */ +struct AcpiGenericErrorStatus { + /* It is a bitmask composed of ACPI_GEBS_xxx macros */ + uint32_t block_status; + uint32_t raw_data_offset; + uint32_t raw_data_length; + uint32_t data_length; + uint32_t error_severity; +} QEMU_PACKED; +typedef struct AcpiGenericErrorStatus AcpiGenericErrorStatus; + +/* + * Masks for block_status flags above + */ +#define ACPI_GEBS_UNCORRECTABLE 1 + +/* + * Values for error_severity field above + */ +enum AcpiGenericErrorSeverity { + ACPI_CPER_SEV_RECOVERABLE, + ACPI_CPER_SEV_FATAL, + ACPI_CPER_SEV_CORRECTED, + ACPI_CPER_SEV_NONE, +}; + +/* + * Generic Hardware Error Source version 2 + */ +#define ACPI_HEST_SOURCE_GENERIC_ERROR_V2 10 + #define ACPI_SRAT_PROCESSOR_APIC 0 #define ACPI_SRAT_MEMORY 1 #define ACPI_SRAT_PROCESSOR_x2APIC 2 -- 1.8.3.1 It will help to add Hardware Error Notification to ACPI tables without using packed C structures and avoid endianness issues as API doesn't need explicit conversion. Signed-off-by: Dongjiu Geng <gengdongjiu@huawei.com> --- hw/acpi/aml-build.c | 22 ++++++++++++++++++++++ include/hw/acpi/aml-build.h | 8 ++++++++ 2 files changed, 30 insertions(+) diff --git a/hw/acpi/aml-build.c b/hw/acpi/aml-build.c index XXXXXXX..XXXXXXX 100644 --- a/hw/acpi/aml-build.c +++ b/hw/acpi/aml-build.c @@ -XXX,XX +XXX,XX @@ void build_append_gas(GArray *table, AmlAddressSpace as, build_append_int_noprefix(table, address, 8); } +/* Hardware Error Notification + * ACPI 4.0: 17.3.2.7 Hardware Error Notification + */ +void build_append_ghes_notify(GArray *table, const uint8_t type, + uint8_t length, uint16_t config_write_enable, + uint32_t poll_interval, uint32_t vector, + uint32_t polling_threshold_value, + uint32_t polling_threshold_window, + uint32_t error_threshold_value, + uint32_t error_threshold_window) +{ + build_append_int_noprefix(table, type, 1); /* type */ + build_append_int_noprefix(table, length, 1); + build_append_int_noprefix(table, config_write_enable, 2); + build_append_int_noprefix(table, poll_interval, 4); + build_append_int_noprefix(table, vector, 4); + build_append_int_noprefix(table, polling_threshold_value, 4); + build_append_int_noprefix(table, polling_threshold_window, 4); + build_append_int_noprefix(table, error_threshold_value, 4); + build_append_int_noprefix(table, error_threshold_window, 4); +} + /* * Build NAME(XXXX, 0x00000000) where 0x00000000 is encoded as a dword, * and return the offset to 0x00000000 for runtime patching. diff --git a/include/hw/acpi/aml-build.h b/include/hw/acpi/aml-build.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/acpi/aml-build.h +++ b/include/hw/acpi/aml-build.h @@ -XXX,XX +XXX,XX @@ build_append_gas_from_struct(GArray *table, const struct AcpiGenericAddress *s) s->access_width, s->address); } +void build_append_ghes_notify(GArray *table, const uint8_t type, + uint8_t length, uint16_t config_write_enable, + uint32_t poll_interval, uint32_t vector, + uint32_t polling_threshold_value, + uint32_t polling_threshold_window, + uint32_t error_threshold_value, + uint32_t error_threshold_window); + void build_srat_memory(AcpiSratMemoryAffinity *numamem, uint64_t base, uint64_t len, int node, MemoryAffinityFlags flags); -- 1.8.3.1 It will help to add Generic Error Data Entry to ACPI tables without using packed C structures and avoid endianness issues as API doesn't need explicit conversion. Signed-off-by: Dongjiu Geng <gengdongjiu@huawei.com> --- hw/acpi/aml-build.c | 32 ++++++++++++++++++++++++++++++++ include/hw/acpi/aml-build.h | 6 ++++++ 2 files changed, 38 insertions(+) diff --git a/hw/acpi/aml-build.c b/hw/acpi/aml-build.c index XXXXXXX..XXXXXXX 100644 --- a/hw/acpi/aml-build.c +++ b/hw/acpi/aml-build.c @@ -XXX,XX +XXX,XX @@ void build_append_ghes_notify(GArray *table, const uint8_t type, build_append_int_noprefix(table, error_threshold_window, 4); } +/* Generic Error Data Entry + * ACPI 4.0: 17.3.2.6.1 Generic Error Data + */ +void build_append_ghes_generic_data(GArray *table, const char *section_type, + uint32_t error_severity, uint16_t revision, + uint8_t validation_bits, uint8_t flags, + uint32_t error_data_length, uint8_t *fru_id, + uint8_t *fru_text, uint64_t time_stamp) +{ + int i; + + for (i = 0; i < 16; i++) { + build_append_int_noprefix(table, section_type[i], 1); + } + + build_append_int_noprefix(table, error_severity, 4); + build_append_int_noprefix(table, revision, 2); + build_append_int_noprefix(table, validation_bits, 1); + build_append_int_noprefix(table, flags, 1); + build_append_int_noprefix(table, error_data_length, 4); + + for (i = 0; i < 16; i++) { + build_append_int_noprefix(table, fru_id[i], 1); + } + + for (i = 0; i < 20; i++) { + build_append_int_noprefix(table, fru_text[i], 1); + } + + build_append_int_noprefix(table, time_stamp, 8); +} + /* * Build NAME(XXXX, 0x00000000) where 0x00000000 is encoded as a dword, * and return the offset to 0x00000000 for runtime patching. diff --git a/include/hw/acpi/aml-build.h b/include/hw/acpi/aml-build.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/acpi/aml-build.h +++ b/include/hw/acpi/aml-build.h @@ -XXX,XX +XXX,XX @@ void build_append_ghes_notify(GArray *table, const uint8_t type, uint32_t error_threshold_value, uint32_t error_threshold_window); +void build_append_ghes_generic_data(GArray *table, const char *section_type, + uint32_t error_severity, uint16_t revision, + uint8_t validation_bits, uint8_t flags, + uint32_t error_data_length, uint8_t *fru_id, + uint8_t *fru_text, uint64_t time_stamp); + void build_srat_memory(AcpiSratMemoryAffinity *numamem, uint64_t base, uint64_t len, int node, MemoryAffinityFlags flags); -- 1.8.3.1 It will help to add Generic Error Status Block to ACPI tables without using packed C structures and avoid endianness issues as API doesn't need explicit conversion. Signed-off-by: Dongjiu Geng <gengdongjiu@huawei.com> --- hw/acpi/aml-build.c | 14 ++++++++++++++ include/hw/acpi/aml-build.h | 6 ++++++ 2 files changed, 20 insertions(+) diff --git a/hw/acpi/aml-build.c b/hw/acpi/aml-build.c index XXXXXXX..XXXXXXX 100644 --- a/hw/acpi/aml-build.c +++ b/hw/acpi/aml-build.c @@ -XXX,XX +XXX,XX @@ void build_append_ghes_notify(GArray *table, const uint8_t type, build_append_int_noprefix(table, error_threshold_window, 4); } +/* Generic Error Status Block + * ACPI 4.0: 17.3.2.6.1 Generic Error Data + */ +void build_append_ghes_generic_status(GArray *table, uint32_t block_status, + uint32_t raw_data_offset, uint32_t raw_data_length, + uint32_t data_length, uint32_t error_severity) +{ + build_append_int_noprefix(table, block_status, 4); + build_append_int_noprefix(table, raw_data_offset, 4); + build_append_int_noprefix(table, raw_data_length, 4); + build_append_int_noprefix(table, data_length, 4); + build_append_int_noprefix(table, error_severity, 4); +} + /* Generic Error Data Entry * ACPI 4.0: 17.3.2.6.1 Generic Error Data */ diff --git a/include/hw/acpi/aml-build.h b/include/hw/acpi/aml-build.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/acpi/aml-build.h +++ b/include/hw/acpi/aml-build.h @@ -XXX,XX +XXX,XX @@ void build_append_ghes_generic_data(GArray *table, const char *section_type, uint32_t error_data_length, uint8_t *fru_id, uint8_t *fru_text, uint64_t time_stamp); +void +build_append_ghes_generic_status(GArray *table, uint32_t block_status, + uint32_t raw_data_offset, + uint32_t raw_data_length, + uint32_t data_length, uint32_t error_severity); + void build_srat_memory(AcpiSratMemoryAffinity *numamem, uint64_t base, uint64_t len, int node, MemoryAffinityFlags flags); -- 1.8.3.1 Add APEI/GHES detailed design document Signed-off-by: Dongjiu Geng <gengdongjiu@huawei.com> --- docs/specs/acpi_hest_ghes.txt | 97 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 97 insertions(+) create mode 100644 docs/specs/acpi_hest_ghes.txt diff --git a/docs/specs/acpi_hest_ghes.txt b/docs/specs/acpi_hest_ghes.txt new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/docs/specs/acpi_hest_ghes.txt @@ -XXX,XX +XXX,XX @@ +APEI tables generating and CPER record +============================= + +Copyright (C) 2017 HuaWei Corporation. + +Design Details: +------------------- + + etc/acpi/tables etc/hardware_errors + ==================== ========================================== ++ +--------------------------+ +-----------------------+ +| | HEST | | address | +--------------+ +| +--------------------------+ | registers | | Error Status | +| | GHES1 | | +---------------------+ | Data Block 1 | +| +--------------------------+ +--------->| |error_block_address1 |----------->| +------------+ +| | ................. | | | +---------------------+ | | CPER | +| | error_status_address-----+-+ +------->| |error_block_address2 |--------+ | | CPER | +| | ................. | | | +---------------------+ | | | .... | +| | read_ack_register--------+-+ | | | .............. | | | | CPER | +| | read_ack_preserve | | | +-----------------------+ | | +------------+ +| | read_ack_write | | | +----->| |error_block_addressN |------+ | | Error Status | ++ +--------------------------+ | | | | +---------------------+ | | | Data Block 2 | +| | GHES2 | +-+-+----->| |read_ack_register1 | | +-->| +------------+ ++ +--------------------------+ | | | +---------------------+ | | | CPER | +| | ................. | | | +--->| |read_ack_register2 | | | | CPER | +| | error_status_address-----+---+ | | | +---------------------+ | | | .... | +| | ................. | | | | | ............. | | | | CPER | +| | read_ack_register--------+-----+-+ | +---------------------+ | +-+------------+ +| | read_ack_preserve | | +->| |read_ack_registerN | | | |.......... | +| | read_ack_write | | | | +---------------------+ | | +------------+ ++ +--------------------------| | | | | Error Status | +| | ............... | | | | | Data Block N | ++ +--------------------------+ | | +---->| +------------+ +| | GHESN | | | | | CPER | ++ +--------------------------+ | | | | CPER | +| | ................. | | | | | .... | +| | error_status_address-----+-----+ | | | CPER | +| | ................. | | +-+------------+ +| | read_ack_register--------+---------+ +| | read_ack_preserve | +| | read_ack_write | ++ +--------------------------+ + +(1) QEMU generates the ACPI HEST table. This table goes in the current + "etc/acpi/tables" fw_cfg blob. Each error source has different + notification type. + +(2) A new fw_cfg blob called "etc/hardware_errors" is introduced. QEMU + also need to populate this blob. The "etc/hardwre_errors" fw_cfg blob + contains one address registers table and one Error Status Data Block + table, all of which are pre-allocated. + +(3) The address registers table contains N Error Block Address entries + and N Read Ack Address entries, the size for each entry is 8-byte. + The Error Status Data Block table contains N Error Status Data Block + entries, the size for each entry is 4096(0x1000) bytes. The total size + for "etc/hardware_errors" fw_cfg blob is (N * 8 * 2 + N * 4096) bytes. + +(4) QEMU generates the ACPI linker/loader script for the firmware + +(4a) The HEST table is part of "etc/acpi/tables", the firmware already + allocates the memory for it, because QEMU already generates an ALLOCATE + linker/loader command for it + +(4b) QEMU creates another ALLOCATE command for the "etc/hardware_errors" + blob. The firmware allocates memory for this blob and downloads it. + +(5) QEMU generates N ADD_POINTER commands, which patch address in the + "error_status_address" fields of the HEST table with a pointer to the + corresponding "address registers" in the downloaded "etc/hardware_errors" + blob. + +(6) QEMU generates N ADD_POINTER commands, which patch address in the + "read_ack_register" fields of the HEST table with a pointer to the + corresponding "address registers" in the downloaded "etc/hardware_errors" blob. + +(7) QEMU generates N ADD_POINTER commands for the firmware, which patch + address in the " error_block_address" fields with a pointer to the + respective "Error Status Data Block" in the downloaded "etc/hardware_errors" + blob. + +(8) QEMU Defines a third and write-only fw_cfg blob which is called + "etc/hardware_errors_addr". Through that blob, the firmware can send back + the guest-side allocation addresses to QEMU. The "etc/hardware_errors_addr" + blob contains a 8-byte entry. QEMU generates a single WRITE_POINTER commands + for the firmware, the firmware will write back the start address of + "etc/hardware_errors" blob to fw_cfg file "etc/hardware_errors_addr". Then + Qemu will know the Error Status Data Block for every error source. Each of + Error Status Data Block has fixed size which is 4096(0x1000). + +(9) When QEMU gets SIGBUS from the kernel, QEMU formats the CPER right into + guest memory, and then injects whatever interrupt (or assert whatever GPIO line) + as a notification which is necessary for notifying the guest. + +(10) This notification (in virtual hardware) will be handled by guest kernel, + guest APEI driver will read the CPER which is recorded by QEMU and do the + recovery. -- 1.8.3.1 This implements APEI GHES Table generation via fw_cfg blobs. Now it only support GPIO-Signal and ARMv8 SEA two types of GHESv2 error source. Afterwards, we can extend the supported types if needed. For the CPER section type, currently it is memory section because kernel mainly wants userspace to handle the memory errors. This patch follows the spec ACPI 6.2 to build the Hardware Error Source table, for the detailed information, please refer to document: docs/specs/acpi_hest_ghes.txt Suggested-by: Laszlo Ersek <lersek@redhat.com> Signed-off-by: Dongjiu Geng <gengdongjiu@huawei.com> --- default-configs/arm-softmmu.mak | 1 + hw/acpi/Kconfig | 4 + hw/acpi/Makefile.objs | 1 + hw/acpi/acpi_ghes.c | 171 ++++++++++++++++++++++++++++++++++++++++ hw/acpi/aml-build.c | 2 + hw/arm/virt-acpi-build.c | 12 +++ include/hw/acpi/acpi_ghes.h | 79 +++++++++++++++++++ include/hw/acpi/aml-build.h | 1 + 8 files changed, 271 insertions(+) create mode 100644 hw/acpi/acpi_ghes.c create mode 100644 include/hw/acpi/acpi_ghes.h diff --git a/default-configs/arm-softmmu.mak b/default-configs/arm-softmmu.mak index XXXXXXX..XXXXXXX 100644 --- a/default-configs/arm-softmmu.mak +++ b/default-configs/arm-softmmu.mak @@ -XXX,XX +XXX,XX @@ CONFIG_MUSICPAL=y # for realview and versatilepb CONFIG_LSI_SCSI_PCI=y +CONFIG_ACPI_APEI=y diff --git a/hw/acpi/Kconfig b/hw/acpi/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/acpi/Kconfig +++ b/hw/acpi/Kconfig @@ -XXX,XX +XXX,XX @@ config ACPI_NVDIMM bool depends on ACPI +config ACPI_APEI + bool + depends on ACPI + config ACPI_VMGENID bool default y diff --git a/hw/acpi/Makefile.objs b/hw/acpi/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/acpi/Makefile.objs +++ b/hw/acpi/Makefile.objs @@ -XXX,XX +XXX,XX @@ common-obj-$(CONFIG_ACPI_MEMORY_HOTPLUG) += memory_hotplug.o common-obj-$(CONFIG_ACPI_CPU_HOTPLUG) += cpu.o common-obj-$(CONFIG_ACPI_NVDIMM) += nvdimm.o common-obj-$(CONFIG_ACPI_VMGENID) += vmgenid.o +common-obj-$(CONFIG_ACPI_APEI) += acpi_ghes.o common-obj-$(call lnot,$(CONFIG_ACPI_X86)) += acpi-stub.o common-obj-y += acpi_interface.o diff --git a/hw/acpi/acpi_ghes.c b/hw/acpi/acpi_ghes.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/acpi/acpi_ghes.c @@ -XXX,XX +XXX,XX @@ +/* Support for generating APEI tables and record CPER for Guests + * + * Copyright (C) 2017 HuaWei Corporation. + * + * Author: Dongjiu Geng <gengdongjiu@huawei.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + + * You should have received a copy of the GNU General Public License along + * with this program; if not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" +#include "hw/acpi/acpi.h" +#include "hw/acpi/aml-build.h" +#include "hw/acpi/acpi_ghes.h" +#include "hw/nvram/fw_cfg.h" +#include "sysemu/sysemu.h" +#include "qemu/error-report.h" + +/* Build table for the hardware error fw_cfg blob */ +void build_hardware_error_table(GArray *hardware_errors, BIOSLinker *linker) +{ + int i; + + /* + * | +--------------------------+ + * | | error_block_address | + * | | .......... | + * | +--------------------------+ + * | | read_ack_register | + * | | ........... | + * | +--------------------------+ + * | | Error Status Data Block | + * | | ........ | + * | +--------------------------+ + */ + + /* Build error_block_address */ + build_append_int_noprefix((void *)hardware_errors, 0, + GHES_ADDRESS_SIZE * ACPI_HEST_ERROR_SOURCE_COUNT); + + /* Build read_ack_register */ + for (i = 0; i < ACPI_HEST_ERROR_SOURCE_COUNT; i++) + /* Initialize the value of read_ack_register to 1, so GHES can be + * writeable in the first time + */ + build_append_int_noprefix((void *)hardware_errors, 1, GHES_ADDRESS_SIZE); + + /* Build Error Status Data Block */ + build_append_int_noprefix((void *)hardware_errors, 0, + GHES_MAX_RAW_DATA_LENGTH * ACPI_HEST_ERROR_SOURCE_COUNT); + + /* Allocate guest memory for the hardware error fw_cfg blob */ + bios_linker_loader_alloc(linker, GHES_ERRORS_FW_CFG_FILE, hardware_errors, + 1, false); +} + +/* Build Hardware Error Source Table */ +void build_apei_hest(GArray *table_data, GArray *hardware_errors, + BIOSLinker *linker) +{ + uint32_t i, error_status_block_offset, length = table_data->len; + + /* Reserve Hardware Error Source Table header size */ + acpi_data_push(table_data, sizeof(AcpiTableHeader)); + + /* Set the error source counts */ + build_append_int_noprefix(table_data, ACPI_HEST_ERROR_SOURCE_COUNT, 4); + + for (i = 0; i < ACPI_HEST_ERROR_SOURCE_COUNT; i++) { + /* Generic Hardware Error Source version 2(GHESv2 - Type 10) + */ + build_append_int_noprefix(table_data, + ACPI_HEST_SOURCE_GENERIC_ERROR_V2, 2); /* type */ + build_append_int_noprefix(table_data, cpu_to_le16(i), 2); /* source id */ + build_append_int_noprefix(table_data, 0xffff, 2); /* related source id */ + build_append_int_noprefix(table_data, 0, 1); /* flags */ + + build_append_int_noprefix(table_data, 1, 1); /* enabled */ + + /* Number of Records To Pre-allocate */ + build_append_int_noprefix(table_data, 1, 4); + /* Max Sections Per Record */ + build_append_int_noprefix(table_data, 1, 4); + /* Max Raw Data Length */ + build_append_int_noprefix(table_data, GHES_MAX_RAW_DATA_LENGTH, 4); + + /* Build error status address*/ + build_append_gas(table_data, AML_SYSTEM_MEMORY, 0x40, 0, 4 /* QWord access */, 0); + bios_linker_loader_add_pointer(linker, + ACPI_BUILD_TABLE_FILE, ERROR_STATUS_ADDRESS_OFFSET(length, i), + GHES_ADDRESS_SIZE, GHES_ERRORS_FW_CFG_FILE, i * GHES_ADDRESS_SIZE); + + /* Build Hardware Error Notification + * Now only enable GPIO-Signal and ARMv8 SEA notification types + */ + if (i == 0) { + build_append_ghes_notify(table_data, ACPI_HEST_NOTIFY_GPIO, 28, + 0, 0, 0, 0, 0, 0, 0); + } else if (i == 1) { + build_append_ghes_notify(table_data, ACPI_HEST_NOTIFY_SEA, 28, 0, + 0, 0, 0, 0, 0, 0); + } + + /* Error Status Block Length */ + build_append_int_noprefix(table_data, + cpu_to_le32(GHES_MAX_RAW_DATA_LENGTH), 4); + + /* Build Read ACK register + * ACPI 6.1/6.2: 18.3.2.8 Generic Hardware Error Source + * version 2 (GHESv2 - Type 10) + */ + build_append_gas(table_data, AML_SYSTEM_MEMORY, 0x40, 0, 4 /* QWord access */, 0); + bios_linker_loader_add_pointer(linker, ACPI_BUILD_TABLE_FILE, + READ_ACK_REGISTER_ADDRESS_OFFSET(length, i), GHES_ADDRESS_SIZE, + GHES_ERRORS_FW_CFG_FILE, + (ACPI_HEST_ERROR_SOURCE_COUNT + i) * GHES_ADDRESS_SIZE); + + /* Build Read Ack Preserve and Read Ack Writer */ + build_append_int_noprefix(table_data, cpu_to_le64(ReadAckPreserve), 8); + build_append_int_noprefix(table_data, cpu_to_le64(ReadAckWrite), 8); + } + + /* Generic Error Status Block offset in the hardware error fw_cfg blob */ + error_status_block_offset = GHES_ADDRESS_SIZE * 2 * + ACPI_HEST_ERROR_SOURCE_COUNT; + + for (i = 0; i < ACPI_HEST_ERROR_SOURCE_COUNT; i++) + /* Patch address of Error Status Data Block into + * the error_block_address of hardware_errors fw_cfg blob + */ + bios_linker_loader_add_pointer(linker, + GHES_ERRORS_FW_CFG_FILE, GHES_ADDRESS_SIZE * i, GHES_ADDRESS_SIZE, + GHES_ERRORS_FW_CFG_FILE, + error_status_block_offset + i * GHES_MAX_RAW_DATA_LENGTH); + + /* write address of hardware_errors fw_cfg blob into the + * hardware_errors_addr fw_cfg blob. + */ + bios_linker_loader_write_pointer(linker, GHES_DATA_ADDR_FW_CFG_FILE, + 0, GHES_ADDRESS_SIZE, GHES_ERRORS_FW_CFG_FILE, 0); + + build_header(linker, table_data, + (void *)(table_data->data + length), "HEST", + table_data->len - length, 1, NULL, "GHES"); +} + +static GhesState ges; +void ghes_add_fw_cfg(FWCfgState *s, GArray *hardware_error) +{ + + size_t size = 2 * GHES_ADDRESS_SIZE + GHES_MAX_RAW_DATA_LENGTH; + size_t request_block_size = ACPI_HEST_ERROR_SOURCE_COUNT * size; + + /* Create a read-only fw_cfg file for GHES */ + fw_cfg_add_file(s, GHES_ERRORS_FW_CFG_FILE, hardware_error->data, + request_block_size); + + /* Create a read-write fw_cfg file for Address */ + fw_cfg_add_file_callback(s, GHES_DATA_ADDR_FW_CFG_FILE, NULL, NULL, NULL, + &ges.ghes_addr_le, sizeof(ges.ghes_addr_le), false); +} diff --git a/hw/acpi/aml-build.c b/hw/acpi/aml-build.c index XXXXXXX..XXXXXXX 100644 --- a/hw/acpi/aml-build.c +++ b/hw/acpi/aml-build.c @@ -XXX,XX +XXX,XX @@ void acpi_build_tables_init(AcpiBuildTables *tables) tables->table_data = g_array_new(false, true /* clear */, 1); tables->tcpalog = g_array_new(false, true /* clear */, 1); tables->vmgenid = g_array_new(false, true /* clear */, 1); + tables->hardware_errors = g_array_new(false, true /* clear */, 1); tables->linker = bios_linker_loader_init(); } @@ -XXX,XX +XXX,XX @@ void acpi_build_tables_cleanup(AcpiBuildTables *tables, bool mfre) g_array_free(tables->table_data, true); g_array_free(tables->tcpalog, mfre); g_array_free(tables->vmgenid, mfre); + g_array_free(tables->hardware_errors, mfre); } /* diff --git a/hw/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt-acpi-build.c +++ b/hw/arm/virt-acpi-build.c @@ -XXX,XX +XXX,XX @@ #include "hw/arm/virt.h" #include "sysemu/numa.h" #include "kvm_arm.h" +#include "hw/acpi/acpi_ghes.h" #define ARM_SPI_BASE 32 #define ACPI_POWER_BUTTON_DEVICE "PWRB" @@ -XXX,XX +XXX,XX @@ void virt_acpi_build(VirtMachineState *vms, AcpiBuildTables *tables) acpi_add_table(table_offsets, tables_blob); build_spcr(tables_blob, tables->linker, vms); + if (!vmc->no_ras) { + acpi_add_table(table_offsets, tables_blob); + build_hardware_error_table(tables->hardware_errors, tables->linker); + build_apei_hest(tables_blob, tables->hardware_errors, tables->linker); + } + if (nb_numa_nodes > 0) { acpi_add_table(table_offsets, tables_blob); build_srat(tables_blob, tables->linker, vms); @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_virt_acpi_build = { void virt_acpi_setup(VirtMachineState *vms) { + VirtMachineClass *vmc = VIRT_MACHINE_GET_CLASS(vms); AcpiBuildTables tables; AcpiBuildState *build_state; @@ -XXX,XX +XXX,XX @@ void virt_acpi_setup(VirtMachineState *vms) fw_cfg_add_file(vms->fw_cfg, ACPI_BUILD_TPMLOG_FILE, tables.tcpalog->data, acpi_data_len(tables.tcpalog)); + if (!vmc->no_ras) { + ghes_add_fw_cfg(vms->fw_cfg, tables.hardware_errors); + } + build_state->rsdp_mr = acpi_add_rom_blob(build_state, tables.rsdp, ACPI_BUILD_RSDP_FILE, 0); diff --git a/include/hw/acpi/acpi_ghes.h b/include/hw/acpi/acpi_ghes.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/acpi/acpi_ghes.h @@ -XXX,XX +XXX,XX @@ +/* Support for generating APEI tables and record CPER for Guests + * + * Copyright (C) 2017 HuaWei Corporation. + * + * Author: Dongjiu Geng <gengdongjiu@huawei.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + + * You should have received a copy of the GNU General Public License along + * with this program; if not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef ACPI_GHES_H +#define ACPI_GHES_H + +#include "hw/acpi/bios-linker-loader.h" + +#define GHES_ERRORS_FW_CFG_FILE "etc/hardware_errors" +#define GHES_DATA_ADDR_FW_CFG_FILE "etc/hardware_errors_addr" + +/* The size of Address field in Generic Address Structure, + * ACPI 2.0/3.0: 5.2.3.1 Generic Address Structure. + */ +#define GHES_ADDRESS_SIZE 8 + +#define GHES_DATA_LENGTH 72 +#define GHES_CPER_LENGTH 80 + +#define ReadAckPreserve 0xfffffffe +#define ReadAckWrite 0x1 + +/* The max size in bytes for one error block */ +#define GHES_MAX_RAW_DATA_LENGTH 0x1000 +/* Now only have GPIO-Signal and ARMv8 SEA notification types error sources + */ +#define ACPI_HEST_ERROR_SOURCE_COUNT 2 + +/* + * | +--------------------------+ 0 + * | | Header | + * | +--------------------------+ 40---+- + * | | ................. | | + * | | error_status_address-----+ 60 | + * | | ................. | | + * | | read_ack_register--------+ 104 92 + * | | read_ack_preserve | | + * | | read_ack_write | | + * + +--------------------------+ 132--+- + * + * From above GHES definition, the error status address offset is 60; + * the Read ack register offset is 104, the whole size of GHESv2 is 92 + */ + +/* The error status address offset in GHES */ +#define ERROR_STATUS_ADDRESS_OFFSET(start_addr, n) (start_addr + 60 + \ + offsetof(struct AcpiGenericAddress, address) + n * 92) + +/* The read Ack register offset in GHES */ +#define READ_ACK_REGISTER_ADDRESS_OFFSET(start_addr, n) (start_addr + 104 + \ + offsetof(struct AcpiGenericAddress, address) + n * 92) + +typedef struct GhesState { + uint64_t ghes_addr_le; +} GhesState; + +void build_apei_hest(GArray *table_data, GArray *hardware_error, + BIOSLinker *linker); + +void build_hardware_error_table(GArray *hardware_errors, BIOSLinker *linker); +void ghes_add_fw_cfg(FWCfgState *s, GArray *hardware_errors); +#endif diff --git a/include/hw/acpi/aml-build.h b/include/hw/acpi/aml-build.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/acpi/aml-build.h +++ b/include/hw/acpi/aml-build.h @@ -XXX,XX +XXX,XX @@ struct AcpiBuildTables { GArray *rsdp; GArray *tcpalog; GArray *vmgenid; + GArray *hardware_errors; BIOSLinker *linker; } AcpiBuildTables; -- 1.8.3.1 kvm_hwpoison_page_add() and kvm_unpoison_all() will be used both by X86 and ARM platforms, so move these functions to a common accel/kvm/ folder to avoid duplicate code. Signed-off-by: Dongjiu Geng <gengdongjiu@huawei.com> --- accel/kvm/kvm-all.c | 33 +++++++++++++++++++++++++++++++++ include/exec/ram_addr.h | 24 ++++++++++++++++++++++++ target/arm/kvm.c | 3 +++ target/i386/kvm.c | 34 +--------------------------------- 4 files changed, 61 insertions(+), 33 deletions(-) diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c index XXXXXXX..XXXXXXX 100644 --- a/accel/kvm/kvm-all.c +++ b/accel/kvm/kvm-all.c @@ -XXX,XX +XXX,XX @@ int kvm_vm_check_extension(KVMState *s, unsigned int extension) return ret; } +typedef struct HWPoisonPage { + ram_addr_t ram_addr; + QLIST_ENTRY(HWPoisonPage) list; +} HWPoisonPage; + +static QLIST_HEAD(, HWPoisonPage) hwpoison_page_list = + QLIST_HEAD_INITIALIZER(hwpoison_page_list); + +void kvm_unpoison_all(void *param) +{ + HWPoisonPage *page, *next_page; + + QLIST_FOREACH_SAFE(page, &hwpoison_page_list, list, next_page) { + QLIST_REMOVE(page, list); + qemu_ram_remap(page->ram_addr, TARGET_PAGE_SIZE); + g_free(page); + } +} + +void kvm_hwpoison_page_add(ram_addr_t ram_addr) +{ + HWPoisonPage *page; + + QLIST_FOREACH(page, &hwpoison_page_list, list) { + if (page->ram_addr == ram_addr) { + return; + } + } + page = g_new(HWPoisonPage, 1); + page->ram_addr = ram_addr; + QLIST_INSERT_HEAD(&hwpoison_page_list, page, list); +} + static uint32_t adjust_ioeventfd_endianness(uint32_t val, uint32_t size) { #if defined(HOST_WORDS_BIGENDIAN) != defined(TARGET_WORDS_BIGENDIAN) diff --git a/include/exec/ram_addr.h b/include/exec/ram_addr.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/ram_addr.h +++ b/include/exec/ram_addr.h @@ -XXX,XX +XXX,XX @@ void qemu_ram_free(RAMBlock *block); int qemu_ram_resize(RAMBlock *block, ram_addr_t newsize, Error **errp); +/** + * kvm_hwpoison_page_add: + * + * Parameters: + * @ram_addr: the address in the RAM for the poisoned page + * + * Add a poisoned page to the list + * + * Return: None. + */ +void kvm_hwpoison_page_add(ram_addr_t ram_addr); + +/** + * kvm_unpoison_all: + * + * Parameters: + * @param: some data may be passed to this function + * + * Free and remove all the poisoned pages in the list + * + * Return: None. + */ +void kvm_unpoison_all(void *param); + #define DIRTY_CLIENTS_ALL ((1 << DIRTY_MEMORY_NUM) - 1) #define DIRTY_CLIENTS_NOCODE (DIRTY_CLIENTS_ALL & ~(1 << DIRTY_MEMORY_CODE)) diff --git a/target/arm/kvm.c b/target/arm/kvm.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm.c +++ b/target/arm/kvm.c @@ -XXX,XX +XXX,XX @@ #include "exec/address-spaces.h" #include "hw/boards.h" #include "qemu/log.h" +#include "exec/ram_addr.h" const KVMCapabilityInfo kvm_arch_required_capabilities[] = { KVM_CAP_LAST_INFO @@ -XXX,XX +XXX,XX @@ int kvm_arch_init(MachineState *ms, KVMState *s) cap_has_mp_state = kvm_check_extension(s, KVM_CAP_MP_STATE); + qemu_register_reset(kvm_unpoison_all, NULL); + return 0; } diff --git a/target/i386/kvm.c b/target/i386/kvm.c index XXXXXXX..XXXXXXX 100644 --- a/target/i386/kvm.c +++ b/target/i386/kvm.c @@ -XXX,XX +XXX,XX @@ #include "migration/blocker.h" #include "exec/memattrs.h" #include "trace.h" +#include "exec/ram_addr.h" //#define DEBUG_KVM @@ -XXX,XX +XXX,XX @@ uint32_t kvm_arch_get_supported_msr_feature(KVMState *s, uint32_t index) } -typedef struct HWPoisonPage { - ram_addr_t ram_addr; - QLIST_ENTRY(HWPoisonPage) list; -} HWPoisonPage; - -static QLIST_HEAD(, HWPoisonPage) hwpoison_page_list = - QLIST_HEAD_INITIALIZER(hwpoison_page_list); - -static void kvm_unpoison_all(void *param) -{ - HWPoisonPage *page, *next_page; - - QLIST_FOREACH_SAFE(page, &hwpoison_page_list, list, next_page) { - QLIST_REMOVE(page, list); - qemu_ram_remap(page->ram_addr, TARGET_PAGE_SIZE); - g_free(page); - } -} - -static void kvm_hwpoison_page_add(ram_addr_t ram_addr) -{ - HWPoisonPage *page; - - QLIST_FOREACH(page, &hwpoison_page_list, list) { - if (page->ram_addr == ram_addr) { - return; - } - } - page = g_new(HWPoisonPage, 1); - page->ram_addr = ram_addr; - QLIST_INSERT_HEAD(&hwpoison_page_list, page, list); -} - static int kvm_get_mce_cap_supported(KVMState *s, uint64_t *mce_cap, int *max_banks) { -- 1.8.3.1 Add synchronous external abort injection logic, setup exception type and syndrome value. When switch to guest, it will jump to the synchronous external abort vector table entry. The ESR_ELx.DFSC is set to synchronous external abort(0x10), and ESR_ELx.FnV is set to not valid(0x1), which will tell guest that FAR is not valid and hold an UNKNOWN value. These value will be set to KVM register structures through KVM_SET_ONE_REG IOCTL. Signed-off-by: Dongjiu Geng <gengdongjiu@huawei.com> --- target/arm/internals.h | 5 +++-- target/arm/kvm64.c | 34 ++++++++++++++++++++++++++++++++++ target/arm/op_helper.c | 2 +- 3 files changed, 38 insertions(+), 3 deletions(-) diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_insn_abort(int same_el, int ea, int s1ptw, int fsc) | ARM_EL_IL | (ea << 9) | (s1ptw << 7) | fsc; } -static inline uint32_t syn_data_abort_no_iss(int same_el, +static inline uint32_t syn_data_abort_no_iss(int same_el, int fnv, int ea, int cm, int s1ptw, int wnr, int fsc) { return (EC_DATAABORT << ARM_EL_EC_SHIFT) | (same_el << ARM_EL_EC_SHIFT) | ARM_EL_IL - | (ea << 9) | (cm << 8) | (s1ptw << 7) | (wnr << 6) | fsc; + | (fnv << 10) | (ea << 9) | (cm << 8) | (s1ptw << 7) + | (wnr << 6) | fsc; } static inline uint32_t syn_data_abort_with_iss(int same_el, diff --git a/target/arm/kvm64.c b/target/arm/kvm64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm64.c +++ b/target/arm/kvm64.c @@ -XXX,XX +XXX,XX @@ int kvm_arm_cpreg_level(uint64_t regidx) return KVM_PUT_RUNTIME_STATE; } +/* Inject synchronous external abort */ +static void kvm_inject_arm_sea(CPUState *c) +{ + ARMCPU *cpu = ARM_CPU(c); + CPUARMState *env = &cpu->env; + CPUClass *cc = CPU_GET_CLASS(c); + uint32_t esr; + bool same_el; + + /** + * set the exception type to synchronous data abort + * and the target exception Level to EL1. + */ + c->exception_index = EXCP_DATA_ABORT; + env->exception.target_el = 1; + + /* + * Set the DFSC to synchronous external abort and set FnV to not valid, + * this will tell guest the FAR_ELx is UNKNOWN for this abort. + */ + + /* This exception comes from lower or current exception level. */ + same_el = arm_current_el(env) == env->exception.target_el; + esr = syn_data_abort_no_iss(same_el, 1, 0, 0, 0, 0, 0x10); + + env->exception.syndrome = esr; + + /** + * The vcpu thread already hold BQL, so no need hold again when + * calling do_interrupt + */ + cc->do_interrupt(c); +} + #define AARCH64_CORE_REG(x) (KVM_REG_ARM64 | KVM_REG_SIZE_U64 | \ KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(x)) diff --git a/target/arm/op_helper.c b/target/arm/op_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/op_helper.c +++ b/target/arm/op_helper.c @@ -XXX,XX +XXX,XX @@ static inline uint32_t merge_syn_data_abort(uint32_t template_syn, * ISV field. */ if (!(template_syn & ARM_EL_ISV) || target_el != 2 || s1ptw) { - syn = syn_data_abort_no_iss(same_el, + syn = syn_data_abort_no_iss(same_el, 0, ea, 0, s1ptw, is_write, fsc); } else { /* Fields: IL, ISV, SAS, SSE, SRT, SF and AR come from the template -- 1.8.3.1 Add SIGBUS signal handler. In this handler, it checks the SIGBUS type, translates the host VA delivered by host to guest PA, then fill this PA to guest APEI GHES memory, then notify guest according to the SIGBUS type. If guest accesses the poisoned memory, it generates Synchronous External Abort(SEA). Then host kernel gets an APEI notification and call memory_failure() to unmapped the affected page for the guest's stage 2, finally return to guest. Guest continues to access PG_hwpoison page, it will trap to KVM as stage2 fault, then a SIGBUS_MCEERR_AR synchronous signal is delivered to Qemu, Qemu record this error address into guest APEI GHES memory and notify guest using Synchronous-External-Abort(SEA). Suggested-by: James Morse <james.morse@arm.com> Signed-off-by: Dongjiu Geng <gengdongjiu@huawei.com> --- hw/acpi/acpi_ghes.c | 177 ++++++++++++++++++++++++++++++++++++++++++++ include/hw/acpi/acpi_ghes.h | 6 +- include/sysemu/kvm.h | 2 +- target/arm/kvm64.c | 40 ++++++++++ 4 files changed, 223 insertions(+), 2 deletions(-) diff --git a/hw/acpi/acpi_ghes.c b/hw/acpi/acpi_ghes.c index XXXXXXX..XXXXXXX 100644 --- a/hw/acpi/acpi_ghes.c +++ b/hw/acpi/acpi_ghes.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/sysemu.h" #include "qemu/error-report.h" +/* UEFI 2.6: N.2.5 Memory Error Section */ +static void build_append_mem_cper(GArray *table, uint64_t error_physical_addr) +{ + /* + * Memory Error Record + */ + build_append_int_noprefix(table, + (1UL << 14) | /* Type Valid */ + (1UL << 1) /* Physical Address Valid */, + 8); + /* Memory error status information */ + build_append_int_noprefix(table, 0, 8); + /* The physical address at which the memory error occurred */ + build_append_int_noprefix(table, error_physical_addr, 8); + build_append_int_noprefix(table, 0, 48); + build_append_int_noprefix(table, 0 /* Unknown error */, 1); + build_append_int_noprefix(table, 0, 7); +} + +static int ghes_record_mem_error(uint64_t error_block_address, + uint64_t error_physical_addr) +{ + GArray *block; + uint64_t current_block_length; + uint32_t data_length; + /* Memory section */ + char mem_section_id_le[] = {0x14, 0x11, 0xBC, 0xA5, 0x64, 0x6F, 0xDE, + 0x4E, 0xB8, 0x63, 0x3E, 0x83, 0xED, 0x7C, + 0x83, 0xB1}; + uint8_t fru_id[16] = {0}; + uint8_t fru_text[20] = {0}; + + /* Generic Error Status Block + * | +---------------------+ + * | | block_status | + * | +---------------------+ + * | | raw_data_offset | + * | +---------------------+ + * | | raw_data_length | + * | +---------------------+ + * | | data_length | + * | +---------------------+ + * | | error_severity | + * | +---------------------+ + */ + block = g_array_new(false, true /* clear */, 1); + + /* Get the length of the Generic Error Data Entries */ + cpu_physical_memory_read(error_block_address + + offsetof(AcpiGenericErrorStatus, data_length), &data_length, 4); + + /* The current whole length of the generic error status block */ + current_block_length = sizeof(AcpiGenericErrorStatus) + le32_to_cpu(data_length); + + /* This is the length if adding a new generic error data entry*/ + data_length += GHES_DATA_LENGTH; + data_length += GHES_MEM_CPER_LENGTH; + + /* Check whether it will run out of the preallocated memory if adding a new + * generic error data entry + */ + if ((data_length + sizeof(AcpiGenericErrorStatus)) > GHES_MAX_RAW_DATA_LENGTH) { + error_report("Record CPER out of boundary!!!"); + return GHES_CPER_FAIL; + } + + /* Build the new generic error status block header */ + build_append_ghes_generic_status(block, cpu_to_le32(ACPI_GEBS_UNCORRECTABLE), 0, 0, + cpu_to_le32(data_length), cpu_to_le32(ACPI_CPER_SEV_RECOVERABLE)); + + /* Write back above generic error status block header to guest memory */ + cpu_physical_memory_write(error_block_address, block->data, + block->len); + + /* Add a new generic error data entry */ + + data_length = block->len; + /* Build this new generic error data entry header */ + build_append_ghes_generic_data(block, mem_section_id_le, + cpu_to_le32(ACPI_CPER_SEV_RECOVERABLE), cpu_to_le32(0x300), 0, 0, + cpu_to_le32(80)/* the total size of Memory Error Record */, fru_id, + fru_text, 0); + + /* Build the memory section CPER for above new generic error data entry */ + build_append_mem_cper(block, error_physical_addr); + + /* Write back above this new generic error data entry to guest memory */ + cpu_physical_memory_write(error_block_address + current_block_length, + block->data + data_length, block->len - data_length); + + g_array_free(block, true); + + return GHES_CPER_OK; +} + /* Build table for the hardware error fw_cfg blob */ void build_hardware_error_table(GArray *hardware_errors, BIOSLinker *linker) { @@ -XXX,XX +XXX,XX @@ void ghes_add_fw_cfg(FWCfgState *s, GArray *hardware_error) fw_cfg_add_file_callback(s, GHES_DATA_ADDR_FW_CFG_FILE, NULL, NULL, NULL, &ges.ghes_addr_le, sizeof(ges.ghes_addr_le), false); } + +bool ghes_record_errors(uint32_t notify, uint64_t physical_address) +{ + uint64_t error_block_addr, read_ack_register_addr; + int read_ack_register = 0, loop = 0; + uint64_t start_addr = le32_to_cpu(ges.ghes_addr_le); + bool ret = GHES_CPER_FAIL; + const uint8_t error_source_id[] = { 0xff, 0xff, 0xff, 0xff, + 0xff, 0xff, 0xff, 0, 1}; + + /* + * | +---------------------+ ges.ghes_addr_le + * | |error_block_address0 | + * | +---------------------+ --+-- + * | | ............. | GHES_ADDRESS_SIZE + * | +---------------------+ --+-- + * | |error_block_addressN | + * | +---------------------+ + * | | read_ack_register0 | + * | +---------------------+ --+-- + * | | ............. | GHES_ADDRESS_SIZE + * | +---------------------+ --+-- + * | | read_ack_registerN | + * | +---------------------+ --+-- + * | | CPER | | + * | | .... | GHES_MAX_RAW_DATA_LENGT + * | | CPER | | + * | +---------------------+ --+-- + * | | .......... | + * | +---------------------+ + * | | CPER | + * | | .... | + * | | CPER | + * | +---------------------+ + */ + if (physical_address && notify < ACPI_HEST_NOTIFY_RESERVED) { + /* Find and check the source id for this new CPER */ + if (error_source_id[notify] != 0xff) { + start_addr += error_source_id[notify] * GHES_ADDRESS_SIZE; + } else { + goto out; + } + + cpu_physical_memory_read(start_addr, &error_block_addr, + GHES_ADDRESS_SIZE); + + read_ack_register_addr = start_addr + + ACPI_HEST_ERROR_SOURCE_COUNT * GHES_ADDRESS_SIZE; +retry: + cpu_physical_memory_read(read_ack_register_addr, + &read_ack_register, GHES_ADDRESS_SIZE); + + /* zero means OSPM does not acknowledge the error */ + if (!read_ack_register) { + if (loop < 3) { + usleep(100 * 1000); + loop++; + goto retry; + } else { + error_report("OSPM does not acknowledge previous error," + " so can not record CPER for current error, forcibly acknowledge" + " previous error to avoid blocking next time CPER record! Exit"); + read_ack_register = 1; + cpu_physical_memory_write(read_ack_register_addr, + &read_ack_register, GHES_ADDRESS_SIZE); + } + } else { + if (error_block_addr) { + read_ack_register = 0; + /* Clear the Read Ack Register, OSPM will write it to 1 when + * acknowledge this error. + */ + cpu_physical_memory_write(read_ack_register_addr, + &read_ack_register, GHES_ADDRESS_SIZE); + ret = ghes_record_mem_error(error_block_addr, physical_address); + } + } + } + +out: + return ret; +} diff --git a/include/hw/acpi/acpi_ghes.h b/include/hw/acpi/acpi_ghes.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/acpi/acpi_ghes.h +++ b/include/hw/acpi/acpi_ghes.h @@ -XXX,XX +XXX,XX @@ #define GHES_ADDRESS_SIZE 8 #define GHES_DATA_LENGTH 72 -#define GHES_CPER_LENGTH 80 +#define GHES_MEM_CPER_LENGTH 80 #define ReadAckPreserve 0xfffffffe #define ReadAckWrite 0x1 +#define GHES_CPER_OK 1 +#define GHES_CPER_FAIL 0 + /* The max size in bytes for one error block */ #define GHES_MAX_RAW_DATA_LENGTH 0x1000 /* Now only have GPIO-Signal and ARMv8 SEA notification types error sources @@ -XXX,XX +XXX,XX @@ void build_apei_hest(GArray *table_data, GArray *hardware_error, void build_hardware_error_table(GArray *hardware_errors, BIOSLinker *linker); void ghes_add_fw_cfg(FWCfgState *s, GArray *hardware_errors); +bool ghes_record_errors(uint32_t notify, uint64_t error_physical_addr); #endif diff --git a/include/sysemu/kvm.h b/include/sysemu/kvm.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/kvm.h +++ b/include/sysemu/kvm.h @@ -XXX,XX +XXX,XX @@ bool kvm_vcpu_id_is_valid(int vcpu_id); /* Returns VCPU ID to be used on KVM_CREATE_VCPU ioctl() */ unsigned long kvm_arch_vcpu_id(CPUState *cpu); -#ifdef TARGET_I386 +#if defined(TARGET_I386) || defined(TARGET_AARCH64) #define KVM_HAVE_MCE_INJECTION 1 void kvm_arch_on_sigbus_vcpu(CPUState *cpu, int code, void *addr); #endif diff --git a/target/arm/kvm64.c b/target/arm/kvm64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm64.c +++ b/target/arm/kvm64.c @@ -XXX,XX +XXX,XX @@ #include "kvm_arm.h" #include "internals.h" #include "hw/arm/arm.h" +#include "exec/ram_addr.h" +#include "hw/acpi/acpi-defs.h" +#include "hw/acpi/acpi_ghes.h" static bool have_guest_debug; @@ -XXX,XX +XXX,XX @@ int kvm_arch_get_registers(CPUState *cs) return ret; } +void kvm_arch_on_sigbus_vcpu(CPUState *c, int code, void *addr) +{ + ARMCPU *cpu = ARM_CPU(c); + CPUARMState *env = &cpu->env; + ram_addr_t ram_addr; + hwaddr paddr; + + assert(code == BUS_MCEERR_AR || code == BUS_MCEERR_AO); + + if (addr) { + ram_addr = qemu_ram_addr_from_host(addr); + if (ram_addr != RAM_ADDR_INVALID && + kvm_physical_memory_addr_from_host(c->kvm_state, addr, &paddr)) { + kvm_hwpoison_page_add(ram_addr); + /* Asynchronous signal will be masked by main thread, so + * only handle synchronous signal. + */ + if (code == BUS_MCEERR_AR) { + kvm_cpu_synchronize_state(c); + if (GHES_CPER_FAIL != ghes_record_errors(ACPI_HEST_NOTIFY_SEA, paddr)) { + kvm_inject_arm_sea(c); + } else { + fprintf(stderr, "failed to record the error\n"); + } + } + return; + } + fprintf(stderr, "Hardware memory error for memory used by " + "QEMU itself instead of guest system!\n"); + } + + if (code == BUS_MCEERR_AR) { + fprintf(stderr, "Hardware memory error!\n"); + exit(1); + } +} + /* C6.6.29 BRK instruction */ static const uint32_t brk_insn = 0xd4200000; -- 1.8.3.1 In the ARMv8 platform, the CPU error types includes synchronous external abort(SEA) and SError Interrupt (SEI). If exception happens in guest, host does not know the detailed information of guest, so it is expected that guest can do the recovery. For example, if an exception happens in a guest user-space application, host does not know which application encounters errors, only guest knows it. For the ARMv8 SEA/SEI, KVM or host kernel delivers SIGBUS to notify userspace. After user space gets the notification, it will record the CPER into guest GHES buffer and inject an exception or IRQ to guest. In the current implementation, if the type of SIGBUS is BUS_MCEERR_AR, we will treat it as a synchronous exception, and notify guest with ARMv8 SEA notification type after recording CPER into guest. A) This series of patches are based on Qemu 4.2, which include two parts: 1. Generate APEI/GHES table. 2. Handle the SIGBUS signal, record the CPER in runtime and fill it into guest memory, then notify guest according to the type of SIGBUS. B) The solution was suggested by James(james.morse@arm.com); The APEI part solution was suggested by Laszlo(lersek@redhat.com). Show some discussions in [1]. C) This series of patches have already been tested on ARM64 platform with RAS feature enabled: 1. Show the APEI part verification result in [2]. 2. Show the SIGBUS of BUS_MCEERR_AR handling verification result in [3]. D) Add 'ras' option in command Line to enable guest RAS error recovery feature, For example: KVM model: ./qemu-system-aarch64 --enable-kvm -cpu host --bios QEMU_EFI.fd_new -machine virt,gic-version=3,ras,kernel-irqchip=on -smp 4 -nographic -kernel Image -append "rdinit=/init console=ttyAMA0 mem=512M root=/dev/ram0" -initrd guestfs_new.cpio.gz TCG model: ./qemu-system-aarch64 -cpu cortex-a57 --bios QEMU_EFI.fd_new -machine virt,gic-version=3,ras,kernel-irqchip=on -smp 4 -nographic -kernel Image -append "rdinit=/init console=ttyAMA0 mem=512M root=/dev/ram0" -initrd guestfs_new.cpio.gz --- Change since v23: 1. fix a warning for uuid Change since v22: 1. Using 1 * KiB instead of 0x400 to define max size of one error block 2. Make the alignment to 8 bytes in bios_linker_loader_alloc() 3. Change "Copyright (c) 2019" to "Copyright (c) 2020" in file header 4. Fix some code style warnings/errors and add some comments in code 5. Address Jonathan's comments to easily support CCIX error injection 6. Add vmstate_ghes_state .subsections in vmstate_acpi_ged Change since v21: 1. Make the user-facing 'ras' option description more clearly to address Peter's comments. 2. Update the doc description in "docs/specs/acpi_hest_ghes.rst" 3. Split HEST/GHES patches to more patches to make the review easily 4. Using source_id to index the location to save the CPER. 5. Optimize and simplify the logic to build HEST/GHES table to address Igor/Michael/Beata comments. 6. make ghes_addr_le a part of GED device. Change since v20: 1. Move some implementation details from acpi_ghes.h to acpi_ghes.c 2. Add the reviewers for the ACPI/APEI/GHES part Change since v19: 1. Fix clang compile error 2. Fix sphinx build error Change since v18: 1. Fix some code-style and typo/grammar problems. 2. Remove no_ras in the VirtMachineClass struct. 3. Convert documentation to rst format. 4. Simplize the code and add comments for some magic value. 5. Move kvm_inject_arm_sea() function into the patch where it's used. 6. Register the reset handler(kvm_unpoison_all()) in the kvm_init() function. Change since v17: 1. Improve some commit messages and comments. 2. Fix some code-style problems. 3. Add a *ras* machine option. 4. Move HEST/GHES related structures and macros into "hw/acpi/acpi_ghes.*". 5. Move HWPoison page functions into "include/sysemu/kvm_int.h". 6. Fix some bugs. 7. Improve the design document. Change since v16: 1. check whether ACPI table is enabled when handling the memory error in the SIGBUS handler. Change since v15: 1. Add a doc-comment in the proper format for 'include/exec/ram_addr.h' 2. Remove write_part_cpustate_to_list() because there is another bug fix patch has been merged "arm: Allow system registers for KVM guests to be changed by QEMU code" 3. Add some comments for kvm_inject_arm_sea() in 'target/arm/kvm64.c' 4. Compare the arm_current_el() return value to 0,1,2,3, not to PSTATE_MODE_* constants. 5. Change the RAS support wasn't introduced before 4.1 QEMU version. 6. Move the no_ras flag patch to begin in this series Change since v14: 1. Remove the BUS_MCEERR_AO handling logic because this asynchronous signal was masked by main thread 2. Address some Igor Mammedov's comments(ACPI part) 1) change the comments for the enum AcpiHestNotifyType definition and remove ditto in patch 1 2) change some patch commit messages and separate "APEI GHES table generation" patch to more patches. 3. Address some peter's comments(arm64 Synchronous External Abort injection) 1) change some code notes 2) using arm_current_el() for current EL 2) use the helper functions for those (syn_data_abort_*). Change since v13: 1. Move the patches that set guest ESR and inject virtual SError out of this series 2. Clean and optimize the APEI part patches 3. Update the commit messages and add some comments for the code Change since v12: 1. Address Paolo's comments to move HWPoisonPage definition to accel/kvm/kvm-all.c 2. Only call kvm_cpu_synchronize_state() when get the BUS_MCEERR_AR signal 3. Only add and enable GPIO-Signal and ARMv8 SEA two hardware error sources 4. Address Michael's comments to not sync SPDX from Linux kernel header file Change since v11: Address James's comments(james.morse@arm.com) 1. Check whether KVM has the capability to to set ESR instead of detecting host CPU RAS capability 2. For SIGBUS_MCEERR_AR SIGBUS, use Synchronous-External-Abort(SEA) notification type for SIGBUS_MCEERR_AO SIGBUS, use GPIO-Signal notification Address Shannon's comments(for ACPI part): 1. Unify hest_ghes.c and hest_ghes.h license declaration 2. Remove unnecessary including "qmp-commands.h" in hest_ghes.c 3. Unconditionally add guest APEI table based on James's comments(james.morse@arm.com) 4. Add a option to virt machine for migration compatibility. On new virt machine it's on by default while off for old ones, we enabled it since 2.12 5. Refer to the ACPI spec version which introduces Hardware Error Notification first time 6. Add ACPI_HEST_NOTIFY_RESERVED notification type Address Igor's comments(for ACPI part): 1. Add doc patch first which will describe how it's supposed to work between QEMU/firmware/guest OS with expected flows. 2. Move APEI diagrams into doc/spec patch 3. Remove redundant g_malloc in ghes_record_cper() 4. Use build_append_int_noprefix() API to compose whole error status block and whole APEI table, and try to get rid of most structures in patch 1, as they will be left unused after that 5. Reuse something like https://github.com/imammedo/qemu/commit/3d2fd6d13a3ea298d2ee814835495ce6241d085c to build GAS 6. Remove much offsetof() in the function 7. Build independent tables first and only then build dependent tables passing to it pointers to previously build table if necessary. 8. Redefine macro GHES_ACPI_HEST_NOTIFY_RESERVED to ACPI_HEST_ERROR_SOURCE_COUNT to avoid confusion Address Peter Maydell's comments 1. linux-headers is done as a patch of their own created using scripts/update-linux-headers.sh run against a mainline kernel tree 2. Tested whether this patchset builds OK on aarch32 3. Abstract Hwpoison page adding code out properly into a cpu-independent source file from target/i386/kvm.c, such as kvm-all.c 4. Add doc-comment formatted documentation comment for new globally-visible function prototype in a header --- [1]: https://lkml.org/lkml/2017/2/27/246 https://patchwork.kernel.org/patch/9633105/ https://patchwork.kernel.org/patch/9925227/ [2]: Note: the UEFI(QEMU_EFI.fd) is needed if guest want to use ACPI table. After guest boot up, dump the APEI table, then can see the initialized table (1) # iasl -p ./HEST -d /sys/firmware/acpi/tables/HEST (2) # cat HEST.dsl /* * Intel ACPI Component Architecture * AML/ASL+ Disassembler version 20170728 (64-bit version) * Copyright (c) 2000 - 2017 Intel Corporation * * Disassembly of /sys/firmware/acpi/tables/HEST, Mon Sep 5 07:59:17 2016 * * ACPI Data Table [HEST] * * Format: [HexOffset DecimalOffset ByteLength] FieldName : FieldValue */ .................................................................................. [308h 0776 2] Subtable Type : 000A [Generic Hardware Error Source V2] [30Ah 0778 2] Source Id : 0001 [30Ch 0780 2] Related Source Id : FFFF [30Eh 0782 1] Reserved : 00 [30Fh 0783 1] Enabled : 01 [310h 0784 4] Records To Preallocate : 00000001 [314h 0788 4] Max Sections Per Record : 00000001 [318h 0792 4] Max Raw Data Length : 00001000 [31Ch 0796 12] Error Status Address : [Generic Address Structure] [31Ch 0796 1] Space ID : 00 [SystemMemory] [31Dh 0797 1] Bit Width : 40 [31Eh 0798 1] Bit Offset : 00 [31Fh 0799 1] Encoded Access Width : 04 [QWord Access:64] [320h 0800 8] Address : 00000000785D0040 [328h 0808 28] Notify : [Hardware Error Notification Structure] [328h 0808 1] Notify Type : 08 [SEA] [329h 0809 1] Notify Length : 1C [32Ah 0810 2] Configuration Write Enable : 0000 [32Ch 0812 4] PollInterval : 00000000 [330h 0816 4] Vector : 00000000 [334h 0820 4] Polling Threshold Value : 00000000 [338h 0824 4] Polling Threshold Window : 00000000 [33Ch 0828 4] Error Threshold Value : 00000000 [340h 0832 4] Error Threshold Window : 00000000 [344h 0836 4] Error Status Block Length : 00001000 [348h 0840 12] Read Ack Register : [Generic Address Structure] [348h 0840 1] Space ID : 00 [SystemMemory] [349h 0841 1] Bit Width : 40 [34Ah 0842 1] Bit Offset : 00 [34Bh 0843 1] Encoded Access Width : 04 [QWord Access:64] [34Ch 0844 8] Address : 00000000785D0098 [354h 0852 8] Read Ack Preserve : 00000000FFFFFFFE [35Ch 0860 8] Read Ack Write : 0000000000000001 ..................................................................................... (3) After a synchronous external abort(SEA) happen, Qemu receive a SIGBUS and filled the CPER into guest GHES memory. For example, according to above table, the address that contains the physical address of a block of memory that holds the error status data is 0x00000000785D0040 (4) the address of error source which is SEA notification type is 0x785d80b0 (qemu) xp /1 0x00000000785D0040 00000000785d0040: 0x785d80b0 (5) check the content of generic error status block and generic error data entry (qemu) xp /100x 0x785d80b0 00000000785d80b0: 0x00000001 0x00000000 0x00000000 0x00000098 00000000785d80c0: 0x00000000 0xa5bc1114 0x4ede6f64 0x833e63b8 00000000785d80d0: 0xb1837ced 0x00000000 0x00000300 0x00000050 00000000785d80e0: 0x00000000 0x00000000 0x00000000 0x00000000 00000000785d80f0: 0x00000000 0x00000000 0x00000000 0x00000000 00000000785d8100: 0x00000000 0x00000000 0x00000000 0x00004002 (6) check the OSPM's ACK value(for example SEA) /* Before OSPM acknowledges the error, check the ACK value */ (qemu) xp /1 0x00000000785D0098 00000000785d00f0: 0x00000000 /* After OSPM acknowledges the error, check the ACK value, it change to 1 from 0 */ (qemu) xp /1 0x00000000785D0098 00000000785d00f0: 0x00000001 [3]: KVM deliver "BUS_MCEERR_AR" to Qemu, Qemu record the guest CPER and inject synchronous external abort to notify guest, then guest do the recovery. [ 1552.516170] Synchronous External Abort: synchronous external abort (0x92000410) at 0x000000003751c6b4 [ 1553.074073] {1}[Hardware Error]: Hardware error from APEI Generic Hardware Error Source: 8 [ 1553.081654] {1}[Hardware Error]: event severity: recoverable [ 1554.034191] {1}[Hardware Error]: Error 0, type: recoverable [ 1554.037934] {1}[Hardware Error]: section_type: memory error [ 1554.513261] {1}[Hardware Error]: physical_address: 0x0000000040fa6000 [ 1554.513944] {1}[Hardware Error]: error_type: 0, unknown [ 1555.041451] Memory failure: 0x40fa6: Killing mca-recover:1296 due to hardware memory corruption [ 1555.373116] Memory failure: 0x40fa6: recovery action for dirty LRU page: Recovered Dongjiu Geng (10): acpi: nvdimm: change NVDIMM_UUID_LE to a common macro hw/arm/virt: Introduce a RAS machine option docs: APEI GHES generation and CPER record description ACPI: Build related register address fields via hardware error fw_cfg blob ACPI: Build Hardware Error Source Table ACPI: Record the Generic Error Status Block address KVM: Move hwpoison page related functions into kvm-all.c ACPI: Record Generic Error Status Block(GESB) table target-arm: kvm64: handle SIGBUS signal from kernel or KVM MAINTAINERS: Add ACPI/HEST/GHES entries MAINTAINERS | 9 + accel/kvm/kvm-all.c | 36 +++ default-configs/arm-softmmu.mak | 1 + docs/specs/acpi_hest_ghes.rst | 110 ++++++++ docs/specs/index.rst | 1 + hw/acpi/Kconfig | 4 + hw/acpi/Makefile.objs | 1 + hw/acpi/aml-build.c | 2 + hw/acpi/generic_event_device.c | 19 ++ hw/acpi/ghes.c | 448 +++++++++++++++++++++++++++++++++ hw/acpi/nvdimm.c | 10 +- hw/arm/virt-acpi-build.c | 15 ++ hw/arm/virt.c | 23 ++ include/hw/acpi/aml-build.h | 1 + include/hw/acpi/generic_event_device.h | 2 + include/hw/acpi/ghes.h | 74 ++++++ include/hw/arm/virt.h | 1 + include/qemu/uuid.h | 27 ++ include/sysemu/kvm.h | 3 +- include/sysemu/kvm_int.h | 12 + target/arm/cpu.h | 4 + target/arm/helper.c | 2 +- target/arm/internals.h | 5 +- target/arm/kvm64.c | 77 ++++++ target/arm/tlb_helper.c | 2 +- target/i386/cpu.h | 2 + target/i386/kvm.c | 36 --- 27 files changed, 878 insertions(+), 49 deletions(-) create mode 100644 docs/specs/acpi_hest_ghes.rst create mode 100644 hw/acpi/ghes.c create mode 100644 include/hw/acpi/ghes.h -- 1.8.3.1 The little end UUID is used in many places, so make NVDIMM_UUID_LE to a common macro to convert the UUID to a little end array. Reviewed-by: Xiang Zheng <zhengxiang9@huawei.com> Signed-off-by: Dongjiu Geng <gengdongjiu@huawei.com> --- Change since v25: 1. Address Peter's comments to add a proper doc-comment comment for UUID_LE macros. --- hw/acpi/nvdimm.c | 10 +++------- include/qemu/uuid.h | 27 +++++++++++++++++++++++++++ 2 files changed, 30 insertions(+), 7 deletions(-) diff --git a/hw/acpi/nvdimm.c b/hw/acpi/nvdimm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/acpi/nvdimm.c +++ b/hw/acpi/nvdimm.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" +#include "qemu/uuid.h" #include "hw/acpi/acpi.h" #include "hw/acpi/aml-build.h" #include "hw/acpi/bios-linker-loader.h" @@ -XXX,XX +XXX,XX @@ #include "hw/mem/nvdimm.h" #include "qemu/nvdimm-utils.h" -#define NVDIMM_UUID_LE(a, b, c, d0, d1, d2, d3, d4, d5, d6, d7) \ - { (a) & 0xff, ((a) >> 8) & 0xff, ((a) >> 16) & 0xff, ((a) >> 24) & 0xff, \ - (b) & 0xff, ((b) >> 8) & 0xff, (c) & 0xff, ((c) >> 8) & 0xff, \ - (d0), (d1), (d2), (d3), (d4), (d5), (d6), (d7) } - /* * define Byte Addressable Persistent Memory (PM) Region according to * ACPI 6.0: 5.2.25.1 System Physical Address Range Structure. */ static const uint8_t nvdimm_nfit_spa_uuid[] = - NVDIMM_UUID_LE(0x66f0d379, 0xb4f3, 0x4074, 0xac, 0x43, 0x0d, 0x33, - 0x18, 0xb7, 0x8c, 0xdb); + UUID_LE(0x66f0d379, 0xb4f3, 0x4074, 0xac, 0x43, 0x0d, 0x33, + 0x18, 0xb7, 0x8c, 0xdb); /* * NVDIMM Firmware Interface Table diff --git a/include/qemu/uuid.h b/include/qemu/uuid.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/uuid.h +++ b/include/qemu/uuid.h @@ -XXX,XX +XXX,XX @@ typedef struct { }; } QemuUUID; +/** + * UUID_LE - converts the fields of UUID to little-endian array, + * each of parameters is the filed of UUID. + * + * @time_low: The low field of the timestamp + * @time_mid: The middle field of the timestamp + * @time_hi_and_version: The high field of the timestamp + * multiplexed with the version number + * @clock_seq_hi_and_reserved: The high field of the clock + * sequence multiplexed with the variant + * @clock_seq_low: The low field of the clock sequence + * @node0: The spatially unique node0 identifier + * @node1: The spatially unique node1 identifier + * @node2: The spatially unique node2 identifier + * @node3: The spatially unique node3 identifier + * @node4: The spatially unique node4 identifier + * @node5: The spatially unique node5 identifier + */ +#define UUID_LE(time_low, time_mid, time_hi_and_version, \ + clock_seq_hi_and_reserved, clock_seq_low, node0, node1, node2, \ + node3, node4, node5) \ + { (time_low) & 0xff, ((time_low) >> 8) & 0xff, ((time_low) >> 16) & 0xff, \ + ((time_low) >> 24) & 0xff, (time_mid) & 0xff, ((time_mid) >> 8) & 0xff, \ + (time_hi_and_version) & 0xff, ((time_hi_and_version) >> 8) & 0xff, \ + (clock_seq_hi_and_reserved), (clock_seq_low), (node0), (node1), (node2),\ + (node3), (node4), (node5) } + #define UUID_FMT "%02hhx%02hhx%02hhx%02hhx-" \ "%02hhx%02hhx-%02hhx%02hhx-" \ "%02hhx%02hhx-" \ -- 1.8.3.1 RAS Virtualization feature is not supported now, so add a RAS machine option and disable it by default. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Dongjiu Geng <gengdongjiu@huawei.com> Signed-off-by: Xiang Zheng <zhengxiang9@huawei.com> Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com> Reviewed-by: Igor Mammedov <imammedo@redhat.com> --- hw/arm/virt.c | 23 +++++++++++++++++++++++ include/hw/arm/virt.h | 1 + 2 files changed, 24 insertions(+) diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ static void virt_set_acpi(Object *obj, Visitor *v, const char *name, visit_type_OnOffAuto(v, name, &vms->acpi, errp); } +static bool virt_get_ras(Object *obj, Error **errp) +{ + VirtMachineState *vms = VIRT_MACHINE(obj); + + return vms->ras; +} + +static void virt_set_ras(Object *obj, bool value, Error **errp) +{ + VirtMachineState *vms = VIRT_MACHINE(obj); + + vms->ras = value; +} + static char *virt_get_gic_version(Object *obj, Error **errp) { VirtMachineState *vms = VIRT_MACHINE(obj); @@ -XXX,XX +XXX,XX @@ static void virt_instance_init(Object *obj) "Valid values are none and smmuv3", NULL); + /* Default disallows RAS instantiation */ + vms->ras = false; + object_property_add_bool(obj, "ras", virt_get_ras, + virt_set_ras, NULL); + object_property_set_description(obj, "ras", + "Set on/off to enable/disable reporting host memory errors " + "to a KVM guest using ACPI and guest external abort exceptions", + NULL); + vms->irqmap = a15irqmap; virt_flash_create(vms); diff --git a/include/hw/arm/virt.h b/include/hw/arm/virt.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/virt.h +++ b/include/hw/arm/virt.h @@ -XXX,XX +XXX,XX @@ typedef struct { bool highmem_ecam; bool its; bool virt; + bool ras; OnOffAuto acpi; VirtGICType gic_version; VirtIOMMUType iommu; -- 1.8.3.1 Add APEI/GHES detailed design document Signed-off-by: Dongjiu Geng <gengdongjiu@huawei.com> Signed-off-by: Xiang Zheng <zhengxiang9@huawei.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Reviewed-by: Igor Mammedov <imammedo@redhat.com> --- docs/specs/acpi_hest_ghes.rst | 110 ++++++++++++++++++++++++++++++++++++++++++ docs/specs/index.rst | 1 + 2 files changed, 111 insertions(+) create mode 100644 docs/specs/acpi_hest_ghes.rst diff --git a/docs/specs/acpi_hest_ghes.rst b/docs/specs/acpi_hest_ghes.rst new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/docs/specs/acpi_hest_ghes.rst @@ -XXX,XX +XXX,XX @@ +APEI tables generating and CPER record +====================================== + +.. + Copyright (c) 2020 HUAWEI TECHNOLOGIES CO., LTD. + + This work is licensed under the terms of the GNU GPL, version 2 or later. + See the COPYING file in the top-level directory. + +Design Details +-------------- + +:: + + etc/acpi/tables etc/hardware_errors + ==================== =============================== + + +--------------------------+ +----------------------------+ + | | HEST | +--------->| error_block_address1 |------+ + | +--------------------------+ | +----------------------------+ | + | | GHES1 | | +------->| error_block_address2 |------+-+ + | +--------------------------+ | | +----------------------------+ | | + | | ................. | | | | .............. | | | + | | error_status_address-----+-+ | -----------------------------+ | | + | | ................. | | +--->| error_block_addressN |------+-+---+ + | | read_ack_register--------+-+ | | +----------------------------+ | | | + | | read_ack_preserve | +-+---+--->| read_ack_register1 | | | | + | | read_ack_write | | | +----------------------------+ | | | + + +--------------------------+ | +-+--->| read_ack_register2 | | | | + | | GHES2 | | | | +----------------------------+ | | | + + +--------------------------+ | | | | ............. | | | | + | | ................. | | | | +----------------------------+ | | | + | | error_status_address-----+---+ | | +->| read_ack_registerN | | | | + | | ................. | | | | +----------------------------+ | | | + | | read_ack_register--------+-----+ | | |Generic Error Status Block 1|<-----+ | | + | | read_ack_preserve | | | |-+------------------------+-+ | | + | | read_ack_write | | | | | CPER | | | | + + +--------------------------| | | | | CPER | | | | + | | ............... | | | | | .... | | | | + + +--------------------------+ | | | | CPER | | | | + | | GHESN | | | |-+------------------------+-| | | + + +--------------------------+ | | |Generic Error Status Block 2|<-------+ | + | | ................. | | | |-+------------------------+-+ | + | | error_status_address-----+-------+ | | | CPER | | | + | | ................. | | | | CPER | | | + | | read_ack_register--------+---------+ | | .... | | | + | | read_ack_preserve | | | CPER | | | + | | read_ack_write | +-+------------------------+-+ | + + +--------------------------+ | .......... | | + |----------------------------+ | + |Generic Error Status Block N |<----------+ + |-+-------------------------+-+ + | | CPER | | + | | CPER | | + | | .... | | + | | CPER | | + +-+-------------------------+-+ + + +(1) QEMU generates the ACPI HEST table. This table goes in the current + "etc/acpi/tables" fw_cfg blob. Each error source has different + notification types. + +(2) A new fw_cfg blob called "etc/hardware_errors" is introduced. QEMU + also needs to populate this blob. The "etc/hardware_errors" fw_cfg blob + contains an address registers table and an Error Status Data Block table. + +(3) The address registers table contains N Error Block Address entries + and N Read Ack Register entries. The size for each entry is 8-byte. + The Error Status Data Block table contains N Error Status Data Block + entries. The size for each entry is 4096(0x1000) bytes. The total size + for the "etc/hardware_errors" fw_cfg blob is (N * 8 * 2 + N * 4096) bytes. + N is the number of the kinds of hardware error sources. + +(4) QEMU generates the ACPI linker/loader script for the firmware. The + firmware pre-allocates memory for "etc/acpi/tables", "etc/hardware_errors" + and copies blob contents there. + +(5) QEMU generates N ADD_POINTER commands, which patch addresses in the + "error_status_address" fields of the HEST table with a pointer to the + corresponding "address registers" in the "etc/hardware_errors" blob. + +(6) QEMU generates N ADD_POINTER commands, which patch addresses in the + "read_ack_register" fields of the HEST table with a pointer to the + corresponding "read_ack_register" within the "etc/hardware_errors" blob. + +(7) QEMU generates N ADD_POINTER commands for the firmware, which patch + addresses in the "error_block_address" fields with a pointer to the + respective "Error Status Data Block" in the "etc/hardware_errors" blob. + +(8) QEMU defines a third and write-only fw_cfg blob which is called + "etc/hardware_errors_addr". Through that blob, the firmware can send back + the guest-side allocation addresses to QEMU. The "etc/hardware_errors_addr" + blob contains a 8-byte entry. QEMU generates a single WRITE_POINTER command + for the firmware. The firmware will write back the start address of + "etc/hardware_errors" blob to the fw_cfg file "etc/hardware_errors_addr". + +(9) When QEMU gets a SIGBUS from the kernel, QEMU writes CPER into corresponding + "Error Status Data Block", guest memory, and then injects platform specific + interrupt (in case of arm/virt machine it's Synchronous External Abort) as a + notification which is necessary for notifying the guest. + +(10) This notification (in virtual hardware) will be handled by the guest + kernel, on receiving notification, guest APEI driver could read the CPER error + and take appropriate action. + +(11) kvm_arch_on_sigbus_vcpu() uses source_id as index in "etc/hardware_errors" to + find out "Error Status Data Block" entry corresponding to error source. So supported + source_id values should be assigned here and not be changed afterwards to make sure + that guest will write error into expected "Error Status Data Block" even if guest was + migrated to a newer QEMU. diff --git a/docs/specs/index.rst b/docs/specs/index.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/specs/index.rst +++ b/docs/specs/index.rst @@ -XXX,XX +XXX,XX @@ Contents: ppc-spapr-xive acpi_hw_reduced_hotplug tpm + acpi_hest_ghes -- 1.8.3.1 This patch builds error_block_address and read_ack_register fields in hardware errors table , the error_block_address points to Generic Error Status Block(GESB) via bios_linker. The max size for one GESB is 1kb, For more detailed information, please refer to document: docs/specs/acpi_hest_ghes.rst Now we only support one Error source, if necessary, we can extend to support more. Suggested-by: Laszlo Ersek <lersek@redhat.com> Signed-off-by: Xiang Zheng <zhengxiang9@huawei.com> Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com> Reviewed-by: Igor Mammedov <imammedo@redhat.com> Signed-off-by: Dongjiu Geng <gengdongjiu@huawei.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> --- default-configs/arm-softmmu.mak | 1 + hw/acpi/Kconfig | 4 ++ hw/acpi/Makefile.objs | 1 + hw/acpi/aml-build.c | 2 + hw/acpi/ghes.c | 89 +++++++++++++++++++++++++++++++++++++++++ hw/arm/virt-acpi-build.c | 5 +++ include/hw/acpi/aml-build.h | 1 + include/hw/acpi/ghes.h | 28 +++++++++++++ 8 files changed, 131 insertions(+) create mode 100644 hw/acpi/ghes.c create mode 100644 include/hw/acpi/ghes.h diff --git a/default-configs/arm-softmmu.mak b/default-configs/arm-softmmu.mak index XXXXXXX..XXXXXXX 100644 --- a/default-configs/arm-softmmu.mak +++ b/default-configs/arm-softmmu.mak @@ -XXX,XX +XXX,XX @@ CONFIG_FSL_IMX7=y CONFIG_FSL_IMX6UL=y CONFIG_SEMIHOSTING=y CONFIG_ALLWINNER_H3=y +CONFIG_ACPI_APEI=y diff --git a/hw/acpi/Kconfig b/hw/acpi/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/acpi/Kconfig +++ b/hw/acpi/Kconfig @@ -XXX,XX +XXX,XX @@ config ACPI_HMAT bool depends on ACPI +config ACPI_APEI + bool + depends on ACPI + config ACPI_PCI bool depends on ACPI && PCI diff --git a/hw/acpi/Makefile.objs b/hw/acpi/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/acpi/Makefile.objs +++ b/hw/acpi/Makefile.objs @@ -XXX,XX +XXX,XX @@ common-obj-$(CONFIG_ACPI_NVDIMM) += nvdimm.o common-obj-$(CONFIG_ACPI_VMGENID) += vmgenid.o common-obj-$(CONFIG_ACPI_HW_REDUCED) += generic_event_device.o common-obj-$(CONFIG_ACPI_HMAT) += hmat.o +common-obj-$(CONFIG_ACPI_APEI) += ghes.o common-obj-$(call lnot,$(CONFIG_ACPI_X86)) += acpi-stub.o common-obj-$(call lnot,$(CONFIG_PC)) += acpi-x86-stub.o diff --git a/hw/acpi/aml-build.c b/hw/acpi/aml-build.c index XXXXXXX..XXXXXXX 100644 --- a/hw/acpi/aml-build.c +++ b/hw/acpi/aml-build.c @@ -XXX,XX +XXX,XX @@ void acpi_build_tables_init(AcpiBuildTables *tables) tables->table_data = g_array_new(false, true /* clear */, 1); tables->tcpalog = g_array_new(false, true /* clear */, 1); tables->vmgenid = g_array_new(false, true /* clear */, 1); + tables->hardware_errors = g_array_new(false, true /* clear */, 1); tables->linker = bios_linker_loader_init(); } @@ -XXX,XX +XXX,XX @@ void acpi_build_tables_cleanup(AcpiBuildTables *tables, bool mfre) g_array_free(tables->table_data, true); g_array_free(tables->tcpalog, mfre); g_array_free(tables->vmgenid, mfre); + g_array_free(tables->hardware_errors, mfre); } /* diff --git a/hw/acpi/ghes.c b/hw/acpi/ghes.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/acpi/ghes.c @@ -XXX,XX +XXX,XX @@ +/* + * Support for generating APEI tables and recording CPER for Guests + * + * Copyright (c) 2020 HUAWEI TECHNOLOGIES CO., LTD. + * + * Author: Dongjiu Geng <gengdongjiu@huawei.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + + * You should have received a copy of the GNU General Public License along + * with this program; if not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" +#include "qemu/units.h" +#include "hw/acpi/ghes.h" +#include "hw/acpi/aml-build.h" + +#define ACPI_GHES_ERRORS_FW_CFG_FILE "etc/hardware_errors" +#define ACPI_GHES_DATA_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 + +/* + * Build table for the hardware error fw_cfg blob. + * 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) +{ + int i, error_status_block_offset; + + /* Build error_block_address */ + for (i = 0; i < ACPI_GHES_ERROR_SOURCE_COUNT; i++) { + build_append_int_noprefix(hardware_errors, 0, sizeof(uint64_t)); + } + + /* Build read_ack_register */ + for (i = 0; i < ACPI_GHES_ERROR_SOURCE_COUNT; i++) { + /* + * Initialize the value of read_ack_register to 1, so GHES can be + * writeable after (re)boot. + * ACPI 6.2: 18.3.2.8 Generic Hardware Error Source version 2 + * (GHESv2 - Type 10) + */ + build_append_int_noprefix(hardware_errors, 1, sizeof(uint64_t)); + } + + /* Generic Error Status Block offset in the hardware error fw_cfg blob */ + error_status_block_offset = hardware_errors->len; + + /* Reserve space for Error Status Data Block */ + acpi_data_push(hardware_errors, + 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, + hardware_errors, sizeof(uint64_t), false); + + for (i = 0; i < ACPI_GHES_ERROR_SOURCE_COUNT; i++) { + /* + * Tell firmware to patch error_block_address entries to point to + * 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); + } + + /* + * 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); +} diff --git a/hw/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt-acpi-build.c +++ b/hw/arm/virt-acpi-build.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/reset.h" #include "kvm_arm.h" #include "migration/vmstate.h" +#include "hw/acpi/ghes.h" #define ARM_SPI_BASE 32 @@ -XXX,XX +XXX,XX @@ void virt_acpi_build(VirtMachineState *vms, AcpiBuildTables *tables) acpi_add_table(table_offsets, tables_blob); build_spcr(tables_blob, tables->linker, vms); + if (vms->ras) { + build_ghes_error_table(tables->hardware_errors, tables->linker); + } + if (ms->numa_state->num_nodes > 0) { acpi_add_table(table_offsets, tables_blob); build_srat(tables_blob, tables->linker, vms); diff --git a/include/hw/acpi/aml-build.h b/include/hw/acpi/aml-build.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/acpi/aml-build.h +++ b/include/hw/acpi/aml-build.h @@ -XXX,XX +XXX,XX @@ struct AcpiBuildTables { GArray *rsdp; GArray *tcpalog; GArray *vmgenid; + GArray *hardware_errors; BIOSLinker *linker; } AcpiBuildTables; diff --git a/include/hw/acpi/ghes.h b/include/hw/acpi/ghes.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/acpi/ghes.h @@ -XXX,XX +XXX,XX @@ +/* + * Support for generating APEI tables and recording CPER for Guests + * + * Copyright (c) 2020 HUAWEI TECHNOLOGIES CO., LTD. + * + * Author: Dongjiu Geng <gengdongjiu@huawei.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + + * You should have received a copy of the GNU General Public License along + * with this program; if not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef ACPI_GHES_H +#define ACPI_GHES_H + +#include "hw/acpi/bios-linker-loader.h" + +void build_ghes_error_table(GArray *hardware_errors, BIOSLinker *linker); +#endif -- 1.8.3.1 This patch builds Hardware Error Source Table(HEST) via fw_cfg blobs. Now it only supports ARMv8 SEA, a type of Generic Hardware Error Source version 2(GHESv2) error source. Afterwards, we can extend the supported types if needed. For the CPER section, currently it is memory section because kernel mainly wants userspace to handle the memory errors. This patch follows the spec ACPI 6.2 to build the Hardware Error Source table. For more detailed information, please refer to document: docs/specs/acpi_hest_ghes.rst build_ghes_hw_error_notification() helper will help to add Hardware Error Notification to ACPI tables without using packed C structures and avoid endianness issues as API doesn't need explicit conversion. Signed-off-by: Xiang Zheng <zhengxiang9@huawei.com> Signed-off-by: Dongjiu Geng <gengdongjiu@huawei.com> Reviewed-by: Igor Mammedov <imammedo@redhat.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> --- hw/acpi/ghes.c | 126 +++++++++++++++++++++++++++++++++++++++++++++++ hw/arm/virt-acpi-build.c | 2 + include/hw/acpi/ghes.h | 39 +++++++++++++++ 3 files changed, 167 insertions(+) diff --git a/hw/acpi/ghes.c b/hw/acpi/ghes.c index XXXXXXX..XXXXXXX 100644 --- a/hw/acpi/ghes.c +++ b/hw/acpi/ghes.c @@ -XXX,XX +XXX,XX @@ #include "qemu/units.h" #include "hw/acpi/ghes.h" #include "hw/acpi/aml-build.h" +#include "qemu/error-report.h" #define ACPI_GHES_ERRORS_FW_CFG_FILE "etc/hardware_errors" #define ACPI_GHES_DATA_ADDR_FW_CFG_FILE "etc/hardware_errors_addr" @@ -XXX,XX +XXX,XX @@ /* 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 + +/* Address offset in Generic Address Structure(GAS) */ +#define GAS_ADDR_OFFSET 4 + +/* + * Hardware Error Notification + * ACPI 4.0: 17.3.2.7 Hardware Error Notification + * Composes dummy Hardware Error Notification descriptor of specified type + */ +static void build_ghes_hw_error_notification(GArray *table, const uint8_t type) +{ + /* Type */ + build_append_int_noprefix(table, type, 1); + /* + * Length: + * Total length of the structure in bytes + */ + build_append_int_noprefix(table, 28, 1); + /* Configuration Write Enable */ + build_append_int_noprefix(table, 0, 2); + /* Poll Interval */ + build_append_int_noprefix(table, 0, 4); + /* Vector */ + build_append_int_noprefix(table, 0, 4); + /* Switch To Polling Threshold Value */ + build_append_int_noprefix(table, 0, 4); + /* Switch To Polling Threshold Window */ + build_append_int_noprefix(table, 0, 4); + /* Error Threshold Value */ + build_append_int_noprefix(table, 0, 4); + /* Error Threshold Window */ + build_append_int_noprefix(table, 0, 4); +} + /* * Build table for the hardware error fw_cfg blob. * Initialize "etc/hardware_errors" and "etc/hardware_errors_addr" fw_cfg blobs. @@ -XXX,XX +XXX,XX @@ void build_ghes_error_table(GArray *hardware_errors, BIOSLinker *linker) bios_linker_loader_write_pointer(linker, ACPI_GHES_DATA_ADDR_FW_CFG_FILE, 0, sizeof(uint64_t), ACPI_GHES_ERRORS_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) +{ + uint64_t address_offset; + /* + * Type: + * Generic Hardware Error Source version 2(GHESv2 - Type 10) + */ + build_append_int_noprefix(table_data, ACPI_GHES_SOURCE_GENERIC_ERROR_V2, 2); + /* Source Id */ + build_append_int_noprefix(table_data, source_id, 2); + /* Related Source Id */ + build_append_int_noprefix(table_data, 0xffff, 2); + /* Flags */ + build_append_int_noprefix(table_data, 0, 1); + /* Enabled */ + build_append_int_noprefix(table_data, 1, 1); + + /* Number of Records To Pre-allocate */ + build_append_int_noprefix(table_data, 1, 4); + /* Max Sections Per Record */ + build_append_int_noprefix(table_data, 1, 4); + /* Max Raw Data Length */ + build_append_int_noprefix(table_data, ACPI_GHES_MAX_RAW_DATA_LENGTH, 4); + + address_offset = table_data->len; + /* Error Status Address */ + 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)); + + 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(); + } + + /* Error Status Block Length */ + build_append_int_noprefix(table_data, ACPI_GHES_MAX_RAW_DATA_LENGTH, 4); + + /* + * Read Ack Register + * ACPI 6.1: 18.3.2.8 Generic Hardware Error Source + * version 2 (GHESv2 - Type 10) + */ + address_offset = table_data->len; + 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)); + + /* + * Read Ack Preserve field + * We only provide the first bit in Read Ack Register to OSPM to write + * while the other bits are preserved. + */ + build_append_int_noprefix(table_data, ~0x1ULL, 8); + /* Read Ack Write */ + build_append_int_noprefix(table_data, 0x1, 8); +} + +/* Build Hardware Error Source Table */ +void acpi_build_hest(GArray *table_data, BIOSLinker *linker) +{ + uint64_t hest_start = table_data->len; + + /* Hardware Error Source Table header*/ + acpi_data_push(table_data, sizeof(AcpiTableHeader)); + + /* 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_header(linker, table_data, (void *)(table_data->data + hest_start), + "HEST", table_data->len - hest_start, 1, NULL, NULL); +} diff --git a/hw/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt-acpi-build.c +++ b/hw/arm/virt-acpi-build.c @@ -XXX,XX +XXX,XX @@ void virt_acpi_build(VirtMachineState *vms, AcpiBuildTables *tables) if (vms->ras) { build_ghes_error_table(tables->hardware_errors, tables->linker); + acpi_add_table(table_offsets, tables_blob); + acpi_build_hest(tables_blob, tables->linker); } if (ms->numa_state->num_nodes > 0) { diff --git a/include/hw/acpi/ghes.h b/include/hw/acpi/ghes.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/acpi/ghes.h +++ b/include/hw/acpi/ghes.h @@ -XXX,XX +XXX,XX @@ #include "hw/acpi/bios-linker-loader.h" +/* + * Values for Hardware Error Notification Type field + */ +enum AcpiGhesNotifyType { + /* Polled */ + ACPI_GHES_NOTIFY_POLLED = 0, + /* External Interrupt */ + ACPI_GHES_NOTIFY_EXTERNAL = 1, + /* Local Interrupt */ + ACPI_GHES_NOTIFY_LOCAL = 2, + /* SCI */ + ACPI_GHES_NOTIFY_SCI = 3, + /* NMI */ + ACPI_GHES_NOTIFY_NMI = 4, + /* CMCI, ACPI 5.0: 18.3.2.7, Table 18-290 */ + ACPI_GHES_NOTIFY_CMCI = 5, + /* MCE, ACPI 5.0: 18.3.2.7, Table 18-290 */ + ACPI_GHES_NOTIFY_MCE = 6, + /* GPIO-Signal, ACPI 6.0: 18.3.2.7, Table 18-332 */ + ACPI_GHES_NOTIFY_GPIO = 7, + /* ARMv8 SEA, ACPI 6.1: 18.3.2.9, Table 18-345 */ + ACPI_GHES_NOTIFY_SEA = 8, + /* ARMv8 SEI, ACPI 6.1: 18.3.2.9, Table 18-345 */ + ACPI_GHES_NOTIFY_SEI = 9, + /* External Interrupt - GSIV, ACPI 6.1: 18.3.2.9, Table 18-345 */ + ACPI_GHES_NOTIFY_GSIV = 10, + /* Software Delegated Exception, ACPI 6.2: 18.3.2.9, Table 18-383 */ + ACPI_GHES_NOTIFY_SDEI = 11, + /* 12 and greater are reserved */ + ACPI_GHES_NOTIFY_RESERVED = 12 +}; + +enum { + ACPI_HEST_SRC_ID_SEA = 0, + /* future ids go here */ + ACPI_HEST_SRC_ID_RESERVED, +}; + void build_ghes_error_table(GArray *hardware_errors, BIOSLinker *linker); +void acpi_build_hest(GArray *table_data, BIOSLinker *linker); #endif -- 1.8.3.1 Record the GHEB address via fw_cfg file, when recording a error to CPER, it will use this address to find out Generic Error Data Entries and write the error. In order to avoid migration failure, make hardware error table address to a part of GED device instead of global variable, then this address will be migrated to target QEMU. Acked-by: Xiang Zheng <zhengxiang9@huawei.com> Signed-off-by: Dongjiu Geng <gengdongjiu@huawei.com> Reviewed-by: Igor Mammedov <imammedo@redhat.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> --- hw/acpi/generic_event_device.c | 19 +++++++++++++++++++ hw/acpi/ghes.c | 14 ++++++++++++++ hw/arm/virt-acpi-build.c | 8 ++++++++ include/hw/acpi/generic_event_device.h | 2 ++ include/hw/acpi/ghes.h | 6 ++++++ 5 files changed, 49 insertions(+) diff --git a/hw/acpi/generic_event_device.c b/hw/acpi/generic_event_device.c index XXXXXXX..XXXXXXX 100644 --- a/hw/acpi/generic_event_device.c +++ b/hw/acpi/generic_event_device.c @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_ged_state = { } }; +static bool ghes_needed(void *opaque) +{ + AcpiGedState *s = opaque; + return s->ghes_state.ghes_addr_le; +} + +static const VMStateDescription vmstate_ghes_state = { + .name = "acpi-ged/ghes", + .version_id = 1, + .minimum_version_id = 1, + .needed = ghes_needed, + .fields = (VMStateField[]) { + VMSTATE_STRUCT(ghes_state, AcpiGedState, 1, + vmstate_ghes_state, AcpiGhesState), + VMSTATE_END_OF_LIST() + } +}; + static const VMStateDescription vmstate_acpi_ged = { .name = "acpi-ged", .version_id = 1, @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_acpi_ged = { }, .subsections = (const VMStateDescription * []) { &vmstate_memhp_state, + &vmstate_ghes_state, NULL } }; diff --git a/hw/acpi/ghes.c b/hw/acpi/ghes.c index XXXXXXX..XXXXXXX 100644 --- a/hw/acpi/ghes.c +++ b/hw/acpi/ghes.c @@ -XXX,XX +XXX,XX @@ #include "hw/acpi/ghes.h" #include "hw/acpi/aml-build.h" #include "qemu/error-report.h" +#include "hw/acpi/generic_event_device.h" +#include "hw/nvram/fw_cfg.h" #define ACPI_GHES_ERRORS_FW_CFG_FILE "etc/hardware_errors" #define ACPI_GHES_DATA_ADDR_FW_CFG_FILE "etc/hardware_errors_addr" @@ -XXX,XX +XXX,XX @@ void acpi_build_hest(GArray *table_data, BIOSLinker *linker) build_header(linker, table_data, (void *)(table_data->data + hest_start), "HEST", table_data->len - hest_start, 1, NULL, NULL); } + +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, + 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); +} diff --git a/hw/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt-acpi-build.c +++ b/hw/arm/virt-acpi-build.c @@ -XXX,XX +XXX,XX @@ void virt_acpi_setup(VirtMachineState *vms) { AcpiBuildTables tables; AcpiBuildState *build_state; + AcpiGedState *acpi_ged_state; if (!vms->fw_cfg) { trace_virt_acpi_setup(); @@ -XXX,XX +XXX,XX @@ void virt_acpi_setup(VirtMachineState *vms) fw_cfg_add_file(vms->fw_cfg, ACPI_BUILD_TPMLOG_FILE, tables.tcpalog->data, acpi_data_len(tables.tcpalog)); + if (vms->ras) { + assert(vms->acpi_dev); + acpi_ged_state = ACPI_GED(vms->acpi_dev); + acpi_ghes_add_fw_cfg(&acpi_ged_state->ghes_state, + vms->fw_cfg, tables.hardware_errors); + } + build_state->rsdp_mr = acpi_add_rom_blob(virt_acpi_build_update, build_state, tables.rsdp, ACPI_BUILD_RSDP_FILE, 0); diff --git a/include/hw/acpi/generic_event_device.h b/include/hw/acpi/generic_event_device.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/acpi/generic_event_device.h +++ b/include/hw/acpi/generic_event_device.h @@ -XXX,XX +XXX,XX @@ #include "hw/sysbus.h" #include "hw/acpi/memory_hotplug.h" +#include "hw/acpi/ghes.h" #define ACPI_POWER_BUTTON_DEVICE "PWRB" @@ -XXX,XX +XXX,XX @@ typedef struct AcpiGedState { GEDState ged_state; uint32_t ged_event_bitmap; qemu_irq irq; + AcpiGhesState ghes_state; } AcpiGedState; void build_ged_aml(Aml *table, const char* name, HotplugHandler *hotplug_dev, diff --git a/include/hw/acpi/ghes.h b/include/hw/acpi/ghes.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/acpi/ghes.h +++ b/include/hw/acpi/ghes.h @@ -XXX,XX +XXX,XX @@ enum { ACPI_HEST_SRC_ID_RESERVED, }; +typedef struct AcpiGhesState { + uint64_t ghes_addr_le; +} AcpiGhesState; + void build_ghes_error_table(GArray *hardware_errors, BIOSLinker *linker); void acpi_build_hest(GArray *table_data, BIOSLinker *linker); +void acpi_ghes_add_fw_cfg(AcpiGhesState *vms, FWCfgState *s, + GArray *hardware_errors); #endif -- 1.8.3.1 kvm_hwpoison_page_add() and kvm_unpoison_all() will both be used by X86 and ARM platforms, so moving them into "accel/kvm/kvm-all.c" to avoid duplicate code. For architectures that don't use the poison-list functionality the reset handler will harmlessly do nothing, so let's register the kvm_unpoison_all() function in the generic kvm_init() function. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Dongjiu Geng <gengdongjiu@huawei.com> Signed-off-by: Xiang Zheng <zhengxiang9@huawei.com> Acked-by: Xiang Zheng <zhengxiang9@huawei.com> --- accel/kvm/kvm-all.c | 36 ++++++++++++++++++++++++++++++++++++ include/sysemu/kvm_int.h | 12 ++++++++++++ target/i386/kvm.c | 36 ------------------------------------ 3 files changed, 48 insertions(+), 36 deletions(-) diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c index XXXXXXX..XXXXXXX 100644 --- a/accel/kvm/kvm-all.c +++ b/accel/kvm/kvm-all.c @@ -XXX,XX +XXX,XX @@ #include "qapi/visitor.h" #include "qapi/qapi-types-common.h" #include "qapi/qapi-visit-common.h" +#include "sysemu/reset.h" #include "hw/boards.h" @@ -XXX,XX +XXX,XX @@ int kvm_vm_check_extension(KVMState *s, unsigned int extension) return ret; } +typedef struct HWPoisonPage { + ram_addr_t ram_addr; + QLIST_ENTRY(HWPoisonPage) list; +} HWPoisonPage; + +static QLIST_HEAD(, HWPoisonPage) hwpoison_page_list = + QLIST_HEAD_INITIALIZER(hwpoison_page_list); + +static void kvm_unpoison_all(void *param) +{ + HWPoisonPage *page, *next_page; + + QLIST_FOREACH_SAFE(page, &hwpoison_page_list, list, next_page) { + QLIST_REMOVE(page, list); + qemu_ram_remap(page->ram_addr, TARGET_PAGE_SIZE); + g_free(page); + } +} + +void kvm_hwpoison_page_add(ram_addr_t ram_addr) +{ + HWPoisonPage *page; + + QLIST_FOREACH(page, &hwpoison_page_list, list) { + if (page->ram_addr == ram_addr) { + return; + } + } + page = g_new(HWPoisonPage, 1); + page->ram_addr = ram_addr; + QLIST_INSERT_HEAD(&hwpoison_page_list, page, list); +} + static uint32_t adjust_ioeventfd_endianness(uint32_t val, uint32_t size) { #if defined(HOST_WORDS_BIGENDIAN) != defined(TARGET_WORDS_BIGENDIAN) @@ -XXX,XX +XXX,XX @@ static int kvm_init(MachineState *ms) s->kernel_irqchip_split = mc->default_kernel_irqchip_split ? ON_OFF_AUTO_ON : ON_OFF_AUTO_OFF; } + qemu_register_reset(kvm_unpoison_all, NULL); + if (s->kernel_irqchip_allowed) { kvm_irqchip_create(s); } diff --git a/include/sysemu/kvm_int.h b/include/sysemu/kvm_int.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/kvm_int.h +++ b/include/sysemu/kvm_int.h @@ -XXX,XX +XXX,XX @@ void kvm_memory_listener_register(KVMState *s, KVMMemoryListener *kml, AddressSpace *as, int as_id); void kvm_set_max_memslot_size(hwaddr max_slot_size); + +/** + * kvm_hwpoison_page_add: + * + * Parameters: + * @ram_addr: the address in the RAM for the poisoned page + * + * Add a poisoned page to the list + * + * Return: None. + */ +void kvm_hwpoison_page_add(ram_addr_t ram_addr); #endif diff --git a/target/i386/kvm.c b/target/i386/kvm.c index XXXXXXX..XXXXXXX 100644 --- a/target/i386/kvm.c +++ b/target/i386/kvm.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/sysemu.h" #include "sysemu/hw_accel.h" #include "sysemu/kvm_int.h" -#include "sysemu/reset.h" #include "sysemu/runstate.h" #include "kvm_i386.h" #include "hyperv.h" @@ -XXX,XX +XXX,XX @@ uint64_t kvm_arch_get_supported_msr_feature(KVMState *s, uint32_t index) } } - -typedef struct HWPoisonPage { - ram_addr_t ram_addr; - QLIST_ENTRY(HWPoisonPage) list; -} HWPoisonPage; - -static QLIST_HEAD(, HWPoisonPage) hwpoison_page_list = - QLIST_HEAD_INITIALIZER(hwpoison_page_list); - -static void kvm_unpoison_all(void *param) -{ - HWPoisonPage *page, *next_page; - - QLIST_FOREACH_SAFE(page, &hwpoison_page_list, list, next_page) { - QLIST_REMOVE(page, list); - qemu_ram_remap(page->ram_addr, TARGET_PAGE_SIZE); - g_free(page); - } -} - -static void kvm_hwpoison_page_add(ram_addr_t ram_addr) -{ - HWPoisonPage *page; - - QLIST_FOREACH(page, &hwpoison_page_list, list) { - if (page->ram_addr == ram_addr) { - return; - } - } - page = g_new(HWPoisonPage, 1); - page->ram_addr = ram_addr; - QLIST_INSERT_HEAD(&hwpoison_page_list, page, list); -} - static int kvm_get_mce_cap_supported(KVMState *s, uint64_t *mce_cap, int *max_banks) { @@ -XXX,XX +XXX,XX @@ int kvm_arch_init(MachineState *ms, KVMState *s) fprintf(stderr, "e820_add_entry() table is full\n"); return ret; } - qemu_register_reset(kvm_unpoison_all, NULL); shadow_mem = object_property_get_int(OBJECT(s), "kvm-shadow-mem", &error_abort); if (shadow_mem != -1) { -- 1.8.3.1 kvm_arch_on_sigbus_vcpu() error injection uses source_id as index in etc/hardware_errors to find out Error Status Data Block entry corresponding to error source. So supported source_id values should be assigned here and not be changed afterwards to make sure that guest will write error into expected Error Status Data Block. Before QEMU writes a new error to ACPI table, it will check whether previous error has been acknowledged. If not acknowledged, the new errors will be ignored and not be recorded. For the errors section type, QEMU simulate it to memory section error. Signed-off-by: Dongjiu Geng <gengdongjiu@huawei.com> Signed-off-by: Xiang Zheng <zhengxiang9@huawei.com> Reviewed-by: Igor Mammedov <imammedo@redhat.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> --- hw/acpi/ghes.c | 219 +++++++++++++++++++++++++++++++++++++++++++++++++ include/hw/acpi/ghes.h | 1 + 2 files changed, 220 insertions(+) diff --git a/hw/acpi/ghes.c b/hw/acpi/ghes.c index XXXXXXX..XXXXXXX 100644 --- a/hw/acpi/ghes.c +++ b/hw/acpi/ghes.c @@ -XXX,XX +XXX,XX @@ #include "qemu/error-report.h" #include "hw/acpi/generic_event_device.h" #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" @@ -XXX,XX +XXX,XX @@ #define GAS_ADDR_OFFSET 4 /* + * The total size of Generic Error Data Entry + * ACPI 6.1/6.2: 18.3.2.7.1 Generic Error Data, + * Table 18-343 Generic Error Data Entry + */ +#define ACPI_GHES_DATA_LENGTH 72 + +/* The memory section CPER size, UEFI 2.6: N.2.5 Memory Error Section */ +#define ACPI_GHES_MEM_CPER_LENGTH 80 + +/* Masks for block_status flags */ +#define ACPI_GEBS_UNCORRECTABLE 1 + +/* + * Total size for Generic Error Status Block except Generic Error Data Entries + * ACPI 6.2: 18.3.2.7.1 Generic Error Data, + * Table 18-380 Generic Error Status Block + */ +#define ACPI_GHES_GESB_SIZE 20 + +/* + * Values for error_severity field + */ +enum AcpiGenericErrorSeverity { + ACPI_CPER_SEV_RECOVERABLE = 0, + ACPI_CPER_SEV_FATAL = 1, + ACPI_CPER_SEV_CORRECTED = 2, + ACPI_CPER_SEV_NONE = 3, +}; + +/* * Hardware Error Notification * ACPI 4.0: 17.3.2.7 Hardware Error Notification * Composes dummy Hardware Error Notification descriptor of specified type @@ -XXX,XX +XXX,XX @@ static void build_ghes_hw_error_notification(GArray *table, const uint8_t type) } /* + * Generic Error Data Entry + * ACPI 6.1: 18.3.2.7.1 Generic Error Data + */ +static void acpi_ghes_generic_error_data(GArray *table, + const uint8_t *section_type, uint32_t error_severity, + uint8_t validation_bits, uint8_t flags, + uint32_t error_data_length, QemuUUID fru_id, + uint64_t time_stamp) +{ + const uint8_t fru_text[20] = {0}; + + /* Section Type */ + g_array_append_vals(table, section_type, 16); + + /* Error Severity */ + build_append_int_noprefix(table, error_severity, 4); + /* Revision */ + build_append_int_noprefix(table, 0x300, 2); + /* Validation Bits */ + build_append_int_noprefix(table, validation_bits, 1); + /* Flags */ + build_append_int_noprefix(table, flags, 1); + /* Error Data Length */ + build_append_int_noprefix(table, error_data_length, 4); + + /* FRU Id */ + g_array_append_vals(table, fru_id.data, ARRAY_SIZE(fru_id.data)); + + /* FRU Text */ + g_array_append_vals(table, fru_text, sizeof(fru_text)); + + /* Timestamp */ + build_append_int_noprefix(table, time_stamp, 8); +} + +/* + * Generic Error Status Block + * ACPI 6.1: 18.3.2.7.1 Generic Error Data + */ +static void acpi_ghes_generic_error_status(GArray *table, uint32_t block_status, + uint32_t raw_data_offset, uint32_t raw_data_length, + uint32_t data_length, uint32_t error_severity) +{ + /* Block Status */ + build_append_int_noprefix(table, block_status, 4); + /* Raw Data Offset */ + build_append_int_noprefix(table, raw_data_offset, 4); + /* Raw Data Length */ + build_append_int_noprefix(table, raw_data_length, 4); + /* Data Length */ + build_append_int_noprefix(table, data_length, 4); + /* Error Severity */ + build_append_int_noprefix(table, error_severity, 4); +} + +/* UEFI 2.6: N.2.5 Memory Error Section */ +static void acpi_ghes_build_append_mem_cper(GArray *table, + uint64_t error_physical_addr) +{ + /* + * Memory Error Record + */ + + /* Validation Bits */ + build_append_int_noprefix(table, + (1ULL << 14) | /* Type Valid */ + (1ULL << 1) /* Physical Address Valid */, + 8); + /* Error Status */ + build_append_int_noprefix(table, 0, 8); + /* Physical Address */ + build_append_int_noprefix(table, error_physical_addr, 8); + /* Skip all the detailed information normally found in such a record */ + build_append_int_noprefix(table, 0, 48); + /* Memory Error Type */ + build_append_int_noprefix(table, 0 /* Unknown error */, 1); + /* Skip all the detailed information normally found in such a record */ + build_append_int_noprefix(table, 0, 7); +} + +static int acpi_ghes_record_mem_error(uint64_t error_block_address, + uint64_t error_physical_addr) +{ + 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; + + /* + * Check whether it will run out of the preallocated memory if adding a new + * generic error data entry + */ + if ((data_length + ACPI_GHES_GESB_SIZE) > ACPI_GHES_MAX_RAW_DATA_LENGTH) { + error_report("Not enough memory to record new CPER!!!"); + g_array_free(block, true); + return -1; + } + + /* 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_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; +} + +/* * Build table for the hardware error fw_cfg blob. * Initialize "etc/hardware_errors" and "etc/hardware_errors_addr" fw_cfg blobs. * See docs/specs/acpi_hest_ghes.rst for blobs format. @@ -XXX,XX +XXX,XX @@ void acpi_ghes_add_fw_cfg(AcpiGhesState *ags, FWCfgState *s, 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); } + +int acpi_ghes_record_errors(uint8_t source_id, uint64_t physical_address) +{ + uint64_t error_block_addr, read_ack_register_addr, read_ack_register = 0; + uint64_t start_addr; + bool ret = -1; + AcpiGedState *acpi_ged_state; + AcpiGhesState *ags; + + assert(source_id < ACPI_HEST_SRC_ID_RESERVED); + + acpi_ged_state = ACPI_GED(object_resolve_path_type("", TYPE_ACPI_GED, + NULL)); + g_assert(acpi_ged_state); + ags = &acpi_ged_state->ghes_state; + + start_addr = le64_to_cpu(ags->ghes_addr_le); + + if (physical_address) { + + if (source_id < ACPI_HEST_SRC_ID_RESERVED) { + start_addr += source_id * sizeof(uint64_t); + } + + cpu_physical_memory_read(start_addr, &error_block_addr, + sizeof(error_block_addr)); + + error_block_addr = le64_to_cpu(error_block_addr); + + read_ack_register_addr = start_addr + + ACPI_GHES_ERROR_SOURCE_COUNT * sizeof(uint64_t); + + 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_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)); + + ret = acpi_ghes_record_mem_error(error_block_addr, + physical_address); + } else + error_report("can not find Generic Error Status Block"); + } + + return ret; +} diff --git a/include/hw/acpi/ghes.h b/include/hw/acpi/ghes.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/acpi/ghes.h +++ b/include/hw/acpi/ghes.h @@ -XXX,XX +XXX,XX @@ void build_ghes_error_table(GArray *hardware_errors, BIOSLinker *linker); void acpi_build_hest(GArray *table_data, BIOSLinker *linker); void acpi_ghes_add_fw_cfg(AcpiGhesState *vms, FWCfgState *s, GArray *hardware_errors); +int acpi_ghes_record_errors(uint8_t notify, uint64_t error_physical_addr); #endif -- 1.8.3.1 Add a SIGBUS signal handler. In this handler, it checks the SIGBUS type, translates the host VA delivered by host to guest PA, then fills this PA to guest APEI GHES memory, then notifies guest according to the SIGBUS type. When guest accesses the poisoned memory, it will generate a Synchronous External Abort(SEA). Then host kernel gets an APEI notification and calls memory_failure() to unmapped the affected page in stage 2, finally returns to guest. Guest continues to access the PG_hwpoison page, it will trap to KVM as stage2 fault, then a SIGBUS_MCEERR_AR synchronous signal is delivered to Qemu, Qemu records this error address into guest APEI GHES memory and notifes guest using Synchronous-External-Abort(SEA). In order to inject a vSEA, we introduce the kvm_inject_arm_sea() function in which we can setup the type of exception and the syndrome information. When switching to guest, the target vcpu will jump to the synchronous external abort vector table entry. The ESR_ELx.DFSC is set to synchronous external abort(0x10), and the ESR_ELx.FnV is set to not valid(0x1), which will tell guest that FAR is not valid and hold an UNKNOWN value. These values will be set to KVM register structures through KVM_SET_ONE_REG IOCTL. Signed-off-by: Dongjiu Geng <gengdongjiu@huawei.com> Signed-off-by: Xiang Zheng <zhengxiang9@huawei.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Acked-by: Xiang Zheng <zhengxiang9@huawei.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Igor Mammedov <imammedo@redhat.com> --- include/sysemu/kvm.h | 3 +- target/arm/cpu.h | 4 +++ target/arm/helper.c | 2 +- target/arm/internals.h | 5 ++-- target/arm/kvm64.c | 77 +++++++++++++++++++++++++++++++++++++++++++++++++ target/arm/tlb_helper.c | 2 +- target/i386/cpu.h | 2 ++ 7 files changed, 89 insertions(+), 6 deletions(-) diff --git a/include/sysemu/kvm.h b/include/sysemu/kvm.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/kvm.h +++ b/include/sysemu/kvm.h @@ -XXX,XX +XXX,XX @@ bool kvm_vcpu_id_is_valid(int vcpu_id); /* Returns VCPU ID to be used on KVM_CREATE_VCPU ioctl() */ unsigned long kvm_arch_vcpu_id(CPUState *cpu); -#ifdef TARGET_I386 -#define KVM_HAVE_MCE_INJECTION 1 +#ifdef KVM_HAVE_MCE_INJECTION void kvm_arch_on_sigbus_vcpu(CPUState *cpu, int code, void *addr); #endif diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ /* ARM processors have a weak memory model */ #define TCG_GUEST_DEFAULT_MO (0) +#ifdef TARGET_AARCH64 +#define KVM_HAVE_MCE_INJECTION 1 +#endif + #define EXCP_UDEF 1 /* undefined instruction */ #define EXCP_SWI 2 /* software interrupt */ #define EXCP_PREFETCH_ABORT 3 diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static uint64_t do_ats_write(CPUARMState *env, uint64_t value, * Report exception with ESR indicating a fault due to a * translation table walk for a cache maintenance instruction. */ - syn = syn_data_abort_no_iss(current_el == target_el, + syn = syn_data_abort_no_iss(current_el == target_el, 0, fi.ea, 1, fi.s1ptw, 1, fsc); env->exception.vaddress = value; env->exception.fsr = fsr; diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_insn_abort(int same_el, int ea, int s1ptw, int fsc) | ARM_EL_IL | (ea << 9) | (s1ptw << 7) | fsc; } -static inline uint32_t syn_data_abort_no_iss(int same_el, +static inline uint32_t syn_data_abort_no_iss(int same_el, int fnv, int ea, int cm, int s1ptw, int wnr, int fsc) { return (EC_DATAABORT << ARM_EL_EC_SHIFT) | (same_el << ARM_EL_EC_SHIFT) | ARM_EL_IL - | (ea << 9) | (cm << 8) | (s1ptw << 7) | (wnr << 6) | fsc; + | (fnv << 10) | (ea << 9) | (cm << 8) | (s1ptw << 7) + | (wnr << 6) | fsc; } static inline uint32_t syn_data_abort_with_iss(int same_el, diff --git a/target/arm/kvm64.c b/target/arm/kvm64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm64.c +++ b/target/arm/kvm64.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/kvm_int.h" #include "kvm_arm.h" #include "internals.h" +#include "hw/acpi/acpi.h" +#include "hw/acpi/ghes.h" +#include "hw/arm/virt.h" static bool have_guest_debug; @@ -XXX,XX +XXX,XX @@ int kvm_arm_cpreg_level(uint64_t regidx) return KVM_PUT_RUNTIME_STATE; } +/* Callers must hold the iothread mutex lock */ +static void kvm_inject_arm_sea(CPUState *c) +{ + ARMCPU *cpu = ARM_CPU(c); + CPUARMState *env = &cpu->env; + CPUClass *cc = CPU_GET_CLASS(c); + uint32_t esr; + bool same_el; + + c->exception_index = EXCP_DATA_ABORT; + env->exception.target_el = 1; + + /* + * Set the DFSC to synchronous external abort and set FnV to not valid, + * this will tell guest the FAR_ELx is UNKNOWN for this abort. + */ + same_el = arm_current_el(env) == env->exception.target_el; + esr = syn_data_abort_no_iss(same_el, 1, 0, 0, 0, 0, 0x10); + + env->exception.syndrome = esr; + + cc->do_interrupt(c); +} + #define AARCH64_CORE_REG(x) (KVM_REG_ARM64 | KVM_REG_SIZE_U64 | \ KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(x)) @@ -XXX,XX +XXX,XX @@ int kvm_arch_get_registers(CPUState *cs) return ret; } +void kvm_arch_on_sigbus_vcpu(CPUState *c, int code, void *addr) +{ + ram_addr_t ram_addr; + hwaddr paddr; + Object *obj = qdev_get_machine(); + VirtMachineState *vms = VIRT_MACHINE(obj); + bool acpi_enabled = virt_is_acpi_enabled(vms); + + assert(code == BUS_MCEERR_AR || code == BUS_MCEERR_AO); + + if (acpi_enabled && addr && + object_property_get_bool(obj, "ras", NULL)) { + ram_addr = qemu_ram_addr_from_host(addr); + if (ram_addr != RAM_ADDR_INVALID && + kvm_physical_memory_addr_from_host(c->kvm_state, addr, &paddr)) { + kvm_hwpoison_page_add(ram_addr); + /* + * If this is a BUS_MCEERR_AR, we know we have been called + * synchronously from the vCPU thread, so we can easily + * synchronize the state and inject an error. + * + * TODO: we currently don't tell the guest at all about + * BUS_MCEERR_AO. In that case we might either be being + * called synchronously from the vCPU thread, or a bit + * later from the main thread, so doing the injection of + * the error would be more complicated. + */ + if (code == BUS_MCEERR_AR) { + kvm_cpu_synchronize_state(c); + if (!acpi_ghes_record_errors(ACPI_HEST_SRC_ID_SEA, paddr)) { + kvm_inject_arm_sea(c); + } else { + error_report("failed to record the error"); + abort(); + } + } + return; + } + if (code == BUS_MCEERR_AO) { + error_report("Hardware memory error at addr %p for memory used by " + "QEMU itself instead of guest system!", addr); + } + } + + if (code == BUS_MCEERR_AR) { + error_report("Hardware memory error!"); + exit(1); + } +} + /* C6.6.29 BRK instruction */ static const uint32_t brk_insn = 0xd4200000; diff --git a/target/arm/tlb_helper.c b/target/arm/tlb_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tlb_helper.c +++ b/target/arm/tlb_helper.c @@ -XXX,XX +XXX,XX @@ static inline uint32_t merge_syn_data_abort(uint32_t template_syn, * ISV field. */ if (!(template_syn & ARM_EL_ISV) || target_el != 2 || s1ptw) { - syn = syn_data_abort_no_iss(same_el, + syn = syn_data_abort_no_iss(same_el, 0, ea, 0, s1ptw, is_write, fsc); } else { /* diff --git a/target/i386/cpu.h b/target/i386/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/i386/cpu.h +++ b/target/i386/cpu.h @@ -XXX,XX +XXX,XX @@ /* The x86 has a strong memory model with some store-after-load re-ordering */ #define TCG_GUEST_DEFAULT_MO (TCG_MO_ALL & ~TCG_MO_ST_LD) +#define KVM_HAVE_MCE_INJECTION 1 + /* Maximum instruction code size */ #define TARGET_MAX_INSN_SIZE 16 -- 1.8.3.1 I and Xiang are willing to review the APEI-related patches and volunteer as the reviewers for the HEST/GHES part. Signed-off-by: Dongjiu Geng <gengdongjiu@huawei.com> Signed-off-by: Xiang Zheng <zhengxiang9@huawei.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Acked-by: Michael S. Tsirkin <mst@redhat.com> --- MAINTAINERS | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: tests/qtest/bios-tables-test.c F: tests/qtest/acpi-utils.[hc] F: tests/data/acpi/ +ACPI/HEST/GHES +R: Dongjiu Geng <gengdongjiu@huawei.com> +R: Xiang Zheng <zhengxiang9@huawei.com> +L: qemu-arm@nongnu.org +S: Maintained +F: hw/acpi/ghes.c +F: include/hw/acpi/ghes.h +F: docs/specs/acpi_hest_ghes.rst + ppc4xx M: David Gibson <david@gibson.dropbear.id.au> L: qemu-ppc@nongnu.org -- 1.8.3.1