KVM Archive on lore.kernel.org
 help / color / Atom feed
From: Igor Mammedov <imammedo@redhat.com>
To: Dongjiu Geng <gengdongjiu@huawei.com>
Cc: <pbonzini@redhat.com>, <mst@redhat.com>,
	<shannon.zhaosl@gmail.com>, <peter.maydell@linaro.org>,
	<fam@euphon.net>, <rth@twiddle.net>, <ehabkost@redhat.com>,
	<mtosatti@redhat.com>, <xuwei5@huawei.com>,
	<jonathan.cameron@huawei.com>, <james.morse@arm.com>,
	<qemu-devel@nongnu.org>, <kvm@vger.kernel.org>,
	<qemu-arm@nongnu.org>, <zhengxiang9@huawei.com>,
	<linuxarm@huawei.com>
Subject: Re: [PATCH v22 7/9] ACPI: Record Generic Error Status Block(GESB) table
Date: Tue, 28 Jan 2020 16:29:38 +0100
Message-ID: <20200128162938.18bd0e95@redhat.com> (raw)
In-Reply-To: <1578483143-14905-8-git-send-email-gengdongjiu@huawei.com>

On Wed, 8 Jan 2020 19:32:21 +0800
Dongjiu Geng <gengdongjiu@huawei.com> wrote:

> 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 even if guest was migrated to a newer QEMU.
> 
> Before QEMU writes a new error to ACPI table, it will check whether
> previous error has been acknowledged. Otherwise it will ignore the new
> error. 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: Michael S. Tsirkin <mst@redhat.com>
> ---
>  hw/acpi/ghes.c         | 224 ++++++++++++++++++++++++++++++++++++++++++++++++-
>  include/hw/acpi/ghes.h |   3 +
>  include/qemu/uuid.h    |   5 ++
>  3 files changed, 230 insertions(+), 2 deletions(-)
> 
> diff --git a/hw/acpi/ghes.c b/hw/acpi/ghes.c
> index 68f4abf..f2ecffe 100644
> --- a/hw/acpi/ghes.c
> +++ b/hw/acpi/ghes.c
> @@ -28,21 +28,56 @@
>  #include "sysemu/sysemu.h"
>  #include "qemu/error-report.h"
>  
> -#include "hw/acpi/bios-linker-loader.h"
why it's moved to header?

> -
>  #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       0x400
> +
>  /* 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
>  
>  /*
> + * 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
> +
> +#define UEFI_CPER_SEC_PLATFORM_MEM                              \
> +    UUID_LE(0xA5BC1114, 0x6F64, 0x4EDE, 0xB8, 0x63, 0x3E, 0x83, \
> +            0xED, 0x7C, 0x83, 0xB1)
> +
> +/*
> + * 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
> @@ -73,6 +108,127 @@ 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, QemuUUID 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)
> +{
> +    /* Section Type */
> +    g_array_append_vals(table, section_type.data,
> +                        ARRAY_SIZE(section_type.data));
> +
> +    /* 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 */
> +    build_append_int_noprefix(table, 0, 20);
> +    /* 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 */
> +    QemuUUID mem_section_id_le = UEFI_CPER_SEC_PLATFORM_MEM;
> +    QemuUUID fru_id = {};
add comment /* invalid fru id: UEFI 2.6: ..., table ...


> +    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!!!");
> +        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, mem_section_id_le,
> +        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 back above this new generic error data entry to guest memory */

/* 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.
> @@ -224,3 +380,67 @@ 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;
> +    int loop = 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));
> +    if (acpi_ged_state) {
> +        ags = &acpi_ged_state->ghes_state;
> +    } else {
> +        error_report("ACPI GED device not found");
> +        return -1;
> +    }
> +
> +    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));
> +
> +        read_ack_register_addr = start_addr +
> +            ACPI_GHES_ERROR_SOURCE_COUNT * sizeof(uint64_t);
> +retry:
> +        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) {
> +            if (loop < 3) {
> +                usleep(100 * 1000);
> +                loop++;
> +                goto retry;
it's not doing what commit message says

if message is supposed to be dropped, just drop it without any delay loops

> +            } else {
> +                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);
                                          ^^^^ pointless "= 0" will do just fine

> +                /*
> +                 * Clear the Read Ack Register, OSPM will write it to 1 when
> +                 * acknowledge this error.
s/acknowledge/it acknowledges/

> +                 */
> +                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);
> +        }
> +    }
> +
> +    return ret;
> +}
> diff --git a/include/hw/acpi/ghes.h b/include/hw/acpi/ghes.h
> index a6761e6..ab0ae33 100644
> --- a/include/hw/acpi/ghes.h
> +++ b/include/hw/acpi/ghes.h
> @@ -22,6 +22,8 @@
>  #ifndef ACPI_GHES_H
>  #define ACPI_GHES_H
>  
> +#include "hw/acpi/bios-linker-loader.h"
> +
>  /*
>   * Values for Hardware Error Notification Type field
>   */
> @@ -69,4 +71,5 @@ void acpi_build_hest(GArray *table_data, GArray *hardware_error,
>                            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
> diff --git a/include/qemu/uuid.h b/include/qemu/uuid.h
> index 129c45f..b35e294 100644
> --- a/include/qemu/uuid.h
> +++ b/include/qemu/uuid.h
> @@ -34,6 +34,11 @@ typedef struct {
>      };
>  } QemuUUID;
>  
> +#define 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) } } }

since you are adding generalizing macro, take of NVDIMM_UUID_LE which served as model


>  #define UUID_FMT "%02hhx%02hhx%02hhx%02hhx-" \
>                   "%02hhx%02hhx-%02hhx%02hhx-" \
>                   "%02hhx%02hhx-" \


  reply index

Thread overview: 43+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-01-08 11:32 [PATCH v22 0/9] Add ARMv8 RAS virtualization support in QEMU Dongjiu Geng
2020-01-08 11:32 ` [PATCH v22 1/9] hw/arm/virt: Introduce a RAS machine option Dongjiu Geng
2020-01-08 11:32 ` [PATCH v22 2/9] docs: APEI GHES generation and CPER record description Dongjiu Geng
2020-01-15 15:11   ` Igor Mammedov
2020-01-08 11:32 ` [PATCH v22 3/9] ACPI: Build related register address fields via hardware error fw_cfg blob Dongjiu Geng
2020-01-23 15:14   ` Igor Mammedov
2020-02-02 14:01     ` gengdongjiu
2020-01-08 11:32 ` [PATCH v22 4/9] ACPI: Build Hardware Error Source Table Dongjiu Geng
2020-01-23 15:48   ` Igor Mammedov
2020-02-02 14:21     ` gengdongjiu
2020-02-05 16:43   ` Jonathan Cameron
2020-02-10 11:18     ` gengdongjiu
2020-01-08 11:32 ` [PATCH v22 5/9] ACPI: Record the Generic Error Status Block address Dongjiu Geng
2020-01-16 16:44   ` Peter Maydell
2020-01-17 10:36     ` gengdongjiu
2020-02-13 15:28     ` gengdongjiu
2020-01-17  7:39   ` Philippe Mathieu-Daudé
2020-01-17 10:47     ` gengdongjiu
2020-01-17 11:20       ` Philippe Mathieu-Daudé
2020-01-28 14:41   ` Igor Mammedov
2020-01-28 16:19     ` Igor Mammedov
2020-02-02 12:44     ` gengdongjiu
2020-02-03  7:51       ` Igor Mammedov
2020-01-08 11:32 ` [PATCH v22 6/9] KVM: Move hwpoison page related functions into kvm-all.c Dongjiu Geng
2020-01-08 11:32 ` [PATCH v22 7/9] ACPI: Record Generic Error Status Block(GESB) table Dongjiu Geng
2020-01-28 15:29   ` Igor Mammedov [this message]
2020-02-02 13:42     ` gengdongjiu
2020-02-03  7:55       ` Igor Mammedov
2020-01-08 11:32 ` [PATCH v22 8/9] target-arm: kvm64: handle SIGBUS signal from kernel or KVM Dongjiu Geng
2020-01-16 16:28   ` Peter Maydell
2020-01-16 16:40     ` Peter Maydell
2020-01-17 10:04     ` gengdongjiu
2020-01-20 12:15       ` Peter Maydell
2020-01-22 15:30         ` gengdongjiu
2020-01-08 11:32 ` [PATCH v22 9/9] MAINTAINERS: Add ACPI/HEST/GHES entries Dongjiu Geng
2020-01-16 16:46   ` Peter Maydell
2020-01-17  7:22     ` Philippe Mathieu-Daudé
2020-01-17 10:16       ` gengdongjiu
2020-01-17 11:09       ` Peter Maydell
2020-01-17 11:22         ` Philippe Mathieu-Daudé
2020-01-19  8:19           ` gengdongjiu
2020-01-17 12:19         ` Michael S. Tsirkin
2020-01-09  3:38 ` [PATCH v22 0/9] Add ARMv8 RAS virtualization support in QEMU gengdongjiu

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200128162938.18bd0e95@redhat.com \
    --to=imammedo@redhat.com \
    --cc=ehabkost@redhat.com \
    --cc=fam@euphon.net \
    --cc=gengdongjiu@huawei.com \
    --cc=james.morse@arm.com \
    --cc=jonathan.cameron@huawei.com \
    --cc=kvm@vger.kernel.org \
    --cc=linuxarm@huawei.com \
    --cc=mst@redhat.com \
    --cc=mtosatti@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=peter.maydell@linaro.org \
    --cc=qemu-arm@nongnu.org \
    --cc=qemu-devel@nongnu.org \
    --cc=rth@twiddle.net \
    --cc=shannon.zhaosl@gmail.com \
    --cc=xuwei5@huawei.com \
    --cc=zhengxiang9@huawei.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

KVM Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/kvm/0 kvm/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 kvm kvm/ https://lore.kernel.org/kvm \
		kvm@vger.kernel.org
	public-inbox-index kvm

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.kvm


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git