Re: [PATCH v10 1/4] ACPI: APEI: set memory failure flags as MF_ACTION_REQUIRED on synchronous events

["Rafael J. Wysocki" <rafael@kernel.org>]

On Mon, Dec 18, 2023 at 7:45 AM Shuai Xue <xueshuai@linux.alibaba.com> wrote:
>
> There are two major types of uncorrected recoverable (UCR) errors :
>
> - Synchronous error: The error is detected and raised at the point of the
>   consumption in the execution flow, e.g. when a CPU tries to access
>   a poisoned cache line. The CPU will take a synchronous error exception
>   such as Synchronous External Abort (SEA) on Arm64 and Machine Check
>   Exception (MCE) on X86. OS requires to take action (for example, offline
>   failure page/kill failure thread) to recover this uncorrectable error.
>
> - Asynchronous error: The error is detected out of processor execution
>   context, e.g. when an error is detected by a background scrubber. Some data
>   in the memory are corrupted. But the data have not been consumed. OS is
>   optional to take action to recover this uncorrectable error.
>
> When APEI firmware first is enabled, a platform may describe one error
> source for the handling of synchronous errors (e.g. MCE or SEA notification
> ), or for handling asynchronous errors (e.g. SCI or External Interrupt
> notification). In other words, we can distinguish synchronous errors by
> APEI notification. For synchronous errors, kernel will kill the current
> process which accessing the poisoned page by sending SIGBUS with
> BUS_MCEERR_AR. In addition, for asynchronous errors, kernel will notify the
> process who owns the poisoned page by sending SIGBUS with BUS_MCEERR_AO in
> early kill mode. However, the GHES driver always sets mf_flags to 0 so that
> all synchronous errors are handled as asynchronous errors in memory failure.
>
> To this end, set memory failure flags as MF_ACTION_REQUIRED on synchronous
> events.
>
> Signed-off-by: Shuai Xue <xueshuai@linux.alibaba.com>
> Tested-by: Ma Wupeng <mawupeng1@huawei.com>
> Reviewed-by: Kefeng Wang <wangkefeng.wang@huawei.com>
> Reviewed-by: Xiaofei Tan <tanxiaofei@huawei.com>
> Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com>
> Reviewed-by: James Morse <james.morse@arm.com>

Applied as 6.8 material.

The other patches in the series still need to receive tags from the
APEI designated reviewers (as per MAINTAINERS).

Thanks!


> ---
>  drivers/acpi/apei/ghes.c | 29 +++++++++++++++++++++++------
>  1 file changed, 23 insertions(+), 6 deletions(-)
>
> diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
> index 63ad0541db38..ab2a82cb1b0b 100644
> --- a/drivers/acpi/apei/ghes.c
> +++ b/drivers/acpi/apei/ghes.c
> @@ -101,6 +101,20 @@ static inline bool is_hest_type_generic_v2(struct ghes *ghes)
>         return ghes->generic->header.type == ACPI_HEST_TYPE_GENERIC_ERROR_V2;
>  }
>
> +/*
> + * A platform may describe one error source for the handling of synchronous
> + * errors (e.g. MCE or SEA), or for handling asynchronous errors (e.g. SCI
> + * or External Interrupt). On x86, the HEST notifications are always
> + * asynchronous, so only SEA on ARM is delivered as a synchronous
> + * notification.
> + */
> +static inline bool is_hest_sync_notify(struct ghes *ghes)
> +{
> +       u8 notify_type = ghes->generic->notify.type;
> +
> +       return notify_type == ACPI_HEST_NOTIFY_SEA;
> +}
> +
>  /*
>   * This driver isn't really modular, however for the time being,
>   * continuing to use module_param is the easiest way to remain
> @@ -489,7 +503,7 @@ static bool ghes_do_memory_failure(u64 physical_addr, int flags)
>  }
>
>  static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata,
> -                                      int sev)
> +                                      int sev, bool sync)
>  {
>         int flags = -1;
>         int sec_sev = ghes_severity(gdata->error_severity);
> @@ -503,7 +517,7 @@ static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata,
>             (gdata->flags & CPER_SEC_ERROR_THRESHOLD_EXCEEDED))
>                 flags = MF_SOFT_OFFLINE;
>         if (sev == GHES_SEV_RECOVERABLE && sec_sev == GHES_SEV_RECOVERABLE)
> -               flags = 0;
> +               flags = sync ? MF_ACTION_REQUIRED : 0;
>
>         if (flags != -1)
>                 return ghes_do_memory_failure(mem_err->physical_addr, flags);
> @@ -511,9 +525,11 @@ static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata,
>         return false;
>  }
>
> -static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata, int sev)
> +static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata,
> +                                      int sev, bool sync)
>  {
>         struct cper_sec_proc_arm *err = acpi_hest_get_payload(gdata);
> +       int flags = sync ? MF_ACTION_REQUIRED : 0;
>         bool queued = false;
>         int sec_sev, i;
>         char *p;
> @@ -538,7 +554,7 @@ static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata, int s
>                  * and don't filter out 'corrected' error here.
>                  */
>                 if (is_cache && has_pa) {
> -                       queued = ghes_do_memory_failure(err_info->physical_fault_addr, 0);
> +                       queued = ghes_do_memory_failure(err_info->physical_fault_addr, flags);
>                         p += err_info->length;
>                         continue;
>                 }
> @@ -666,6 +682,7 @@ static bool ghes_do_proc(struct ghes *ghes,
>         const guid_t *fru_id = &guid_null;
>         char *fru_text = "";
>         bool queued = false;
> +       bool sync = is_hest_sync_notify(ghes);
>
>         sev = ghes_severity(estatus->error_severity);
>         apei_estatus_for_each_section(estatus, gdata) {
> @@ -683,13 +700,13 @@ static bool ghes_do_proc(struct ghes *ghes,
>                         atomic_notifier_call_chain(&ghes_report_chain, sev, mem_err);
>
>                         arch_apei_report_mem_error(sev, mem_err);
> -                       queued = ghes_handle_memory_failure(gdata, sev);
> +                       queued = ghes_handle_memory_failure(gdata, sev, sync);
>                 }
>                 else if (guid_equal(sec_type, &CPER_SEC_PCIE)) {
>                         ghes_handle_aer(gdata);
>                 }
>                 else if (guid_equal(sec_type, &CPER_SEC_PROC_ARM)) {
> -                       queued = ghes_handle_arm_hw_error(gdata, sev);
> +                       queued = ghes_handle_arm_hw_error(gdata, sev, sync);
>                 } else {
>                         void *err = acpi_hest_get_payload(gdata);
>
> --
> 2.39.3
>