| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <CAJZ5v0ifxfuwdHd9HrWby6qdXwCq1YHbk6UapQL3g39TGynLHg@mail.gmail.com>
Date: Wed, 9 Jun 2021 15:22:43 +0200
From: "Rafael J. Wysocki" <rafael@...nel.org>
To: Xiaofei Tan <tanxiaofei@...wei.com>
Cc: James Morse <james.morse@....com>,
"Rafael J. Wysocki" <rafael@...nel.org>,
"Rafael J. Wysocki" <rjw@...ysocki.net>,
Len Brown <lenb@...nel.org>, Tony Luck <tony.luck@...el.com>,
Borislav Petkov <bp@...en8.de>,
Andrew Morton <akpm@...ux-foundation.org>,
Joerg Roedel <jroedel@...e.de>,
Peter Zijlstra <peterz@...radead.org>,
ACPI Devel Maling List <linux-acpi@...r.kernel.org>,
Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
linuxarm@...neuler.org
Subject: Re: [PATCH v6] ACPI / APEI: fix the regression of synchronous
external aborts occur in user-mode
On Wed, Jun 9, 2021 at 8:06 AM Xiaofei Tan <tanxiaofei@...wei.com> wrote:
>
> Before commit 8fcc4ae6faf8 ("arm64: acpi: Make apei_claim_sea()
> synchronise with APEI's irq work"), do_sea() would unconditionally
> signal the affected task from the arch code. Since that change,
> the GHES driver sends the signals.
Since this fixes a regression apparently introduced by the above
commit, please add a Fixes tag pointing to that commit to it.
> This exposes a problem as errors the GHES driver doesn't understand
> or doesn't handle effectively are silently ignored. It will cause
> the errors get taken again, and circulate endlessly. User-space task
> get stuck in this loop.
>
> Existing firmware on Kunpeng9xx systems reports cache errors with the
> 'ARM Processor Error' CPER records.
>
> Do memory failure handling for ARM Processor Error Section just like
> for Memory Error Section.
So why is this the right thing to do?
I guess it doesn't address the problem entirely, but only in this
particular case, so what if the firmware on some other platform
reports errors with a new type unknown to the GHES driver? Will the
problem show up again?
> Signed-off-by: Xiaofei Tan <tanxiaofei@...wei.com>
> Reviewed-by: James Morse <james.morse@....com>
>
> ---
> Changes since v5:
> - Do some changes following James's suggestions: 1) optimize commit log
> 2) use err_info->length instead of err_info++' 3) some coding style
> advice.
>
> Changes since v4:
> - 1. Change the patch name from " ACPI / APEI: do memory failure on the
> physical address reported by ARM processor error section" to this
> more proper one.
> - 2. Add a comment in the code to tell why not filter out corrected
> error in an uncorrected section.
>
> Changes since v3:
> - Print unhandled error following James Morse's advice.
>
> Changes since v2:
> - Updated commit log
> ---
> drivers/acpi/apei/ghes.c | 81 ++++++++++++++++++++++++++++++++++++++----------
> 1 file changed, 64 insertions(+), 17 deletions(-)
>
> diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
> index fce7ade..0c8330e 100644
> --- a/drivers/acpi/apei/ghes.c
> +++ b/drivers/acpi/apei/ghes.c
> @@ -441,28 +441,35 @@ static void ghes_kick_task_work(struct callback_head *head)
> gen_pool_free(ghes_estatus_pool, (unsigned long)estatus_node, node_len);
> }
>
> -static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata,
> - int sev)
> +static bool ghes_do_memory_failure(u64 physical_addr, int flags)
> {
> unsigned long pfn;
> - int flags = -1;
> - int sec_sev = ghes_severity(gdata->error_severity);
> - struct cper_sec_mem_err *mem_err = acpi_hest_get_payload(gdata);
>
> if (!IS_ENABLED(CONFIG_ACPI_APEI_MEMORY_FAILURE))
> return false;
>
> - if (!(mem_err->validation_bits & CPER_MEM_VALID_PA))
> - return false;
> -
> - pfn = mem_err->physical_addr >> PAGE_SHIFT;
> + pfn = PHYS_PFN(physical_addr);
> if (!pfn_valid(pfn)) {
> pr_warn_ratelimited(FW_WARN GHES_PFX
> "Invalid address in generic error data: %#llx\n",
> - mem_err->physical_addr);
> + physical_addr);
> return false;
> }
>
> + memory_failure_queue(pfn, flags);
> + return true;
> +}
> +
> +static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata,
> + int sev)
> +{
> + int flags = -1;
> + int sec_sev = ghes_severity(gdata->error_severity);
> + struct cper_sec_mem_err *mem_err = acpi_hest_get_payload(gdata);
> +
> + if (!(mem_err->validation_bits & CPER_MEM_VALID_PA))
> + return false;
> +
> /* iff following two events can be handled properly by now */
> if (sec_sev == GHES_SEV_CORRECTED &&
> (gdata->flags & CPER_SEC_ERROR_THRESHOLD_EXCEEDED))
> @@ -470,14 +477,56 @@ static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata,
> if (sev == GHES_SEV_RECOVERABLE && sec_sev == GHES_SEV_RECOVERABLE)
> flags = 0;
>
> - if (flags != -1) {
> - memory_failure_queue(pfn, flags);
> - return true;
> - }
> + if (flags != -1)
> + return ghes_do_memory_failure(mem_err->physical_addr, flags);
>
> return false;
> }
>
> +static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata, int sev)
> +{
> + struct cper_sec_proc_arm *err = acpi_hest_get_payload(gdata);
> + bool queued = false;
> + int sec_sev, i;
> + char *p;
> +
> + log_arm_hw_error(err);
> +
> + sec_sev = ghes_severity(gdata->error_severity);
> + if (sev != GHES_SEV_RECOVERABLE || sec_sev != GHES_SEV_RECOVERABLE)
> + return false;
> +
> + p = (char *)(err + 1);
> + for (i = 0; i < err->err_info_num; i++) {
> + struct cper_arm_err_info *err_info = (struct cper_arm_err_info *)p;
> + bool is_cache = (err_info->type == CPER_ARM_CACHE_ERROR);
> + bool has_pa = (err_info->validation_bits & CPER_ARM_INFO_VALID_PHYSICAL_ADDR);
> + const char *error_type = "unknown error";
> +
> + /*
> + * The field (err_info->error_info & BIT(26)) is fixed to set to
> + * 1 in some old firmware of HiSilicon Kunpeng920. We assume that
> + * firmware won't mix corrected errors in an uncorrected section,
> + * and don't filter out 'corrected' error here.
> + */
> + if (is_cache && has_pa) {
> + queued = ghes_do_memory_failure(err_info->physical_fault_addr, 0);
> + p += err_info->length;
> + continue;
> + }
> +
> + if (err_info->type < ARRAY_SIZE(cper_proc_error_type_strs))
> + error_type = cper_proc_error_type_strs[err_info->type];
> +
> + pr_warn_ratelimited(FW_WARN GHES_PFX
> + "Unhandled processor error type: %s\n",
> + error_type);
> + p += err_info->length;
> + }
> +
> + return queued;
> +}
> +
> /*
> * PCIe AER errors need to be sent to the AER driver for reporting and
> * recovery. The GHES severities map to the following AER severities and
> @@ -605,9 +654,7 @@ static bool ghes_do_proc(struct ghes *ghes,
> ghes_handle_aer(gdata);
> }
> else if (guid_equal(sec_type, &CPER_SEC_PROC_ARM)) {
> - struct cper_sec_proc_arm *err = acpi_hest_get_payload(gdata);
> -
> - log_arm_hw_error(err);
> + queued = ghes_handle_arm_hw_error(gdata, sev);
> } else {
> void *err = acpi_hest_get_payload(gdata);
>
> --
> 2.8.1
>
Powered by blists - more mailing lists