Hi Tyler,
On 2017/4/19 7:05, Tyler Baicar wrote:
> ARM APEI extension proposal added SEA (Synchronous External Abort)
> notification type for ARMv8.
> Add a new GHES error source handling function for SEA. If an error
> source's notification type is SEA, then this function can be registered
> into the SEA exception handler. That way GHES will parse and report
> SEA exceptions when they occur.
> An SEA can interrupt code that had interrupts masked and is treated as
> an NMI. To aid this the page of address space for mapping APEI buffers
> while in_nmi() is always reserved, and ghes_ioremap_pfn_nmi() is
> changed to use the helper methods to find the prot_t to map with in
> the same way as ghes_ioremap_pfn_irq().
>
> Signed-off-by: Tyler Baicar <tbaicar@xxxxxxxxxxxxxx>
> CC: Jonathan (Zhixiong) Zhang <zjzhang@xxxxxxxxxxxxxx>
> Reviewed-by: James Morse <james.morse@xxxxxxx>
> Acked-by: Catalin Marinas <catalin.marinas@xxxxxxx>
> ---
> @@ -518,6 +520,17 @@ static int do_sea(unsigned long addr, unsigned int esr, struct pt_regs *regs)
> pr_err("Synchronous External Abort: %s (0x%08x) at 0x%016lx\n",
> inf->name, esr, addr);
>
> + /*
> + * Synchronous aborts may interrupt code which had interrupts masked.
> + * Before calling out into the wider kernel tell the interested
> + * subsystems.
> + */
> + if (IS_ENABLED(CONFIG_ACPI_APEI_SEA)) {
> + nmi_enter();
> + ghes_notify_sea();
> + nmi_exit();
> + }
> +
> info.si_signo = SIGBUS;
> info.si_errno = 0;
> info.si_code = 0;
For instruction abort, if there exists memory section in ghes, we will call memory_failure() in ghes_notify_sea()
and reread the instruction from the disk. In this case, we don't have to send SIGBUS to the application.
But memory_failure() is scheduled in a work queue, we don't what the result of memory_failure will be when ghes_notify_sea() returned.
Do you have any idea about how to fix this, so we don't have to kill the application in the instruction abort case.
Thanks,
Wang Xiongfeng
> diff --git a/drivers/acpi/apei/Kconfig b/drivers/acpi/apei/Kconfig
> index b0140c8..de14d49 100644
> --- a/drivers/acpi/apei/Kconfig
> +++ b/drivers/acpi/apei/Kconfig
> @@ -39,6 +39,21 @@ config ACPI_APEI_PCIEAER
> PCIe AER errors may be reported via APEI firmware first mode.
> Turn on this option to enable the corresponding support.
>
> +config ACPI_APEI_SEA
> + bool "APEI Synchronous External Abort logging/recovering support"
> + depends on ARM64 && ACPI_APEI_GHES
> + default y
> + help
> + This option should be enabled if the system supports
> + firmware first handling of SEA (Synchronous External Abort).
> + SEA happens with certain faults of data abort or instruction
> + abort synchronous exceptions on ARMv8 systems. If a system
> + supports firmware first handling of SEA, the platform analyzes
> + and handles hardware error notifications from SEA, and it may then
> + form a HW error record for the OS to parse and handle. This
> + option allows the OS to look for such hardware error record, and
> + take appropriate action.
> +
> config ACPI_APEI_MEMORY_FAILURE
> bool "APEI memory error recovering support"
> depends on ACPI_APEI && MEMORY_FAILURE
> diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
> index dfb7dd2..2d387f8 100644
> --- a/drivers/acpi/apei/ghes.c
> +++ b/drivers/acpi/apei/ghes.c
> @@ -115,11 +115,7 @@
> * Two virtual pages are used, one for IRQ/PROCESS context, the other for
> * NMI context (optionally).
> */
> -#ifdef CONFIG_HAVE_ACPI_APEI_NMI
> #define GHES_IOREMAP_PAGES 2
> -#else
> -#define GHES_IOREMAP_PAGES 1
> -#endif
> #define GHES_IOREMAP_IRQ_PAGE(base) (base)
> #define GHES_IOREMAP_NMI_PAGE(base) ((base) + PAGE_SIZE)
>
> @@ -158,10 +154,14 @@ static void ghes_ioremap_exit(void)
> static void __iomem *ghes_ioremap_pfn_nmi(u64 pfn)
> {
> unsigned long vaddr;
> + phys_addr_t paddr;
> + pgprot_t prot;
>
> vaddr = (unsigned long)GHES_IOREMAP_NMI_PAGE(ghes_ioremap_area->addr);
> - ioremap_page_range(vaddr, vaddr + PAGE_SIZE,
> - pfn << PAGE_SHIFT, PAGE_KERNEL);
> +
> + paddr = pfn << PAGE_SHIFT;
> + prot = arch_apei_get_mem_attribute(paddr);
> + ioremap_page_range(vaddr, vaddr + PAGE_SIZE, paddr, prot);
>
> return (void __iomem *)vaddr;
> }
> @@ -771,6 +771,50 @@ static int ghes_notify_sci(struct notifier_block *this,
> .notifier_call = ghes_notify_sci,
> };
>
> +#ifdef CONFIG_ACPI_APEI_SEA
> +static LIST_HEAD(ghes_sea);
> +
> +void ghes_notify_sea(void)
> +{
> + struct ghes *ghes;
> +
> + /*
> + * synchronize_rcu() will wait for nmi_exit(), so no need to
> + * rcu_read_lock().
> + */
> + list_for_each_entry_rcu(ghes, &ghes_sea, list) {
> + ghes_proc(ghes);
> + }
> +}
> +
> +static void ghes_sea_add(struct ghes *ghes)
> +{
> + mutex_lock(&ghes_list_mutex);
> + list_add_rcu(&ghes->list, &ghes_sea);
> + mutex_unlock(&ghes_list_mutex);
> +}
> +
> +static void ghes_sea_remove(struct ghes *ghes)
> +{
> + mutex_lock(&ghes_list_mutex);
> + list_del_rcu(&ghes->list);
> + mutex_unlock(&ghes_list_mutex);
> + synchronize_rcu();
> +}
> +#else /* CONFIG_ACPI_APEI_SEA */
> +static inline void ghes_sea_add(struct ghes *ghes)
> +{
> + pr_err(GHES_PFX "ID: %d, trying to add SEA notification which is not supported\n",
> + ghes->generic->header.source_id);
> +}
> +
> +static inline void ghes_sea_remove(struct ghes *ghes)
> +{
> + pr_err(GHES_PFX "ID: %d, trying to remove SEA notification which is not supported\n",
> + ghes->generic->header.source_id);
> +}
> +#endif /* CONFIG_ACPI_APEI_SEA */
> +
> #ifdef CONFIG_HAVE_ACPI_APEI_NMI
> /*
> * printk is not safe in NMI context. So in NMI handler, we allocate
> @@ -1016,6 +1060,14 @@ static int ghes_probe(struct platform_device *ghes_dev)
> case ACPI_HEST_NOTIFY_EXTERNAL:
> case ACPI_HEST_NOTIFY_SCI:
> break;
> + case ACPI_HEST_NOTIFY_SEA:
> + if (!IS_ENABLED(CONFIG_ACPI_APEI_SEA)) {
> + pr_warn(GHES_PFX "Generic hardware error source: %d notified via SEA is not supported\n",
> + generic->header.source_id);
> + rc = -ENOTSUPP;
> + goto err;
> + }
> + break;
> case ACPI_HEST_NOTIFY_NMI:
> if (!IS_ENABLED(CONFIG_HAVE_ACPI_APEI_NMI)) {
> pr_warn(GHES_PFX "Generic hardware error source: %d notified via NMI interrupt is not supported!\n",
> @@ -1081,6 +1133,9 @@ static int ghes_probe(struct platform_device *ghes_dev)
> list_add_rcu(&ghes->list, &ghes_sci);
> mutex_unlock(&ghes_list_mutex);
> break;
> + case ACPI_HEST_NOTIFY_SEA:
> + ghes_sea_add(ghes);
> + break;
> case ACPI_HEST_NOTIFY_NMI:
> ghes_nmi_add(ghes);
> break;
> @@ -1124,6 +1179,9 @@ static int ghes_remove(struct platform_device *ghes_dev)
> mutex_unlock(&ghes_list_mutex);
> synchronize_rcu();
> break;
> + case ACPI_HEST_NOTIFY_SEA:
> + ghes_sea_remove(ghes);
> + break;
> case ACPI_HEST_NOTIFY_NMI:
> ghes_nmi_remove(ghes);
> break;
> diff --git a/include/acpi/ghes.h b/include/acpi/ghes.h
> index b89361a..ef0040893 100644
> --- a/include/acpi/ghes.h
> +++ b/include/acpi/ghes.h
> @@ -1,3 +1,6 @@
> +#ifndef GHES_H
> +#define GHES_H
> +
> #include <acpi/apei.h>
> #include <acpi/hed.h>
>
> @@ -95,3 +98,7 @@ static inline void *acpi_hest_get_payload(struct acpi_hest_generic_data *gdata)
>
> return gdata + 1;
> }
> +
> +void ghes_notify_sea(void);
> +
> +#endif /* GHES_H */
>
--
To unsubscribe from this list: send the line "unsubscribe linux-acpi" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
