Re: [PATCH V7 04/10] arm64: exception: handle Synchronous External Abort

From: Will Deacon
Date: Mon Jan 16 2017 - 06:53:25 EST


On Thu, Jan 12, 2017 at 11:15:18AM -0700, Tyler Baicar wrote:
> SEA exceptions are often caused by an uncorrected hardware
> error, and are handled when data abort and instruction abort
> exception classes have specific values for their Fault Status
> Code.
> When SEA occurs, before killing the process, go through
> the handlers registered in the notification list.
> Update fault_info[] with specific SEA faults so that the
> new SEA handler is used.
>
> Signed-off-by: Tyler Baicar <tbaicar@xxxxxxxxxxxxxx>
> Signed-off-by: Jonathan (Zhixiong) Zhang <zjzhang@xxxxxxxxxxxxxx>
> Signed-off-by: Naveen Kaje <nkaje@xxxxxxxxxxxxxx>
> ---
> arch/arm64/include/asm/system_misc.h | 13 ++++++++
> arch/arm64/mm/fault.c | 58 +++++++++++++++++++++++++++++-------
> 2 files changed, 61 insertions(+), 10 deletions(-)
>
> diff --git a/arch/arm64/include/asm/system_misc.h b/arch/arm64/include/asm/system_misc.h
> index 57f110b..e7f3440 100644
> --- a/arch/arm64/include/asm/system_misc.h
> +++ b/arch/arm64/include/asm/system_misc.h
> @@ -64,4 +64,17 @@ extern void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd);
>
> #endif /* __ASSEMBLY__ */
>
> +/*
> + * The functions below are used to register and unregister callbacks
> + * that are to be invoked when a Synchronous External Abort (SEA)
> + * occurs. An SEA is raised by certain fault status codes that have
> + * either data or instruction abort as the exception class, and
> + * callbacks may be registered to parse or handle such hardware errors.
> + *
> + * Registered callbacks are run in an interrupt/atomic context. They
> + * are not allowed to block or sleep.
> + */
> +int register_sea_notifier(struct notifier_block *nb);
> +void unregister_sea_notifier(struct notifier_block *nb);

I still don't understand why you need notifiers for this. You register
precisely one hook in the series.

> #endif /* __ASM_SYSTEM_MISC_H */
> diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
> index 05d2bd7..81039c7 100644
> --- a/arch/arm64/mm/fault.c
> +++ b/arch/arm64/mm/fault.c
> @@ -39,6 +39,22 @@
> #include <asm/pgtable.h>
> #include <asm/tlbflush.h>
>
> +/*
> + * GHES SEA handler code may register a notifier call here to
> + * handle HW error record passed from platform.
> + */
> +static ATOMIC_NOTIFIER_HEAD(sea_handler_chain);
> +
> +int register_sea_notifier(struct notifier_block *nb)
> +{
> + return atomic_notifier_chain_register(&sea_handler_chain, nb);
> +}
> +
> +void unregister_sea_notifier(struct notifier_block *nb)
> +{
> + atomic_notifier_chain_unregister(&sea_handler_chain, nb);
> +}
> +
> static const char *fault_name(unsigned int esr);
>
> #ifdef CONFIG_KPROBES
> @@ -480,6 +496,28 @@ static int do_bad(unsigned long addr, unsigned int esr, struct pt_regs *regs)
> return 1;
> }
>
> +/*
> + * This abort handler deals with Synchronous External Abort.
> + * It calls notifiers, and then returns "fault".
> + */
> +static int do_sea(unsigned long addr, unsigned int esr, struct pt_regs *regs)
> +{
> + struct siginfo info;
> +
> + atomic_notifier_call_chain(&sea_handler_chain, 0, NULL);
> +
> + pr_err("Synchronous External Abort: %s (0x%08x) at 0x%016lx\n",
> + fault_name(esr), esr, addr);
> +
> + info.si_signo = SIGBUS;
> + info.si_errno = 0;
> + info.si_code = 0;
> + info.si_addr = (void __user *)addr;
> + arm64_notify_die("", regs, &info, esr);
> +
> + return 0;
> +}
> +
> static const struct fault_info {
> int (*fn)(unsigned long addr, unsigned int esr, struct pt_regs *regs);
> int sig;
> @@ -502,22 +540,22 @@ static const struct fault_info {
> { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 1 permission fault" },
> { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 2 permission fault" },
> { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 3 permission fault" },
> - { do_bad, SIGBUS, 0, "synchronous external abort" },
> + { do_sea, SIGBUS, 0, "synchronous external abort" },
> { do_bad, SIGBUS, 0, "unknown 17" },
> { do_bad, SIGBUS, 0, "unknown 18" },
> { do_bad, SIGBUS, 0, "unknown 19" },
> - { do_bad, SIGBUS, 0, "synchronous abort (translation table walk)" },
> - { do_bad, SIGBUS, 0, "synchronous abort (translation table walk)" },
> - { do_bad, SIGBUS, 0, "synchronous abort (translation table walk)" },
> - { do_bad, SIGBUS, 0, "synchronous abort (translation table walk)" },
> - { do_bad, SIGBUS, 0, "synchronous parity error" },
> + { do_sea, SIGBUS, 0, "level 0 SEA (translation table walk)" },
> + { do_sea, SIGBUS, 0, "level 1 SEA (translation table walk)" },
> + { do_sea, SIGBUS, 0, "level 2 SEA (translation table walk)" },
> + { do_sea, SIGBUS, 0, "level 3 SEA (translation table walk)" },

Perhaps I wasn't clear enough in my previous review, but please expand the
acronym for strings and comments.

> + { do_sea, SIGBUS, 0, "synchronous parity or ECC err" },

s/err/error/

Will