Hi Tyler,
On 01/02/17 17:16, 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, report the error
> in the kernel logs.
> Update fault_info[] with specific SEA faults so that the
> new SEA handler is used.
> diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
> index 156169c..9ae7e65 100644
> --- a/arch/arm64/mm/fault.c
> +++ b/arch/arm64/mm/fault.c
> @@ -487,6 +487,31 @@ static int do_bad(unsigned long addr, unsigned int esr, struct pt_regs *regs)
> return 1;
> }
>
> +#define SEA_FnV_MASK 0x00000400
There are a glut of ESR_ELx_ macros in arch/arm64/include/asm/esr.h, could this
be fitted in there in a similar format?
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -83,6 +83,7 @@
#define ESR_ELx_WNR (UL(1) << 6)
/* Shared ISS field definitions for Data/Instruction aborts */
+#define ESR_ELx_FnV (UL(1) << 10)
#define ESR_ELx_EA (UL(1) << 9)
#define ESR_ELx_S1PTW (UL(1) << 7)
> +
> +/*
> + * 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;
> +
> + 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;
> + if (esr & SEA_FnV_MASK)
> + info.si_addr = 0;
> + else
> + 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;
> @@ -509,22 +534,22 @@ static int do_bad(unsigned long addr, unsigned int esr, struct pt_regs *regs)
> { 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" },
This will print:
> Synchronous External Abort: synchronous external abort
It looks odd, but I can't think of anything better to put there.
> { do_bad, SIGBUS, 0, "unknown 17" },
> { do_bad, SIGBUS, 0, "unknown 18" },
> { do_bad, SIGBUS, 0, "unknown 19" },
> - { do_bad, SIGBUS, 0, "synchronous external abort (translation table walk)" },
> - { do_bad, SIGBUS, 0, "synchronous external abort (translation table walk)" },
> - { do_bad, SIGBUS, 0, "synchronous external abort (translation table walk)" },
> - { do_bad, SIGBUS, 0, "synchronous external abort (translation table walk)" },
> - { do_bad, SIGBUS, 0, "synchronous parity error" },
> + { do_sea, SIGBUS, 0, "level 0 (translation table walk)" },
> + { do_sea, SIGBUS, 0, "level 1 (translation table walk)" },
> + { do_sea, SIGBUS, 0, "level 2 (translation table walk)" },
> + { do_sea, SIGBUS, 0, "level 3 (translation table walk)" },
> + { do_sea, SIGBUS, 0, "synchronous parity or ECC error" },
> { do_bad, SIGBUS, 0, "unknown 25" },
> { do_bad, SIGBUS, 0, "unknown 26" },
> { do_bad, SIGBUS, 0, "unknown 27" },
> - { do_bad, SIGBUS, 0, "synchronous parity error (translation table walk)" },
> - { do_bad, SIGBUS, 0, "synchronous parity error (translation table walk)" },
> - { do_bad, SIGBUS, 0, "synchronous parity error (translation table walk)" },
> - { do_bad, SIGBUS, 0, "synchronous parity error (translation table walk)" },
> + { do_sea, SIGBUS, 0, "level 0 synchronous parity error (translation table walk)" },
> + { do_sea, SIGBUS, 0, "level 1 synchronous parity error (translation table walk)" },
> + { do_sea, SIGBUS, 0, "level 2 synchronous parity error (translation table walk)" },
> + { do_sea, SIGBUS, 0, "level 3 synchronous parity error (translation table walk)" },
> { do_bad, SIGBUS, 0, "unknown 32" },
> { do_alignment_fault, SIGBUS, BUS_ADRALN, "alignment fault" },
> { do_bad, SIGBUS, 0, "unknown 34" },
>
With the ESR_ELx_FnV change above,
Reviewed-by: James Morse <james.morse@xxxxxxx>
Thanks,
James
