[PATCH -next v5 6/8] arm64: add support for machine check error safe

Mark Rutland mark.rutland at arm.com
Fri Jun 17 18:55:19 AEST 2022


On Sat, May 28, 2022 at 06:50:54AM +0000, Tong Tiangen wrote:
> During the processing of arm64 kernel hardware memory errors(do_sea()), if
> the errors is consumed in the kernel, the current processing is panic.
> However, it is not optimal.
> 
> Take uaccess for example, if the uaccess operation fails due to memory
> error, only the user process will be affected, kill the user process
> and isolate the user page with hardware memory errors is a better choice.
> 
> This patch only enable machine error check framework, it add exception
> fixup before kernel panic in do_sea() and only limit the consumption of
> hardware memory errors in kernel mode triggered by user mode processes.
> If fixup successful, panic can be avoided.
> 
> Signed-off-by: Tong Tiangen <tongtiangen at huawei.com>
> ---
>  arch/arm64/Kconfig               |  1 +
>  arch/arm64/include/asm/extable.h |  1 +
>  arch/arm64/mm/extable.c          | 17 +++++++++++++++++
>  arch/arm64/mm/fault.c            | 27 ++++++++++++++++++++++++++-
>  4 files changed, 45 insertions(+), 1 deletion(-)
> 
> diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
> index aaeb70358979..a3b12ff0cd7f 100644
> --- a/arch/arm64/Kconfig
> +++ b/arch/arm64/Kconfig
> @@ -19,6 +19,7 @@ config ARM64
>  	select ARCH_ENABLE_SPLIT_PMD_PTLOCK if PGTABLE_LEVELS > 2
>  	select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE
>  	select ARCH_HAS_CACHE_LINE_SIZE
> +	select ARCH_HAS_COPY_MC if ACPI_APEI_GHES
>  	select ARCH_HAS_CURRENT_STACK_POINTER
>  	select ARCH_HAS_DEBUG_VIRTUAL
>  	select ARCH_HAS_DEBUG_VM_PGTABLE
> diff --git a/arch/arm64/include/asm/extable.h b/arch/arm64/include/asm/extable.h
> index 72b0e71cc3de..f80ebd0addfd 100644
> --- a/arch/arm64/include/asm/extable.h
> +++ b/arch/arm64/include/asm/extable.h
> @@ -46,4 +46,5 @@ bool ex_handler_bpf(const struct exception_table_entry *ex,
>  #endif /* !CONFIG_BPF_JIT */
>  
>  bool fixup_exception(struct pt_regs *regs);
> +bool fixup_exception_mc(struct pt_regs *regs);
>  #endif
> diff --git a/arch/arm64/mm/extable.c b/arch/arm64/mm/extable.c
> index 228d681a8715..c301dcf6335f 100644
> --- a/arch/arm64/mm/extable.c
> +++ b/arch/arm64/mm/extable.c
> @@ -9,6 +9,7 @@
>  
>  #include <asm/asm-extable.h>
>  #include <asm/ptrace.h>
> +#include <asm/esr.h>
>  
>  static inline unsigned long
>  get_ex_fixup(const struct exception_table_entry *ex)
> @@ -76,3 +77,19 @@ bool fixup_exception(struct pt_regs *regs)
>  
>  	BUG();
>  }
> +
> +bool fixup_exception_mc(struct pt_regs *regs)
> +{
> +	const struct exception_table_entry *ex;
> +
> +	ex = search_exception_tables(instruction_pointer(regs));
> +	if (!ex)
> +		return false;
> +
> +	/*
> +	 * This is not complete, More Machine check safe extable type can
> +	 * be processed here.
> +	 */
> +
> +	return false;
> +}
> diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
> index c5e11768e5c1..b262bd282a89 100644
> --- a/arch/arm64/mm/fault.c
> +++ b/arch/arm64/mm/fault.c
> @@ -696,6 +696,29 @@ static int do_bad(unsigned long far, unsigned long esr, struct pt_regs *regs)
>  	return 1; /* "fault" */
>  }
>  
> +static bool arm64_do_kernel_sea(unsigned long addr, unsigned int esr,
> +				     struct pt_regs *regs, int sig, int code)
> +{
> +	if (!IS_ENABLED(CONFIG_ARCH_HAS_COPY_MC))
> +		return false;
> +
> +	if (user_mode(regs) || !current->mm)
> +		return false;

What's the `!current->mm` check for?

> +
> +	if (apei_claim_sea(regs) < 0)
> +		return false;
> +
> +	if (!fixup_exception_mc(regs))
> +		return false;

I thought we still wanted to signal the task in this case? Or do you expect to
add that into `fixup_exception_mc()` ?

> +
> +	set_thread_esr(0, esr);

Why are we not setting the address? Is that deliberate, or an oversight?

> +
> +	arm64_force_sig_fault(sig, code, addr,
> +		"Uncorrected hardware memory error in kernel-access\n");

I think the wording here is misleading since we don't expect to recover from
accesses to kernel memory, and would be better as something like:

	"Uncorrected memory error on access to user memory\n"

Thanks,
Mark.

> +
> +	return true;
> +}
> +
>  static int do_sea(unsigned long far, unsigned long esr, struct pt_regs *regs)
>  {
>  	const struct fault_info *inf;
> @@ -721,7 +744,9 @@ static int do_sea(unsigned long far, unsigned long esr, struct pt_regs *regs)
>  		 */
>  		siaddr  = untagged_addr(far);
>  	}
> -	arm64_notify_die(inf->name, regs, inf->sig, inf->code, siaddr, esr);
> +
> +	if (!arm64_do_kernel_sea(siaddr, esr, regs, inf->sig, inf->code))
> +		arm64_notify_die(inf->name, regs, inf->sig, inf->code, siaddr, esr);
>  
>  	return 0;
>  }
> -- 
> 2.25.1
> 


More information about the Linuxppc-dev mailing list