Re: [PATCH 21/35] arm64: mte: Add in-kernel tag fault handler

[Vincenzo Frascino]

On 8/27/20 10:54 AM, Catalin Marinas wrote:
> On Fri, Aug 14, 2020 at 07:27:03PM +0200, Andrey Konovalov wrote:
>> diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
>> index 5e832b3387f1..c62c8ba85c0e 100644
>> --- a/arch/arm64/mm/fault.c
>> +++ b/arch/arm64/mm/fault.c
>> @@ -33,6 +33,7 @@
>>  #include <asm/debug-monitors.h>
>>  #include <asm/esr.h>
>>  #include <asm/kprobes.h>
>> +#include <asm/mte.h>
>>  #include <asm/processor.h>
>>  #include <asm/sysreg.h>
>>  #include <asm/system_misc.h>
>> @@ -222,6 +223,20 @@ int ptep_set_access_flags(struct vm_area_struct *vma,
>>  	return 1;
>>  }
>>  
>> +static bool is_el1_mte_sync_tag_check_fault(unsigned int esr)
>> +{
>> +	unsigned int ec = ESR_ELx_EC(esr);
>> +	unsigned int fsc = esr & ESR_ELx_FSC;
>> +
>> +	if (ec != ESR_ELx_EC_DABT_CUR)
>> +		return false;
>> +
>> +	if (fsc == ESR_ELx_FSC_MTE)
>> +		return true;
>> +
>> +	return false;
>> +}
>> +
>>  static bool is_el1_instruction_abort(unsigned int esr)
>>  {
>>  	return ESR_ELx_EC(esr) == ESR_ELx_EC_IABT_CUR;
>> @@ -294,6 +309,18 @@ static void die_kernel_fault(const char *msg, unsigned long addr,
>>  	do_exit(SIGKILL);
>>  }
>>  
>> +static void report_tag_fault(unsigned long addr, unsigned int esr,
>> +			     struct pt_regs *regs)
>> +{
>> +	bool is_write = ((esr & ESR_ELx_WNR) >> ESR_ELx_WNR_SHIFT) != 0;
>> +
>> +	pr_alert("Memory Tagging Extension Fault in %pS\n", (void *)regs->pc);
>> +	pr_alert("  %s at address %lx\n", is_write ? "Write" : "Read", addr);
>> +	pr_alert("  Pointer tag: [%02x], memory tag: [%02x]\n",
>> +			mte_get_ptr_tag(addr),
>> +			mte_get_mem_tag((void *)addr));
>> +}
>> +
>>  static void __do_kernel_fault(unsigned long addr, unsigned int esr,
>>  			      struct pt_regs *regs)
>>  {
>> @@ -317,12 +344,16 @@ static void __do_kernel_fault(unsigned long addr, unsigned int esr,
>>  			msg = "execute from non-executable memory";
>>  		else
>>  			msg = "read from unreadable memory";
>> +	} else if (is_el1_mte_sync_tag_check_fault(esr)) {
>> +		report_tag_fault(addr, esr, regs);
>> +		msg = "memory tagging extension fault";
> 
> IIUC, that's dead code. See my comment below on do_tag_check_fault().
>

That's correct. This was useful with "panic_on_mte_fault" kernel command line
parameter. Since it has now been replaced by a similar kasan feature, this code
can be safely removed.

>>  	} else if (addr < PAGE_SIZE) {
>>  		msg = "NULL pointer dereference";
>>  	} else {
>>  		msg = "paging request";
>>  	}
>>  
>> +
> 
> Unnecessary empty line.
> 

Agree.

>>  	die_kernel_fault(msg, addr, esr, regs);
>>  }
>>  
>> @@ -658,10 +689,27 @@ static int do_sea(unsigned long addr, unsigned int esr, struct pt_regs *regs)
>>  	return 0;
>>  }
>>  
>> +static int do_tag_recovery(unsigned long addr, unsigned int esr,
>> +			   struct pt_regs *regs)
>> +{
>> +	report_tag_fault(addr, esr, regs);
>> +
>> +	/* Skip over the faulting instruction and continue: */
>> +	arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
> 
> Ooooh, do we expect the kernel to still behave correctly after this? I
> thought the recovery means disabling tag checking altogether and
> restarting the instruction rather than skipping over it. We only skip if
> we emulated it.
> 

I tried to dig it out but I am not sure why we need this as well.

>> +
>> +	return 0;
>> +}
>> +
>> +
>>  static int do_tag_check_fault(unsigned long addr, unsigned int esr,
>>  			      struct pt_regs *regs)
>>  {
>> -	do_bad_area(addr, esr, regs);
>> +	/* The tag check fault (TCF) is per TTBR */
>> +	if (is_ttbr0_addr(addr))
>> +		do_bad_area(addr, esr, regs);
>> +	else
>> +		do_tag_recovery(addr, esr, regs);
> 
> So we never invoke __do_kernel_fault() for a synchronous tag check in
> the kernel. What's with all the is_el1_mte_sync_tag_check_fault() check
> above?
> 

That's correct. This had a meaning with "panic_on_mte_fault" but since the
feature has been replaced is_el1_mte_sync_tag_check_fault() is not useful anymore.

-- 
Regards,
Vincenzo