Re: [PATCH 05/23] target/arm: All UNDEF-at-EL0 traps take priority over HSTR_EL2 traps

[Richard Henderson <richard.henderson@linaro.org>]

On 1/27/23 07:54, Peter Maydell wrote:
> The HSTR_EL2 register has a collection of trap bits which allow
> trapping to EL2 for AArch32 EL0 or EL1 accesses to coprocessor
> registers.  The specification of these bits is that when the bit is
> set we should trap
>   * EL1 accesses
>   * EL0 accesses, if the access is not UNDEFINED when the
>     trap bit is 0
> 
> In other words, all UNDEF traps from EL0 to EL1 take precedence over
> the HSTR_EL2 trap to EL2.  (Since this is all AArch32, the only kind
> of trap-to-EL1 is the UNDEF.)
> 
> Our implementation doesn't quite get this right -- we check for traps
> in the order:
>   * no such register
>   * ARMCPRegInfo::access bits
>   * HSTR_EL2 trap bits
>   * ARMCPRegInfo::accessfn
> 
> So UNDEFs that happen because of the access bits or because the
> register doesn't exist at all correctly take priority over the
> HSTR_EL2 trap, but where a register can UNDEF at EL0 because of the
> accessfn we are incorrectly always taking the HSTR_EL2 trap.  There
> aren't many of these, but one example is the PMCR; if you look at the
> access pseudocode for this register you can see that UNDEFs taken
> because of the value of PMUSERENR.EN are checked before the HSTR_EL2
> bit.
> 
> Rearrange helper_access_check_cp_reg() so that we always call the
> accessfn, and use its return value if it indicates that the access
> traps to EL0 rather than continuing to do the HSTR_EL2 check.
> 
> Signed-off-by: Peter Maydell<peter.maydell@linaro.org>
> ---
>   target/arm/op_helper.c | 21 ++++++++++++++++-----
>   1 file changed, 16 insertions(+), 5 deletions(-)

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>

r~