target/arm: All UNDEF-at-EL0 traps take priority over HSTR_EL2 traps

target/arm: All UNDEF-at-EL0 traps take priority over HSTR_EL2 traps

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>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Tested-by: Fuad Tabba <tabba@google.com>
Message-id: 20230130182459.3309057-6-peter.maydell@linaro.org
Message-id: 20230127175507.2895013-6-peter.maydell@linaro.org