| Message ID | 20230127175507.2895013-4-peter.maydell@linaro.org |
|---|---|
| State | Superseded |
| Headers | show |
| Series | target/arm: Implement FEAT_FGT fine-grained traps | expand |
On 1/27/23 07:54, Peter Maydell wrote: > We added the CPAccessResult values CP_ACCESS_TRAP_UNCATEGORIZED_EL2 > and CP_ACCESS_TRAP_UNCATEGORIZED_EL3 purely in order to use them in > the ats_access() function, but doing so was incorrect (a bug fixed in > a previous commit). There aren't any cases where we want an access > function to be able to request a trap to EL2 or EL3 with a zero > syndrome value, so remove these enum values. > > As well as cleaning up dead code, the motivation here is that > we'd like to implement fine-grained-trap handling in > helper_access_check_cp_reg(). Although the fine-grained traps > to EL2 are always lower priority than trap-to-same-EL and > higher priority than trap-to-EL3, they are in the middle of > various other kinds of trap-to-EL2. Knowing that a trap-to-EL2 > must always for us have the same syndrome (ie that an access > function will return CP_ACCESS_TRAP_EL2 and there is no other > kind of trap-to-EL2 enum value) means we don't have to try > to choose which of the two syndrome values to report if the > access would trap to EL2 both for the fine-grained-trap and > because the access function requires it. > > Signed-off-by: Peter Maydell<peter.maydell@linaro.org> > --- > This isn't just "not used in QEMU"; the architecture doesn't have > any cases where you need to do this, except for the FPCR/FPSR > with HCR_TGE case, which we handle in raise_exception() by > squashing the EC_ADVSIMDFPACCESSTRAP to uncategorized. > --- > target/arm/cpregs.h | 4 ++-- > target/arm/op_helper.c | 2 ++ > 2 files changed, 4 insertions(+), 2 deletions(-) Reviewed-by: Richard Henderson <richard.henderson@linaro.org> r~
diff --git a/target/arm/cpregs.h b/target/arm/cpregs.h index 7e78c2c05c6..9744179df01 100644 --- a/target/arm/cpregs.h +++ b/target/arm/cpregs.h @@ -224,10 +224,10 @@ typedef enum CPAccessResult { * Access fails and results in an exception syndrome 0x0 ("uncategorized"). * Note that this is not a catch-all case -- the set of cases which may * result in this failure is specifically defined by the architecture. + * This trap is always to the usual target EL, never directly to a + * specified target EL. */ CP_ACCESS_TRAP_UNCATEGORIZED = (2 << 2), - CP_ACCESS_TRAP_UNCATEGORIZED_EL2 = CP_ACCESS_TRAP_UNCATEGORIZED | 2, - CP_ACCESS_TRAP_UNCATEGORIZED_EL3 = CP_ACCESS_TRAP_UNCATEGORIZED | 3, } CPAccessResult; typedef struct ARMCPRegInfo ARMCPRegInfo; diff --git a/target/arm/op_helper.c b/target/arm/op_helper.c index 31f89db8997..def5d3515e2 100644 --- a/target/arm/op_helper.c +++ b/target/arm/op_helper.c @@ -673,6 +673,8 @@ const void *HELPER(access_check_cp_reg)(CPUARMState *env, uint32_t key, case CP_ACCESS_TRAP: break; case CP_ACCESS_TRAP_UNCATEGORIZED: + /* Only CP_ACCESS_TRAP traps are direct to a specified EL */ + assert((res & CP_ACCESS_EL_MASK) == 0); if (cpu_isar_feature(aa64_ids, cpu) && isread && arm_cpreg_in_idspace(ri)) { /*
We added the CPAccessResult values CP_ACCESS_TRAP_UNCATEGORIZED_EL2 and CP_ACCESS_TRAP_UNCATEGORIZED_EL3 purely in order to use them in the ats_access() function, but doing so was incorrect (a bug fixed in a previous commit). There aren't any cases where we want an access function to be able to request a trap to EL2 or EL3 with a zero syndrome value, so remove these enum values. As well as cleaning up dead code, the motivation here is that we'd like to implement fine-grained-trap handling in helper_access_check_cp_reg(). Although the fine-grained traps to EL2 are always lower priority than trap-to-same-EL and higher priority than trap-to-EL3, they are in the middle of various other kinds of trap-to-EL2. Knowing that a trap-to-EL2 must always for us have the same syndrome (ie that an access function will return CP_ACCESS_TRAP_EL2 and there is no other kind of trap-to-EL2 enum value) means we don't have to try to choose which of the two syndrome values to report if the access would trap to EL2 both for the fine-grained-trap and because the access function requires it. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- This isn't just "not used in QEMU"; the architecture doesn't have any cases where you need to do this, except for the FPCR/FPSR with HCR_TGE case, which we handle in raise_exception() by squashing the EC_ADVSIMDFPACCESSTRAP to uncategorized. --- target/arm/cpregs.h | 4 ++-- target/arm/op_helper.c | 2 ++ 2 files changed, 4 insertions(+), 2 deletions(-)