target/arm: Fold secure and non-secure a-profile mmu indexes

For a-profile aarch64, which does not bank system registers, it takes
quite a lot of code to switch between security states.  In the process,
registers such as TCR_EL{1,2} must be swapped, which in itself requires
the flushing of softmmu tlbs.  Therefore it doesn't buy us anything to
separate tlbs by security state.

Retain the distinction between Stage2 and Stage2_S.

This will be important as we implement FEAT_RME, and do not wish to
add a third set of mmu indexes for Realm state.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20221001162318.153420-11-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

1 files changed, 26 insertions, 46 deletions

diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index a085c17297..53f4c236e1 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -2884,26 +2884,27 @@ bool write_cpustate_to_list(ARMCPU *cpu, bool kvm_sync);
  *     table over and over.
  *  6. we need separate EL1/EL2 mmu_idx for handling the Privileged Access
  *     Never (PAN) bit within PSTATE.
+ *  7. we fold together the secure and non-secure regimes for A-profile,
+ *     because there are no banked system registers for aarch64, so the
+ *     process of switching between secure and non-secure is
+ *     already heavyweight.
  *
  * This gives us the following list of cases:
  *
- * NS EL0 EL1&0 stage 1+2 (aka NS PL0)
- * NS EL1 EL1&0 stage 1+2 (aka NS PL1)
- * NS EL1 EL1&0 stage 1+2 +PAN
- * NS EL0 EL2&0
- * NS EL2 EL2&0
- * NS EL2 EL2&0 +PAN
- * NS EL2 (aka NS PL2)
- * S EL0 EL1&0 (aka S PL0)
- * S EL1 EL1&0 (not used if EL3 is 32 bit)
- * S EL1 EL1&0 +PAN
- * S EL3 (aka S PL1)
+ * EL0 EL1&0 stage 1+2 (aka NS PL0)
+ * EL1 EL1&0 stage 1+2 (aka NS PL1)
+ * EL1 EL1&0 stage 1+2 +PAN
+ * EL0 EL2&0
+ * EL2 EL2&0
+ * EL2 EL2&0 +PAN
+ * EL2 (aka NS PL2)
+ * EL3 (aka S PL1)
  *
- * for a total of 11 different mmu_idx.
+ * for a total of 8 different mmu_idx.
  *
  * R profile CPUs have an MPU, but can use the same set of MMU indexes
- * as A profile. They only need to distinguish NS EL0 and NS EL1 (and
- * NS EL2 if we ever model a Cortex-R52).
+ * as A profile. They only need to distinguish EL0 and EL1 (and
+ * EL2 if we ever model a Cortex-R52).
  *
  * M profile CPUs are rather different as they do not have a true MMU.
  * They have the following different MMU indexes:
@@ -2942,9 +2943,6 @@ bool write_cpustate_to_list(ARMCPU *cpu, bool kvm_sync);
 #define ARM_MMU_IDX_NOTLB 0x20  /* does not have a TLB */
 #define ARM_MMU_IDX_M     0x40  /* M profile */
 
-/* Meanings of the bits for A profile mmu idx values */
-#define ARM_MMU_IDX_A_NS     0x8
-
 /* Meanings of the bits for M profile mmu idx values */
 #define ARM_MMU_IDX_M_PRIV   0x1
 #define ARM_MMU_IDX_M_NEGPRI 0x2
@@ -2958,22 +2956,14 @@ typedef enum ARMMMUIdx {
     /*
      * A-profile.
      */
-    ARMMMUIdx_SE10_0     =  0 | ARM_MMU_IDX_A,
-    ARMMMUIdx_SE20_0     =  1 | ARM_MMU_IDX_A,
-    ARMMMUIdx_SE10_1     =  2 | ARM_MMU_IDX_A,
-    ARMMMUIdx_SE20_2     =  3 | ARM_MMU_IDX_A,
-    ARMMMUIdx_SE10_1_PAN =  4 | ARM_MMU_IDX_A,
-    ARMMMUIdx_SE20_2_PAN =  5 | ARM_MMU_IDX_A,
-    ARMMMUIdx_SE2        =  6 | ARM_MMU_IDX_A,
-    ARMMMUIdx_SE3        =  7 | ARM_MMU_IDX_A,
-
-    ARMMMUIdx_E10_0     = ARMMMUIdx_SE10_0 | ARM_MMU_IDX_A_NS,
-    ARMMMUIdx_E20_0     = ARMMMUIdx_SE20_0 | ARM_MMU_IDX_A_NS,
-    ARMMMUIdx_E10_1     = ARMMMUIdx_SE10_1 | ARM_MMU_IDX_A_NS,
-    ARMMMUIdx_E20_2     = ARMMMUIdx_SE20_2 | ARM_MMU_IDX_A_NS,
-    ARMMMUIdx_E10_1_PAN = ARMMMUIdx_SE10_1_PAN | ARM_MMU_IDX_A_NS,
-    ARMMMUIdx_E20_2_PAN = ARMMMUIdx_SE20_2_PAN | ARM_MMU_IDX_A_NS,
-    ARMMMUIdx_E2        = ARMMMUIdx_SE2 | ARM_MMU_IDX_A_NS,
+    ARMMMUIdx_E10_0     = 0 | ARM_MMU_IDX_A,
+    ARMMMUIdx_E20_0     = 1 | ARM_MMU_IDX_A,
+    ARMMMUIdx_E10_1     = 2 | ARM_MMU_IDX_A,
+    ARMMMUIdx_E20_2     = 3 | ARM_MMU_IDX_A,
+    ARMMMUIdx_E10_1_PAN = 4 | ARM_MMU_IDX_A,
+    ARMMMUIdx_E20_2_PAN = 5 | ARM_MMU_IDX_A,
+    ARMMMUIdx_E2        = 6 | ARM_MMU_IDX_A,
+    ARMMMUIdx_E3        = 7 | ARM_MMU_IDX_A,
 
     /*
      * These are not allocated TLBs and are used only for AT system
@@ -2982,9 +2972,6 @@ typedef enum ARMMMUIdx {
     ARMMMUIdx_Stage1_E0 = 0 | ARM_MMU_IDX_NOTLB,
     ARMMMUIdx_Stage1_E1 = 1 | ARM_MMU_IDX_NOTLB,
     ARMMMUIdx_Stage1_E1_PAN = 2 | ARM_MMU_IDX_NOTLB,
-    ARMMMUIdx_Stage1_SE0 = 3 | ARM_MMU_IDX_NOTLB,
-    ARMMMUIdx_Stage1_SE1 = 4 | ARM_MMU_IDX_NOTLB,
-    ARMMMUIdx_Stage1_SE1_PAN = 5 | ARM_MMU_IDX_NOTLB,
     /*
      * Not allocated a TLB: used only for second stage of an S12 page
      * table walk, or for descriptor loads during first stage of an S1
@@ -2992,8 +2979,8 @@ typedef enum ARMMMUIdx {
      * then various TLB flush insns which currently are no-ops or flush
      * only stage 1 MMU indexes will need to change to flush stage 2.
      */
-    ARMMMUIdx_Stage2     = 6 | ARM_MMU_IDX_NOTLB,
-    ARMMMUIdx_Stage2_S   = 7 | ARM_MMU_IDX_NOTLB,
+    ARMMMUIdx_Stage2     = 3 | ARM_MMU_IDX_NOTLB,
+    ARMMMUIdx_Stage2_S   = 4 | ARM_MMU_IDX_NOTLB,
 
     /*
      * M-profile.
@@ -3023,14 +3010,7 @@ typedef enum ARMMMUIdxBit {
     TO_CORE_BIT(E2),
     TO_CORE_BIT(E20_2),
     TO_CORE_BIT(E20_2_PAN),
-    TO_CORE_BIT(SE10_0),
-    TO_CORE_BIT(SE20_0),
-    TO_CORE_BIT(SE10_1),
-    TO_CORE_BIT(SE20_2),
-    TO_CORE_BIT(SE10_1_PAN),
-    TO_CORE_BIT(SE20_2_PAN),
-    TO_CORE_BIT(SE2),
-    TO_CORE_BIT(SE3),
+    TO_CORE_BIT(E3),
 
     TO_CORE_BIT(MUser),
     TO_CORE_BIT(MPriv),