target-arm: Set PSTATE.SS correctly on exception return from AArch64

Set the PSTATE.SS bit correctly on exception returns from AArch64,
as required by the debug single-step functionality.
Signed-off-by: NPeter Maydell <peter.maydell@linaro.org>
Reviewed-by: NEdgar E. Iglesias <edgar.iglesias@xilinx.com>

target-arm/cpu.h

@@ -220,6 +220,7 @@ typedef struct CPUARMState {
         uint64_t dbgbcr[16]; /* breakpoint control registers */
         uint64_t dbgwvr[16]; /* watchpoint value registers */
         uint64_t dbgwcr[16]; /* watchpoint control registers */
+        uint64_t mdscr_el1;
         /* If the counter is enabled, this stores the last time the counter
          * was reset. Otherwise it stores the counter value
          */
@@ -1119,6 +1120,66 @@ static inline int cpu_mmu_index (CPUARMState *env)
     return arm_current_pl(env);
 }
 
+/* Return the Exception Level targeted by debug exceptions;
+ * currently always EL1 since we don't implement EL2 or EL3.
+ */
+static inline int arm_debug_target_el(CPUARMState *env)
+{
+    return 1;
+}
+
+static inline bool aa64_generate_debug_exceptions(CPUARMState *env)
+{
+    if (arm_current_pl(env) == arm_debug_target_el(env)) {
+        if ((extract32(env->cp15.mdscr_el1, 13, 1) == 0)
+            || (env->daif & PSTATE_D)) {
+            return false;
+        }
+    }
+    return true;
+}
+
+static inline bool aa32_generate_debug_exceptions(CPUARMState *env)
+{
+    if (arm_current_pl(env) == 0 && arm_el_is_aa64(env, 1)) {
+        return aa64_generate_debug_exceptions(env);
+    }
+    return arm_current_pl(env) != 2;
+}
+
+/* Return true if debugging exceptions are currently enabled.
+ * This corresponds to what in ARM ARM pseudocode would be
+ *    if UsingAArch32() then
+ *        return AArch32.GenerateDebugExceptions()
+ *    else
+ *        return AArch64.GenerateDebugExceptions()
+ * We choose to push the if() down into this function for clarity,
+ * since the pseudocode has it at all callsites except for the one in
+ * CheckSoftwareStep(), where it is elided because both branches would
+ * always return the same value.
+ *
+ * Parts of the pseudocode relating to EL2 and EL3 are omitted because we
+ * don't yet implement those exception levels or their associated trap bits.
+ */
+static inline bool arm_generate_debug_exceptions(CPUARMState *env)
+{
+    if (env->aarch64) {
+        return aa64_generate_debug_exceptions(env);
+    } else {
+        return aa32_generate_debug_exceptions(env);
+    }
+}
+
+/* Is single-stepping active? (Note that the "is EL_D AArch64?" check
+ * implicitly means this always returns false in pre-v8 CPUs.)
+ */
+static inline bool arm_singlestep_active(CPUARMState *env)
+{
+    return extract32(env->cp15.mdscr_el1, 0, 1)
+        && arm_el_is_aa64(env, arm_debug_target_el(env))
+        && arm_generate_debug_exceptions(env);
+}
+
 #include "exec/cpu-all.h"
 
 /* Bit usage in the TB flags field: bit 31 indicates whether we are

target-arm/op_helper.c

@@ -380,12 +380,26 @@ void HELPER(exception_return)(CPUARMState *env)
 
     env->exclusive_addr = -1;
 
+    /* We must squash the PSTATE.SS bit to zero unless both of the
+     * following hold:
+     *  1. debug exceptions are currently disabled
+     *  2. singlestep will be active in the EL we return to
+     * We check 1 here and 2 after we've done the pstate/cpsr write() to
+     * transition to the EL we're going to.
+     */
+    if (arm_generate_debug_exceptions(env)) {
+        spsr &= ~PSTATE_SS;
+    }
+
     if (spsr & PSTATE_nRW) {
         /* TODO: We currently assume EL1/2/3 are running in AArch64.  */
         env->aarch64 = 0;
         new_el = 0;
         env->uncached_cpsr = 0x10;
         cpsr_write(env, spsr, ~0);
+        if (!arm_singlestep_active(env)) {
+            env->uncached_cpsr &= ~PSTATE_SS;
+        }
         for (i = 0; i < 15; i++) {
             env->regs[i] = env->xregs[i];
         }
@@ -410,6 +424,9 @@ void HELPER(exception_return)(CPUARMState *env)
         }
         env->aarch64 = 1;
         pstate_write(env, spsr);
+        if (!arm_singlestep_active(env)) {
+            env->pstate &= ~PSTATE_SS;
+        }
         aarch64_restore_sp(env, new_el);
         env->pc = env->elr_el[cur_el];
     }
@@ -429,6 +446,9 @@ illegal_return:
     spsr &= PSTATE_NZCV | PSTATE_DAIF;
     spsr |= pstate_read(env) & ~(PSTATE_NZCV | PSTATE_DAIF);
     pstate_write(env, spsr);
+    if (!arm_singlestep_active(env)) {
+        env->pstate &= ~PSTATE_SS;
+    }
 }
 
 /* ??? Flag setting arithmetic is awkward because we need to do comparisons.