target-arm: Implement ARMv8 single-stepping for AArch32 code

ARMv8 single-stepping requires the exception level that controls
the single-stepping to be in AArch64 execution state, but the
code being stepped may be in AArch64 or AArch32. Implement the
necessary support code for single-stepping AArch32 code.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com>

2 files changed, 95 insertions, 2 deletions

diff --git a/target-arm/cpu.h b/target-arm/cpu.h
index 3d3e1d5..8098b8d 100644
--- a/target-arm/cpu.h
+++ b/target-arm/cpu.h
@@ -1205,6 +1205,10 @@ static inline bool arm_singlestep_active(CPUARMState *env)
 #define ARM_TBFLAG_BSWAP_CODE_MASK  (1 << ARM_TBFLAG_BSWAP_CODE_SHIFT)
 #define ARM_TBFLAG_CPACR_FPEN_SHIFT 17
 #define ARM_TBFLAG_CPACR_FPEN_MASK  (1 << ARM_TBFLAG_CPACR_FPEN_SHIFT)
+#define ARM_TBFLAG_SS_ACTIVE_SHIFT 18
+#define ARM_TBFLAG_SS_ACTIVE_MASK (1 << ARM_TBFLAG_SS_ACTIVE_SHIFT)
+#define ARM_TBFLAG_PSTATE_SS_SHIFT 19
+#define ARM_TBFLAG_PSTATE_SS_MASK (1 << ARM_TBFLAG_PSTATE_SS_SHIFT)
 
 /* Bit usage when in AArch64 state */
 #define ARM_TBFLAG_AA64_EL_SHIFT    0
@@ -1235,6 +1239,10 @@ static inline bool arm_singlestep_active(CPUARMState *env)
     (((F) & ARM_TBFLAG_BSWAP_CODE_MASK) >> ARM_TBFLAG_BSWAP_CODE_SHIFT)
 #define ARM_TBFLAG_CPACR_FPEN(F) \
     (((F) & ARM_TBFLAG_CPACR_FPEN_MASK) >> ARM_TBFLAG_CPACR_FPEN_SHIFT)
+#define ARM_TBFLAG_SS_ACTIVE(F) \
+    (((F) & ARM_TBFLAG_SS_ACTIVE_MASK) >> ARM_TBFLAG_SS_ACTIVE_SHIFT)
+#define ARM_TBFLAG_PSTATE_SS(F) \
+    (((F) & ARM_TBFLAG_PSTATE_SS_MASK) >> ARM_TBFLAG_PSTATE_SS_SHIFT)
 #define ARM_TBFLAG_AA64_EL(F) \
     (((F) & ARM_TBFLAG_AA64_EL_MASK) >> ARM_TBFLAG_AA64_EL_SHIFT)
 #define ARM_TBFLAG_AA64_FPEN(F) \
@@ -1292,6 +1300,19 @@ static inline void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc,
         if (fpen == 3 || (fpen == 1 && arm_current_pl(env) != 0)) {
             *flags |= ARM_TBFLAG_CPACR_FPEN_MASK;
         }
+        /* The SS_ACTIVE and PSTATE_SS bits correspond to the state machine
+         * states defined in the ARM ARM for software singlestep:
+         *  SS_ACTIVE   PSTATE.SS   State
+         *     0            x       Inactive (the TB flag for SS is always 0)
+         *     1            0       Active-pending
+         *     1            1       Active-not-pending
+         */
+        if (arm_singlestep_active(env)) {
+            *flags |= ARM_TBFLAG_SS_ACTIVE_MASK;
+            if (env->uncached_cpsr & PSTATE_SS) {
+                *flags |= ARM_TBFLAG_PSTATE_SS_MASK;
+            }
+        }
     }
 
     *cs_base = 0;
diff --git a/target-arm/translate.c b/target-arm/translate.c
index 4cde309..2c0b1de 100644
--- a/target-arm/translate.c
+++ b/target-arm/translate.c
@@ -205,6 +205,33 @@ static void gen_exception(int excp, uint32_t syndrome)
     tcg_temp_free_i32(tcg_excp);
 }
 
+static void gen_ss_advance(DisasContext *s)
+{
+    /* If the singlestep state is Active-not-pending, advance to
+     * Active-pending.
+     */
+    if (s->ss_active) {
+        s->pstate_ss = 0;
+        gen_helper_clear_pstate_ss(cpu_env);
+    }
+}
+
+static void gen_step_complete_exception(DisasContext *s)
+{
+    /* We just completed step of an insn. Move from Active-not-pending
+     * to Active-pending, and then also take the swstep exception.
+     * This corresponds to making the (IMPDEF) choice to prioritize
+     * swstep exceptions over asynchronous exceptions taken to an exception
+     * level where debug is disabled. This choice has the advantage that
+     * we do not need to maintain internal state corresponding to the
+     * ISV/EX syndrome bits between completion of the step and generation
+     * of the exception, and our syndrome information is always correct.
+     */
+    gen_ss_advance(s);
+    gen_exception(EXCP_UDEF, syn_swstep(s->ss_same_el, 1, s->is_ldex));
+    s->is_jmp = DISAS_EXC;
+}
+
 static void gen_smul_dual(TCGv_i32 a, TCGv_i32 b)
 {
     TCGv_i32 tmp1 = tcg_temp_new_i32();
@@ -3860,7 +3887,7 @@ static inline void gen_goto_tb(DisasContext *s, int n, target_ulong dest)
 
 static inline void gen_jmp (DisasContext *s, uint32_t dest)
 {
-    if (unlikely(s->singlestep_enabled)) {
+    if (unlikely(s->singlestep_enabled || s->ss_active)) {
         /* An indirect jump so that we still trigger the debug exception.  */
         if (s->thumb)
             dest |= 1;
@@ -7281,6 +7308,8 @@ static void gen_load_exclusive(DisasContext *s, int rt, int rt2,
 {
     TCGv_i32 tmp = tcg_temp_new_i32();
 
+    s->is_ldex = true;
+
     switch (size) {
     case 0:
         gen_aa32_ld8u(tmp, addr, get_mem_index(s));
@@ -10917,6 +10946,26 @@ static inline void gen_intermediate_code_internal(ARMCPU *cpu,
     dc->current_pl = arm_current_pl(env);
     dc->features = env->features;
 
+    /* Single step state. The code-generation logic here is:
+     *  SS_ACTIVE == 0:
+     *   generate code with no special handling for single-stepping (except
+     *   that anything that can make us go to SS_ACTIVE == 1 must end the TB;
+     *   this happens anyway because those changes are all system register or
+     *   PSTATE writes).
+     *  SS_ACTIVE == 1, PSTATE.SS == 1: (active-not-pending)
+     *   emit code for one insn
+     *   emit code to clear PSTATE.SS
+     *   emit code to generate software step exception for completed step
+     *   end TB (as usual for having generated an exception)
+     *  SS_ACTIVE == 1, PSTATE.SS == 0: (active-pending)
+     *   emit code to generate a software step exception
+     *   end the TB
+     */
+    dc->ss_active = ARM_TBFLAG_SS_ACTIVE(tb->flags);
+    dc->pstate_ss = ARM_TBFLAG_PSTATE_SS(tb->flags);
+    dc->is_ldex = false;
+    dc->ss_same_el = false; /* Can't be true since EL_d must be AArch64 */
+
     cpu_F0s = tcg_temp_new_i32();
     cpu_F1s = tcg_temp_new_i32();
     cpu_F0d = tcg_temp_new_i64();
@@ -11026,6 +11075,22 @@ static inline void gen_intermediate_code_internal(ARMCPU *cpu,
             tcg_gen_debug_insn_start(dc->pc);
         }
 
+        if (dc->ss_active && !dc->pstate_ss) {
+            /* Singlestep state is Active-pending.
+             * If we're in this state at the start of a TB then either
+             *  a) we just took an exception to an EL which is being debugged
+             *     and this is the first insn in the exception handler
+             *  b) debug exceptions were masked and we just unmasked them
+             *     without changing EL (eg by clearing PSTATE.D)
+             * In either case we're going to take a swstep exception in the
+             * "did not step an insn" case, and so the syndrome ISV and EX
+             * bits should be zero.
+             */
+            assert(num_insns == 0);
+            gen_exception(EXCP_UDEF, syn_swstep(dc->ss_same_el, 0, 0));
+            goto done_generating;
+        }
+
         if (dc->thumb) {
             disas_thumb_insn(env, dc);
             if (dc->condexec_mask) {
@@ -11058,6 +11123,7 @@ static inline void gen_intermediate_code_internal(ARMCPU *cpu,
     } while (!dc->is_jmp && tcg_ctx.gen_opc_ptr < gen_opc_end &&
              !cs->singlestep_enabled &&
              !singlestep &&
+             !dc->ss_active &&
              dc->pc < next_page_start &&
              num_insns < max_insns);
 
@@ -11073,12 +11139,15 @@ static inline void gen_intermediate_code_internal(ARMCPU *cpu,
     /* At this stage dc->condjmp will only be set when the skipped
        instruction was a conditional branch or trap, and the PC has
        already been written.  */
-    if (unlikely(cs->singlestep_enabled)) {
+    if (unlikely(cs->singlestep_enabled || dc->ss_active)) {
         /* Make sure the pc is updated, and raise a debug exception.  */
         if (dc->condjmp) {
             gen_set_condexec(dc);
             if (dc->is_jmp == DISAS_SWI) {
+                gen_ss_advance(dc);
                 gen_exception(EXCP_SWI, syn_aa32_svc(dc->svc_imm, dc->thumb));
+            } else if (dc->ss_active) {
+                gen_step_complete_exception(dc);
             } else {
                 gen_exception_internal(EXCP_DEBUG);
             }
@@ -11090,7 +11159,10 @@ static inline void gen_intermediate_code_internal(ARMCPU *cpu,
         }
         gen_set_condexec(dc);
         if (dc->is_jmp == DISAS_SWI && !dc->condjmp) {
+            gen_ss_advance(dc);
             gen_exception(EXCP_SWI, syn_aa32_svc(dc->svc_imm, dc->thumb));
+        } else if (dc->ss_active) {
+            gen_step_complete_exception(dc);
         } else {
             /* FIXME: Single stepping a WFI insn will not halt
                the CPU.  */