[Qemu-devel] [PULL 37/37] target/arm: Implement the ARMv8.1-LOR extension

[Peter Maydell]

From: Richard Henderson <address@hidden>

Provide a trivial implementation with zero limited ordering regions,
which causes the LDLAR and STLLR instructions to devolve into the
LDAR and STLR instructions from the base ARMv8.0 instruction set.

Reviewed-by: Peter Maydell <address@hidden>
Signed-off-by: Richard Henderson <address@hidden>
Message-id: address@hidden
Signed-off-by: Peter Maydell <address@hidden>
---
 target/arm/cpu.h           |  5 +++
 target/arm/cpu64.c         |  1 +
 target/arm/helper.c        | 75 ++++++++++++++++++++++++++++++++++++++
 target/arm/translate-a64.c | 12 ++++++
 4 files changed, 93 insertions(+)

diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index 05ac883b6be..c943f35dd92 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -3340,6 +3340,11 @@ static inline bool isar_feature_aa64_sve(const 
ARMISARegisters *id)
     return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, SVE) != 0;
 }
 
+static inline bool isar_feature_aa64_lor(const ARMISARegisters *id)
+{
+    return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, LO) != 0;
+}
+
 /*
  * Forward to the above feature tests given an ARMCPU pointer.
  */
diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c
index 1a4289c9dda..1d57be0c910 100644
--- a/target/arm/cpu64.c
+++ b/target/arm/cpu64.c
@@ -326,6 +326,7 @@ static void aarch64_max_initfn(Object *obj)
 
         t = cpu->isar.id_aa64mmfr1;
         t = FIELD_DP64(t, ID_AA64MMFR1, HPDS, 1); /* HPD */
+        t = FIELD_DP64(t, ID_AA64MMFR1, LO, 1);
         cpu->isar.id_aa64mmfr1 = t;
 
         /* Replicate the same data to the 32-bit id registers.  */
diff --git a/target/arm/helper.c b/target/arm/helper.c
index d6f8be9f4e1..644599b29d6 100644
--- a/target/arm/helper.c
+++ b/target/arm/helper.c
@@ -1281,6 +1281,7 @@ static void scr_write(CPUARMState *env, const 
ARMCPRegInfo *ri, uint64_t value)
 {
     /* Begin with base v8.0 state.  */
     uint32_t valid_mask = 0x3fff;
+    ARMCPU *cpu = arm_env_get_cpu(env);
 
     if (arm_el_is_aa64(env, 3)) {
         value |= SCR_FW | SCR_AW;   /* these two bits are RES1.  */
@@ -1303,6 +1304,9 @@ static void scr_write(CPUARMState *env, const 
ARMCPRegInfo *ri, uint64_t value)
             valid_mask &= ~SCR_SMD;
         }
     }
+    if (cpu_isar_feature(aa64_lor, cpu)) {
+        valid_mask |= SCR_TLOR;
+    }
 
     /* Clear all-context RES0 bits.  */
     value &= valid_mask;
@@ -3963,6 +3967,9 @@ static void hcr_write(CPUARMState *env, const 
ARMCPRegInfo *ri, uint64_t value)
          */
         valid_mask &= ~HCR_TSC;
     }
+    if (cpu_isar_feature(aa64_lor, cpu)) {
+        valid_mask |= HCR_TLOR;
+    }
 
     /* Clear RES0 bits.  */
     value &= valid_mask;
@@ -5018,6 +5025,42 @@ static uint64_t id_aa64pfr0_read(CPUARMState *env, const 
ARMCPRegInfo *ri)
     return pfr0;
 }
 
+/* Shared logic between LORID and the rest of the LOR* registers.
+ * Secure state has already been delt with.
+ */
+static CPAccessResult access_lor_ns(CPUARMState *env)
+{
+    int el = arm_current_el(env);
+
+    if (el < 2 && (arm_hcr_el2_eff(env) & HCR_TLOR)) {
+        return CP_ACCESS_TRAP_EL2;
+    }
+    if (el < 3 && (env->cp15.scr_el3 & SCR_TLOR)) {
+        return CP_ACCESS_TRAP_EL3;
+    }
+    return CP_ACCESS_OK;
+}
+
+static CPAccessResult access_lorid(CPUARMState *env, const ARMCPRegInfo *ri,
+                                   bool isread)
+{
+    if (arm_is_secure_below_el3(env)) {
+        /* Access ok in secure mode.  */
+        return CP_ACCESS_OK;
+    }
+    return access_lor_ns(env);
+}
+
+static CPAccessResult access_lor_other(CPUARMState *env,
+                                       const ARMCPRegInfo *ri, bool isread)
+{
+    if (arm_is_secure_below_el3(env)) {
+        /* Access denied in secure mode.  */
+        return CP_ACCESS_TRAP;
+    }
+    return access_lor_ns(env);
+}
+
 void register_cp_regs_for_features(ARMCPU *cpu)
 {
     /* Register all the coprocessor registers based on feature bits */
@@ -5759,6 +5802,38 @@ void register_cp_regs_for_features(ARMCPU *cpu)
         define_one_arm_cp_reg(cpu, &sctlr);
     }
 
+    if (cpu_isar_feature(aa64_lor, cpu)) {
+        /*
+         * A trivial implementation of ARMv8.1-LOR leaves all of these
+         * registers fixed at 0, which indicates that there are zero
+         * supported Limited Ordering regions.
+         */
+        static const ARMCPRegInfo lor_reginfo[] = {
+            { .name = "LORSA_EL1", .state = ARM_CP_STATE_AA64,
+              .opc0 = 3, .opc1 = 0, .crn = 10, .crm = 4, .opc2 = 0,
+              .access = PL1_RW, .accessfn = access_lor_other,
+              .type = ARM_CP_CONST, .resetvalue = 0 },
+            { .name = "LOREA_EL1", .state = ARM_CP_STATE_AA64,
+              .opc0 = 3, .opc1 = 0, .crn = 10, .crm = 4, .opc2 = 1,
+              .access = PL1_RW, .accessfn = access_lor_other,
+              .type = ARM_CP_CONST, .resetvalue = 0 },
+            { .name = "LORN_EL1", .state = ARM_CP_STATE_AA64,
+              .opc0 = 3, .opc1 = 0, .crn = 10, .crm = 4, .opc2 = 2,
+              .access = PL1_RW, .accessfn = access_lor_other,
+              .type = ARM_CP_CONST, .resetvalue = 0 },
+            { .name = "LORC_EL1", .state = ARM_CP_STATE_AA64,
+              .opc0 = 3, .opc1 = 0, .crn = 10, .crm = 4, .opc2 = 3,
+              .access = PL1_RW, .accessfn = access_lor_other,
+              .type = ARM_CP_CONST, .resetvalue = 0 },
+            { .name = "LORID_EL1", .state = ARM_CP_STATE_AA64,
+              .opc0 = 3, .opc1 = 0, .crn = 10, .crm = 4, .opc2 = 7,
+              .access = PL1_R, .accessfn = access_lorid,
+              .type = ARM_CP_CONST, .resetvalue = 0 },
+            REGINFO_SENTINEL
+        };
+        define_arm_cp_regs(cpu, lor_reginfo);
+    }
+
     if (cpu_isar_feature(aa64_sve, cpu)) {
         define_one_arm_cp_reg(cpu, &zcr_el1_reginfo);
         if (arm_feature(env, ARM_FEATURE_EL2)) {
diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
index fd36425f1ae..e1da1e4d6f5 100644
--- a/target/arm/translate-a64.c
+++ b/target/arm/translate-a64.c
@@ -2290,6 +2290,12 @@ static void disas_ldst_excl(DisasContext *s, uint32_t 
insn)
         }
         return;
 
+    case 0x8: /* STLLR */
+        if (!dc_isar_feature(aa64_lor, s)) {
+            break;
+        }
+        /* StoreLORelease is the same as Store-Release for QEMU.  */
+        /* fall through */
     case 0x9: /* STLR */
         /* Generate ISS for non-exclusive accesses including LASR.  */
         if (rn == 31) {
@@ -2301,6 +2307,12 @@ static void disas_ldst_excl(DisasContext *s, uint32_t 
insn)
                   disas_ldst_compute_iss_sf(size, false, 0), is_lasr);
         return;
 
+    case 0xc: /* LDLAR */
+        if (!dc_isar_feature(aa64_lor, s)) {
+            break;
+        }
+        /* LoadLOAcquire is the same as Load-Acquire for QEMU.  */
+        /* fall through */
     case 0xd: /* LDAR */
         /* Generate ISS for non-exclusive accesses including LASR.  */
         if (rn == 31) {
-- 
2.19.2