Merge remote-tracking branch 'remotes/pmaydell/tags/pull-target-arm-20210308' into staging

target-arm queue:
 * sbsa-ref: remove cortex-a53 from list of supported cpus
 * sbsa-ref: add 'max' to list of allowed cpus
 * target/arm: Add support for FEAT_SSBS, Speculative Store Bypass Safe
 * npcm7xx: add EMC model
 * xlnx-zynqmp: Remove obsolete 'has_rpu' property
 * target/arm: Speed up aarch64 TBL/TBX
 * virtio-mmio: improve virtio-mmio get_dev_path alog
 * target/arm: Use TCF0 and TFSRE0 for unprivileged tag checks
 * target/arm: Restrict v8M IDAU to TCG
 * target/arm/cpu: Update coding style to make checkpatch.pl happy
 * musicpal, tc6393xb, omap_lcdc, tcx: drop dead code for non-32-bit-RGB surfaces
 * Add new board: mps3-an524

# gpg: Signature made Mon 08 Mar 2021 11:56:24 GMT
# gpg:                using RSA key E1A5C593CD419DE28E8315CF3C2525ED14360CDE
# gpg:                issuer "peter.maydell@linaro.org"
# gpg: Good signature from "Peter Maydell <peter.maydell@linaro.org>" [ultimate]
# gpg:                 aka "Peter Maydell <pmaydell@gmail.com>" [ultimate]
# gpg:                 aka "Peter Maydell <pmaydell@chiark.greenend.org.uk>" [ultimate]
# Primary key fingerprint: E1A5 C593 CD41 9DE2 8E83  15CF 3C25 25ED 1436 0CDE

* remotes/pmaydell/tags/pull-target-arm-20210308: (49 commits)
  hw/arm/mps2: Update old infocenter.arm.com URLs
  docs/system/arm/mps2.rst: Document the new mps3-an524 board
  hw/arm/mps2-tz: Provide PL031 RTC on mps3-an524
  hw/arm/mps2-tz: Stub out USB controller for mps3-an524
  hw/arm/mps2-tz: Add new mps3-an524 board
  hw/arm/mps2-tz: Get armv7m_load_kernel() size argument from RAMInfo
  hw/arm/mps2-tz: Support ROMs as well as RAMs
  hw/arm/mps2-tz: Set MachineClass default_ram info from RAMInfo data
  hw/arm/mps2-tz: Make RAM arrangement board-specific
  hw/arm/mps2-tz: Allow boards to have different PPCInfo data
  hw/arm/mps2-tz: Size the uart-irq-orgate based on the number of UARTs
  hw/arm/mps2-tz: Move device IRQ info to data structures
  hw/arm/mps2-tz: Allow PPCPortInfo structures to specify device interrupts
  hw/arm/mps2-tz: Correct wrong interrupt numbers for DMA and SPI
  hw/misc/mps2-scc: Implement CFG_REG5 and CFG_REG6 for MPS3 AN524
  hw/arm/mps2-tz: Make number of IRQs board-specific
  hw/arm/mps2-tz: Condition IRQ splitting on number of CPUs, not board type
  hw/arm/mps2-tz: Make FPGAIO switch and LED config per-board
  hw/misc/mps2-fpgaio: Support SWITCH register
  hw/misc/mps2-fpgaio: Make number of LEDs configurable by board
  ...

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

11 files changed, 160 insertions, 101 deletions

diff --git a/target/arm/cpu.c b/target/arm/cpu.c
index b8bc89e..6facb66 100644
--- a/target/arm/cpu.c
+++ b/target/arm/cpu.c
@@ -1972,7 +1972,8 @@ static void cortex_a8_initfn(Object *obj)
 }
 
 static const ARMCPRegInfo cortexa9_cp_reginfo[] = {
-    /* power_control should be set to maximum latency. Again,
+    /*
+     * power_control should be set to maximum latency. Again,
      * default to 0 and set by private hook
      */
     { .name = "A9_PWRCTL", .cp = 15, .crn = 15, .crm = 0, .opc1 = 0, .opc2 = 0,
@@ -2009,7 +2010,8 @@ static void cortex_a9_initfn(Object *obj)
     set_feature(&cpu->env, ARM_FEATURE_NEON);
     set_feature(&cpu->env, ARM_FEATURE_THUMB2EE);
     set_feature(&cpu->env, ARM_FEATURE_EL3);
-    /* Note that A9 supports the MP extensions even for
+    /*
+     * Note that A9 supports the MP extensions even for
      * A9UP and single-core A9MP (which are both different
      * and valid configurations; we don't model A9UP).
      */
@@ -2046,7 +2048,8 @@ static uint64_t a15_l2ctlr_read(CPUARMState *env, const ARMCPRegInfo *ri)
 {
     MachineState *ms = MACHINE(qdev_get_machine());
 
-    /* Linux wants the number of processors from here.
+    /*
+     * Linux wants the number of processors from here.
      * Might as well set the interrupt-controller bit too.
      */
     return ((ms->smp.cpus - 1) << 24) | (1 << 23);
@@ -2093,7 +2096,8 @@ static void cortex_a7_initfn(Object *obj)
     cpu->isar.id_mmfr1 = 0x40000000;
     cpu->isar.id_mmfr2 = 0x01240000;
     cpu->isar.id_mmfr3 = 0x02102211;
-    /* a7_mpcore_r0p5_trm, page 4-4 gives 0x01101110; but
+    /*
+     * a7_mpcore_r0p5_trm, page 4-4 gives 0x01101110; but
      * table 4-41 gives 0x02101110, which includes the arm div insns.
      */
     cpu->isar.id_isar0 = 0x02101110;
@@ -2217,6 +2221,10 @@ static void arm_max_initfn(Object *obj)
         t = cpu->isar.id_pfr0;
         t = FIELD_DP32(t, ID_PFR0, DIT, 1);
         cpu->isar.id_pfr0 = t;
+
+        t = cpu->isar.id_pfr2;
+        t = FIELD_DP32(t, ID_PFR2, SSBS, 1);
+        cpu->isar.id_pfr2 = t;
     }
 #endif
 }
@@ -2380,12 +2388,6 @@ static const TypeInfo arm_cpu_type_info = {
     .class_init = arm_cpu_class_init,
 };
 
-static const TypeInfo idau_interface_type_info = {
-    .name = TYPE_IDAU_INTERFACE,
-    .parent = TYPE_INTERFACE,
-    .class_size = sizeof(IDAUInterfaceClass),
-};
-
 static void arm_cpu_register_types(void)
 {
     const size_t cpu_count = ARRAY_SIZE(arm_cpus);
@@ -2399,7 +2401,6 @@ static void arm_cpu_register_types(void)
     if (cpu_count) {
         size_t i;
 
-        type_register_static(&idau_interface_type_info);
         for (i = 0; i < cpu_count; ++i) {
             arm_cpu_register(&arm_cpus[i]);
         }
diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index efa1618..193a49e 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -1206,6 +1206,7 @@ void pmu_init(ARMCPU *cpu);
 #define SCTLR_TE      (1U << 30) /* AArch32 only */
 #define SCTLR_EnIB    (1U << 30) /* v8.3, AArch64 only */
 #define SCTLR_EnIA    (1U << 31) /* v8.3, AArch64 only */
+#define SCTLR_DSSBS_32 (1U << 31) /* v8.5, AArch32 only */
 #define SCTLR_BT0     (1ULL << 35) /* v8.5-BTI */
 #define SCTLR_BT1     (1ULL << 36) /* v8.5-BTI */
 #define SCTLR_ITFSB   (1ULL << 37) /* v8.5-MemTag */
@@ -1213,7 +1214,7 @@ void pmu_init(ARMCPU *cpu);
 #define SCTLR_TCF     (3ULL << 40) /* v8.5-MemTag */
 #define SCTLR_ATA0    (1ULL << 42) /* v8.5-MemTag */
 #define SCTLR_ATA     (1ULL << 43) /* v8.5-MemTag */
-#define SCTLR_DSSBS   (1ULL << 44) /* v8.5 */
+#define SCTLR_DSSBS_64 (1ULL << 44) /* v8.5, AArch64 only */
 
 #define CPTR_TCPAC    (1U << 31)
 #define CPTR_TTA      (1U << 20)
@@ -1250,6 +1251,7 @@ void pmu_init(ARMCPU *cpu);
 #define CPSR_IL (1U << 20)
 #define CPSR_DIT (1U << 21)
 #define CPSR_PAN (1U << 22)
+#define CPSR_SSBS (1U << 23)
 #define CPSR_J (1U << 24)
 #define CPSR_IT_0_1 (3U << 25)
 #define CPSR_Q (1U << 27)
@@ -1312,6 +1314,7 @@ void pmu_init(ARMCPU *cpu);
 #define PSTATE_A (1U << 8)
 #define PSTATE_D (1U << 9)
 #define PSTATE_BTYPE (3U << 10)
+#define PSTATE_SSBS (1U << 12)
 #define PSTATE_IL (1U << 20)
 #define PSTATE_SS (1U << 21)
 #define PSTATE_PAN (1U << 22)
@@ -3915,6 +3918,11 @@ static inline bool isar_feature_aa32_dit(const ARMISARegisters *id)
     return FIELD_EX32(id->id_pfr0, ID_PFR0, DIT) != 0;
 }
 
+static inline bool isar_feature_aa32_ssbs(const ARMISARegisters *id)
+{
+    return FIELD_EX32(id->id_pfr2, ID_PFR2, SSBS) != 0;
+}
+
 /*
  * 64-bit feature tests via id registers.
  */
@@ -4169,6 +4177,11 @@ static inline bool isar_feature_aa64_dit(const ARMISARegisters *id)
     return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, DIT) != 0;
 }
 
+static inline bool isar_feature_aa64_ssbs(const ARMISARegisters *id)
+{
+    return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, SSBS) != 0;
+}
+
 /*
  * Feature tests for "does this exist in either 32-bit or 64-bit?"
  */
diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c
index c255f1b..f0a9e96 100644
--- a/target/arm/cpu64.c
+++ b/target/arm/cpu64.c
@@ -674,6 +674,7 @@ static void aarch64_max_initfn(Object *obj)
 
         t = cpu->isar.id_aa64pfr1;
         t = FIELD_DP64(t, ID_AA64PFR1, BT, 1);
+        t = FIELD_DP64(t, ID_AA64PFR1, SSBS, 2);
         /*
          * Begin with full support for MTE. This will be downgraded to MTE=0
          * during realize if the board provides no tag memory, much like
@@ -723,6 +724,10 @@ static void aarch64_max_initfn(Object *obj)
         u = FIELD_DP32(u, ID_PFR0, DIT, 1);
         cpu->isar.id_pfr0 = u;
 
+        u = cpu->isar.id_pfr2;
+        u = FIELD_DP32(u, ID_PFR2, SSBS, 1);
+        cpu->isar.id_pfr2 = u;
+
         u = cpu->isar.id_mmfr3;
         u = FIELD_DP32(u, ID_MMFR3, PAN, 2); /* ATS1E1 */
         cpu->isar.id_mmfr3 = u;
diff --git a/target/arm/cpu_tcg.c b/target/arm/cpu_tcg.c
index c29b434..fb07a33 100644
--- a/target/arm/cpu_tcg.c
+++ b/target/arm/cpu_tcg.c
@@ -14,6 +14,7 @@
 #include "hw/core/tcg-cpu-ops.h"
 #endif /* CONFIG_TCG */
 #include "internals.h"
+#include "target/arm/idau.h"
 
 /* CPU models. These are not needed for the AArch64 linux-user build. */
 #if !defined(CONFIG_USER_ONLY) || !defined(TARGET_AARCH64)
@@ -739,10 +740,17 @@ static const ARMCPUInfo arm_tcg_cpus[] = {
     { .name = "pxa270-c5",   .initfn = pxa270c5_initfn },
 };
 
+static const TypeInfo idau_interface_type_info = {
+    .name = TYPE_IDAU_INTERFACE,
+    .parent = TYPE_INTERFACE,
+    .class_size = sizeof(IDAUInterfaceClass),
+};
+
 static void arm_tcg_cpu_register_types(void)
 {
     size_t i;
 
+    type_register_static(&idau_interface_type_info);
     for (i = 0; i < ARRAY_SIZE(arm_tcg_cpus); ++i) {
         arm_cpu_register(&arm_tcg_cpus[i]);
     }
diff --git a/target/arm/helper-a64.c b/target/arm/helper-a64.c
index 7f56c78..061c8ff 100644
--- a/target/arm/helper-a64.c
+++ b/target/arm/helper-a64.c
@@ -179,38 +179,6 @@ float64 HELPER(vfp_mulxd)(float64 a, float64 b, void *fpstp)
     return float64_mul(a, b, fpst);
 }
 
-uint64_t HELPER(simd_tbl)(CPUARMState *env, uint64_t result, uint64_t indices,
-                          uint32_t rn, uint32_t numregs)
-{
-    /* Helper function for SIMD TBL and TBX. We have to do the table
-     * lookup part for the 64 bits worth of indices we're passed in.
-     * result is the initial results vector (either zeroes for TBL
-     * or some guest values for TBX), rn the register number where
-     * the table starts, and numregs the number of registers in the table.
-     * We return the results of the lookups.
-     */
-    int shift;
-
-    for (shift = 0; shift < 64; shift += 8) {
-        int index = extract64(indices, shift, 8);
-        if (index < 16 * numregs) {
-            /* Convert index (a byte offset into the virtual table
-             * which is a series of 128-bit vectors concatenated)
-             * into the correct register element plus a bit offset
-             * into that element, bearing in mind that the table
-             * can wrap around from V31 to V0.
-             */
-            int elt = (rn * 2 + (index >> 3)) % 64;
-            int bitidx = (index & 7) * 8;
-            uint64_t *q = aa64_vfp_qreg(env, elt >> 1);
-            uint64_t val = extract64(q[elt & 1], bitidx, 8);
-
-            result = deposit64(result, shift, 8, val);
-        }
-    }
-    return result;
-}
-
 /* 64bit/double versions of the neon float compare functions */
 uint64_t HELPER(neon_ceq_f64)(float64 a, float64 b, void *fpstp)
 {
diff --git a/target/arm/helper-a64.h b/target/arm/helper-a64.h
index 7bd6aed..c139fa8 100644
--- a/target/arm/helper-a64.h
+++ b/target/arm/helper-a64.h
@@ -28,7 +28,7 @@ DEF_HELPER_3(vfp_cmps_a64, i64, f32, f32, ptr)
 DEF_HELPER_3(vfp_cmpes_a64, i64, f32, f32, ptr)
 DEF_HELPER_3(vfp_cmpd_a64, i64, f64, f64, ptr)
 DEF_HELPER_3(vfp_cmped_a64, i64, f64, f64, ptr)
-DEF_HELPER_FLAGS_5(simd_tbl, TCG_CALL_NO_RWG_SE, i64, env, i64, i64, i32, i32)
+DEF_HELPER_FLAGS_4(simd_tblx, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_3(vfp_mulxs, TCG_CALL_NO_RWG, f32, f32, f32, ptr)
 DEF_HELPER_FLAGS_3(vfp_mulxd, TCG_CALL_NO_RWG, f64, f64, f64, ptr)
 DEF_HELPER_FLAGS_3(neon_ceq_f64, TCG_CALL_NO_RWG, i64, i64, i64, ptr)
diff --git a/target/arm/helper.c b/target/arm/helper.c
index 0e1a3b9..904b092 100644
--- a/target/arm/helper.c
+++ b/target/arm/helper.c
@@ -4450,6 +4450,24 @@ static const ARMCPRegInfo dit_reginfo = {
     .readfn = aa64_dit_read, .writefn = aa64_dit_write
 };
 
+static uint64_t aa64_ssbs_read(CPUARMState *env, const ARMCPRegInfo *ri)
+{
+    return env->pstate & PSTATE_SSBS;
+}
+
+static void aa64_ssbs_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                           uint64_t value)
+{
+    env->pstate = (env->pstate & ~PSTATE_SSBS) | (value & PSTATE_SSBS);
+}
+
+static const ARMCPRegInfo ssbs_reginfo = {
+    .name = "SSBS", .state = ARM_CP_STATE_AA64,
+    .opc0 = 3, .opc1 = 3, .crn = 4, .crm = 2, .opc2 = 6,
+    .type = ARM_CP_NO_RAW, .access = PL0_RW,
+    .readfn = aa64_ssbs_read, .writefn = aa64_ssbs_write
+};
+
 static CPAccessResult aa64_cacheop_poc_access(CPUARMState *env,
                                               const ARMCPRegInfo *ri,
                                               bool isread)
@@ -8244,6 +8262,9 @@ void register_cp_regs_for_features(ARMCPU *cpu)
     if (cpu_isar_feature(aa64_dit, cpu)) {
         define_one_arm_cp_reg(cpu, &dit_reginfo);
     }
+    if (cpu_isar_feature(aa64_ssbs, cpu)) {
+        define_one_arm_cp_reg(cpu, &ssbs_reginfo);
+    }
 
     if (arm_feature(env, ARM_FEATURE_EL2) && cpu_isar_feature(aa64_vh, cpu)) {
         define_arm_cp_regs(cpu, vhe_reginfo);
@@ -9463,6 +9484,14 @@ static void take_aarch32_exception(CPUARMState *env, int new_mode,
     env->uncached_cpsr &= ~(CPSR_IL | CPSR_J);
     env->daif |= mask;
 
+    if (cpu_isar_feature(aa32_ssbs, env_archcpu(env))) {
+        if (env->cp15.sctlr_el[new_el] & SCTLR_DSSBS_32) {
+            env->uncached_cpsr |= CPSR_SSBS;
+        } else {
+            env->uncached_cpsr &= ~CPSR_SSBS;
+        }
+    }
+
     if (new_mode == ARM_CPU_MODE_HYP) {
         env->thumb = (env->cp15.sctlr_el[2] & SCTLR_TE) != 0;
         env->elr_el[2] = env->regs[15];
@@ -9973,6 +10002,14 @@ static void arm_cpu_do_interrupt_aarch64(CPUState *cs)
         new_mode |= PSTATE_TCO;
     }
 
+    if (cpu_isar_feature(aa64_ssbs, cpu)) {
+        if (env->cp15.sctlr_el[new_el] & SCTLR_DSSBS_64) {
+            new_mode |= PSTATE_SSBS;
+        } else {
+            new_mode &= ~PSTATE_SSBS;
+        }
+    }
+
     pstate_write(env, PSTATE_DAIF | new_mode);
     env->aarch64 = 1;
     aarch64_restore_sp(env, new_el);
@@ -13133,7 +13170,7 @@ static uint32_t rebuild_hflags_a64(CPUARMState *env, int el, int fp_el,
         if (FIELD_EX32(flags, TBFLAG_A64, UNPRIV)
             && tbid
             && !(env->pstate & PSTATE_TCO)
-            && (sctlr & SCTLR_TCF)
+            && (sctlr & SCTLR_TCF0)
             && allocation_tag_access_enabled(env, 0, sctlr)) {
             flags = FIELD_DP32(flags, TBFLAG_A64, MTE0_ACTIVE, 1);
         }
diff --git a/target/arm/internals.h b/target/arm/internals.h
index 05cebc8..f11bd32 100644
--- a/target/arm/internals.h
+++ b/target/arm/internals.h
@@ -987,6 +987,9 @@ static inline uint32_t aarch32_cpsr_valid_mask(uint64_t features,
     if (isar_feature_aa32_dit(id)) {
         valid |= CPSR_DIT;
     }
+    if (isar_feature_aa32_ssbs(id)) {
+        valid |= CPSR_SSBS;
+    }
 
     return valid;
 }
@@ -1008,6 +1011,9 @@ static inline uint32_t aarch64_pstate_valid_mask(const ARMISARegisters *id)
     if (isar_feature_aa64_dit(id)) {
         valid |= PSTATE_DIT;
     }
+    if (isar_feature_aa64_ssbs(id)) {
+        valid |= PSTATE_SSBS;
+    }
     if (isar_feature_aa64_mte(id)) {
         valid |= PSTATE_TCO;
     }
diff --git a/target/arm/mte_helper.c b/target/arm/mte_helper.c
index 1c56933..0bbb9ec 100644
--- a/target/arm/mte_helper.c
+++ b/target/arm/mte_helper.c
@@ -550,10 +550,14 @@ static void mte_check_fail(CPUARMState *env, uint32_t desc,
     reg_el = regime_el(env, arm_mmu_idx);
     sctlr = env->cp15.sctlr_el[reg_el];
 
-    el = arm_current_el(env);
-    if (el == 0) {
+    switch (arm_mmu_idx) {
+    case ARMMMUIdx_E10_0:
+    case ARMMMUIdx_E20_0:
+        el = 0;
         tcf = extract64(sctlr, 38, 2);
-    } else {
+        break;
+    default:
+        el = reg_el;
         tcf = extract64(sctlr, 40, 2);
     }
 
@@ -570,7 +574,8 @@ static void mte_check_fail(CPUARMState *env, uint32_t desc,
         env->exception.vaddress = dirty_ptr;
 
         is_write = FIELD_EX32(desc, MTEDESC, WRITE);
-        syn = syn_data_abort_no_iss(el != 0, 0, 0, 0, 0, is_write, 0x11);
+        syn = syn_data_abort_no_iss(arm_current_el(env) != 0, 0, 0, 0, 0,
+                                    is_write, 0x11);
         raise_exception(env, EXCP_DATA_ABORT, syn, exception_target_el(env));
         /* noreturn, but fall through to the assert anyway */
 
diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
index b23a897..b591f09 100644
--- a/target/arm/translate-a64.c
+++ b/target/arm/translate-a64.c
@@ -1703,6 +1703,18 @@ static void handle_msr_i(DisasContext *s, uint32_t insn,
         tcg_temp_free_i32(t1);
         break;
 
+    case 0x19: /* SSBS */
+        if (!dc_isar_feature(aa64_ssbs, s)) {
+            goto do_unallocated;
+        }
+        if (crm & 1) {
+            set_pstate_bits(PSTATE_SSBS);
+        } else {
+            clear_pstate_bits(PSTATE_SSBS);
+        }
+        /* Don't need to rebuild hflags since SSBS is a nop */
+        break;
+
     case 0x1a: /* DIT */
         if (!dc_isar_feature(aa64_dit, s)) {
             goto do_unallocated;
@@ -7520,10 +7532,8 @@ static void disas_simd_tb(DisasContext *s, uint32_t insn)
     int rm = extract32(insn, 16, 5);
     int rn = extract32(insn, 5, 5);
     int rd = extract32(insn, 0, 5);
-    int is_tblx = extract32(insn, 12, 1);
-    int len = extract32(insn, 13, 2);
-    TCGv_i64 tcg_resl, tcg_resh, tcg_idx;
-    TCGv_i32 tcg_regno, tcg_numregs;
+    int is_tbx = extract32(insn, 12, 1);
+    int len = (extract32(insn, 13, 2) + 1) * 16;
 
     if (op2 != 0) {
         unallocated_encoding(s);
@@ -7534,53 +7544,11 @@ static void disas_simd_tb(DisasContext *s, uint32_t insn)
         return;
     }
 
-    /* This does a table lookup: for every byte element in the input
-     * we index into a table formed from up to four vector registers,
-     * and then the output is the result of the lookups. Our helper
-     * function does the lookup operation for a single 64 bit part of
-     * the input.
-     */
-    tcg_resl = tcg_temp_new_i64();
-    tcg_resh = NULL;
-
-    if (is_tblx) {
-        read_vec_element(s, tcg_resl, rd, 0, MO_64);
-    } else {
-        tcg_gen_movi_i64(tcg_resl, 0);
-    }
-
-    if (is_q) {
-        tcg_resh = tcg_temp_new_i64();
-        if (is_tblx) {
-            read_vec_element(s, tcg_resh, rd, 1, MO_64);
-        } else {
-            tcg_gen_movi_i64(tcg_resh, 0);
-        }
-    }
-
-    tcg_idx = tcg_temp_new_i64();
-    tcg_regno = tcg_const_i32(rn);
-    tcg_numregs = tcg_const_i32(len + 1);
-    read_vec_element(s, tcg_idx, rm, 0, MO_64);
-    gen_helper_simd_tbl(tcg_resl, cpu_env, tcg_resl, tcg_idx,
-                        tcg_regno, tcg_numregs);
-    if (is_q) {
-        read_vec_element(s, tcg_idx, rm, 1, MO_64);
-        gen_helper_simd_tbl(tcg_resh, cpu_env, tcg_resh, tcg_idx,
-                            tcg_regno, tcg_numregs);
-    }
-    tcg_temp_free_i64(tcg_idx);
-    tcg_temp_free_i32(tcg_regno);
-    tcg_temp_free_i32(tcg_numregs);
-
-    write_vec_element(s, tcg_resl, rd, 0, MO_64);
-    tcg_temp_free_i64(tcg_resl);
-
-    if (is_q) {
-        write_vec_element(s, tcg_resh, rd, 1, MO_64);
-        tcg_temp_free_i64(tcg_resh);
-    }
-    clear_vec_high(s, is_q, rd);
+    tcg_gen_gvec_2_ptr(vec_full_reg_offset(s, rd),
+                       vec_full_reg_offset(s, rm), cpu_env,
+                       is_q ? 16 : 8, vec_full_reg_size(s),
+                       (len << 6) | (is_tbx << 5) | rn,
+                       gen_helper_simd_tblx);
 }
 
 /* ZIP/UZP/TRN
diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c
index 7174030..3fbeae8 100644
--- a/target/arm/vec_helper.c
+++ b/target/arm/vec_helper.c
@@ -1937,3 +1937,51 @@ DO_VRINT_RMODE(gvec_vrint_rm_h, helper_rinth, uint16_t)
 DO_VRINT_RMODE(gvec_vrint_rm_s, helper_rints, uint32_t)
 
 #undef DO_VRINT_RMODE
+
+#ifdef TARGET_AARCH64
+void HELPER(simd_tblx)(void *vd, void *vm, void *venv, uint32_t desc)
+{
+    const uint8_t *indices = vm;
+    CPUARMState *env = venv;
+    size_t oprsz = simd_oprsz(desc);
+    uint32_t rn = extract32(desc, SIMD_DATA_SHIFT, 5);
+    bool is_tbx = extract32(desc, SIMD_DATA_SHIFT + 5, 1);
+    uint32_t table_len = desc >> (SIMD_DATA_SHIFT + 6);
+    union {
+        uint8_t b[16];
+        uint64_t d[2];
+    } result;
+
+    /*
+     * We must construct the final result in a temp, lest the output
+     * overlaps the input table.  For TBL, begin with zero; for TBX,
+     * begin with the original register contents.  Note that we always
+     * copy 16 bytes here to avoid an extra branch; clearing the high
+     * bits of the register for oprsz == 8 is handled below.
+     */
+    if (is_tbx) {
+        memcpy(&result, vd, 16);
+    } else {
+        memset(&result, 0, 16);
+    }
+
+    for (size_t i = 0; i < oprsz; ++i) {
+        uint32_t index = indices[H1(i)];
+
+        if (index < table_len) {
+            /*
+             * Convert index (a byte offset into the virtual table
+             * which is a series of 128-bit vectors concatenated)
+             * into the correct register element, bearing in mind
+             * that the table can wrap around from V31 to V0.
+             */
+            const uint8_t *table = (const uint8_t *)
+                aa64_vfp_qreg(env, (rn + (index >> 4)) % 32);
+            result.b[H1(i)] = table[H1(index % 16)];
+        }
+    }
+
+    memcpy(vd, &result, 16);
+    clear_tail(vd, oprsz, simd_maxsz(desc));
+}
+#endif