Merge tag 'pull-target-arm-20250307' of https://git.linaro.org/people/pmaydell/qemu-arm into staging

target-arm queue:
 * hw/arm/smmu-common: Remove the repeated ttb field
 * hw/gpio: npcm7xx: fixup out-of-bounds access
 * tests/functional/test_arm_sx1: Check whether the serial console is working
 * target/arm: Fix minor bugs in generic timer register handling
 * target/arm: Implement SEL2 physical and virtual timers
 * target/arm: Correct STRD, LDRD atomicity and fault behaviour
 * target/arm: Make dummy debug registers RAZ, not NOP
 * util/qemu-timer.c: Don't warp timer from timerlist_rearm()
 * include/exec/memop.h: Expand comment for MO_ATOM_SUBALIGN
 * hw/arm/smmu: Introduce smmu_configs_inv_sid_range() helper
 * target/rx: Set exception vector base to 0xffffff80
 * target/rx: Remove TCG_CALL_NO_WG from helpers which write env

# -----BEGIN PGP SIGNATURE-----
#
# iQJNBAABCAA3FiEE4aXFk81BneKOgxXPPCUl7RQ2DN4FAmfLCzgZHHBldGVyLm1h
# eWRlbGxAbGluYXJvLm9yZwAKCRA8JSXtFDYM3pwVEACgJJm1zdtRd87AnA0eY29a
# uG8M35+VS/bNbA6IXzz1hFHUFh1smrda0C7VOefRqThEhkDObh1gfKWK3YeBenDn
# FQsI6Hwu23ozTCgOniheU8SGbTtIvVxRRX4S91xNZgJ15riEATDnTisZv8iUChdr
# DcZopuH0uRiOq7TWuRjxqvhaqH6WusvHzK0mizTqr9UhbqPHVl7CZfr1/AtJLpZF
# 32ix0JMofFWS52LFI19KWPlQG5Z3+lOw2ASyTf4cCaoCG6FTMv22E1x8mbMc2i96
# WrsB+NdhlBVRu7mskOP2Br09AbQZ/Fy7AGlDhgZebipOUVMlpDj1RXj/BDH3H/px
# qsjOk3V3gzM2bD+KvJuO4FlGXgEbOzGsGBwwY152C/6DYW5uTha/H1Pp+/iR8kcS
# HvAsqNLh/uF7O1Kn8qzCNvglKDC3z0C4X15Sj8SjGz8Xtn1Ign/GVkDv8ZCoR39K
# ltnXwvhzlDMkcGFFfEn33MYZZYqB15nX5a78/cStB/aOGPtZwUJ+2udLDzmug5ve
# 9oY9WMqqBDVxo4+qcAeZ+aem2VD6w79mhJyy1xmqOkifhFWqQ2VbDrKtqnrqhPK/
# neyWrd2zCF6fY1wvb7vVKMy7aC5jI2K6qVU7ueZGCGKU2MtvbVaFJFByOjnVjv6o
# c65VNXkbaCIedrSlalMO4w==
# =8typ
# -----END PGP SIGNATURE-----
# gpg: Signature made Fri 07 Mar 2025 23:05:28 HKT
# gpg:                using RSA key E1A5C593CD419DE28E8315CF3C2525ED14360CDE
# gpg:                issuer "peter.maydell@linaro.org"
# gpg: Good signature from "Peter Maydell <peter.maydell@linaro.org>" [full]
# gpg:                 aka "Peter Maydell <pmaydell@gmail.com>" [full]
# gpg:                 aka "Peter Maydell <pmaydell@chiark.greenend.org.uk>" [full]
# gpg:                 aka "Peter Maydell <peter@archaic.org.uk>" [unknown]
# Primary key fingerprint: E1A5 C593 CD41 9DE2 8E83  15CF 3C25 25ED 1436 0CDE

* tag 'pull-target-arm-20250307' of https://git.linaro.org/people/pmaydell/qemu-arm: (21 commits)
  target/rx: Remove TCG_CALL_NO_WG from helpers which write env
  target/rx: Set exception vector base to 0xffffff80
  hw/arm/smmu: Introduce smmu_configs_inv_sid_range() helper
  include/exec/memop.h: Expand comment for MO_ATOM_SUBALIGN
  util/qemu-timer.c: Don't warp timer from timerlist_rearm()
  target/arm: Make dummy debug registers RAZ, not NOP
  target/arm: Drop unused address_offset from op_addr_{rr, ri}_post()
  target/arm: Correct STRD atomicity
  target/arm: Correct LDRD atomicity and fault behaviour
  hw/arm: enable secure EL2 timers for sbsa machine
  hw/arm: enable secure EL2 timers for virt machine
  target/arm: Document the architectural names of our GTIMERs
  target/arm: Implement SEL2 physical and virtual timers
  target/arm: Refactor handling of timer offset for direct register accesses
  target/arm: Always apply CNTVOFF_EL2 for CNTV_TVAL_EL02 accesses
  target/arm: Make CNTPS_* UNDEF from Secure EL1 when Secure EL2 is enabled
  target/arm: Don't apply CNTVOFF_EL2 for EL2_VIRT timer
  target/arm: Apply correct timer offset when calculating deadlines
  tests/functional/test_arm_sx1: Check whether the serial console is working
  hw/gpio: npcm7xx: fixup out-of-bounds access
  ...

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

23 files changed, 455 insertions, 176 deletions

diff --git a/MAINTAINERS b/MAINTAINERS
index 77fab92..7ac04f3 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2010,6 +2010,7 @@ S: Maintained
 F: hw/*/omap*
 F: include/hw/arm/omap.h
 F: docs/system/arm/sx1.rst
+F: tests/functional/test_arm_sx1.py
 
 IPack
 M: Alberto Garcia <berto@igalia.com>
diff --git a/hw/arm/sbsa-ref.c b/hw/arm/sbsa-ref.c
index e720de3..aa09d7a 100644
--- a/hw/arm/sbsa-ref.c
+++ b/hw/arm/sbsa-ref.c
@@ -484,6 +484,8 @@ static void create_gic(SBSAMachineState *sms, MemoryRegion *mem)
             [GTIMER_HYP]  = ARCH_TIMER_NS_EL2_IRQ,
             [GTIMER_SEC]  = ARCH_TIMER_S_EL1_IRQ,
             [GTIMER_HYPVIRT] = ARCH_TIMER_NS_EL2_VIRT_IRQ,
+            [GTIMER_S_EL2_PHYS] = ARCH_TIMER_S_EL2_IRQ,
+            [GTIMER_S_EL2_VIRT] = ARCH_TIMER_S_EL2_VIRT_IRQ,
         };
 
         for (irq = 0; irq < ARRAY_SIZE(timer_irq); irq++) {
diff --git a/hw/arm/smmu-common.c b/hw/arm/smmu-common.c
index 8c1b407..6e720e1 100644
--- a/hw/arm/smmu-common.c
+++ b/hw/arm/smmu-common.c
@@ -225,6 +225,27 @@ static gboolean smmu_hash_remove_by_vmid_ipa(gpointer key, gpointer value,
            ((entry->iova & ~info->mask) == info->iova);
 }
 
+static gboolean
+smmu_hash_remove_by_sid_range(gpointer key, gpointer value, gpointer user_data)
+{
+    SMMUDevice *sdev = (SMMUDevice *)key;
+    uint32_t sid = smmu_get_sid(sdev);
+    SMMUSIDRange *sid_range = (SMMUSIDRange *)user_data;
+
+    if (sid < sid_range->start || sid > sid_range->end) {
+        return false;
+    }
+    trace_smmu_config_cache_inv(sid);
+    return true;
+}
+
+void smmu_configs_inv_sid_range(SMMUState *s, SMMUSIDRange sid_range)
+{
+    trace_smmu_configs_inv_sid_range(sid_range.start, sid_range.end);
+    g_hash_table_foreach_remove(s->configs, smmu_hash_remove_by_sid_range,
+                                &sid_range);
+}
+
 void smmu_iotlb_inv_iova(SMMUState *s, int asid, int vmid, dma_addr_t iova,
                          uint8_t tg, uint64_t num_pages, uint8_t ttl)
 {
diff --git a/hw/arm/smmu-internal.h b/hw/arm/smmu-internal.h
index 843bebb..d143d29 100644
--- a/hw/arm/smmu-internal.h
+++ b/hw/arm/smmu-internal.h
@@ -141,9 +141,4 @@ typedef struct SMMUIOTLBPageInvInfo {
     uint64_t mask;
 } SMMUIOTLBPageInvInfo;
 
-typedef struct SMMUSIDRange {
-    uint32_t start;
-    uint32_t end;
-} SMMUSIDRange;
-
 #endif
diff --git a/hw/arm/smmuv3.c b/hw/arm/smmuv3.c
index b40acbe..1a96287 100644
--- a/hw/arm/smmuv3.c
+++ b/hw/arm/smmuv3.c
@@ -903,7 +903,7 @@ static void smmuv3_flush_config(SMMUDevice *sdev)
     SMMUv3State *s = sdev->smmu;
     SMMUState *bc = &s->smmu_state;
 
-    trace_smmuv3_config_cache_inv(smmu_get_sid(sdev));
+    trace_smmu_config_cache_inv(smmu_get_sid(sdev));
     g_hash_table_remove(bc->configs, sdev);
 }
 
@@ -1277,20 +1277,6 @@ static void smmuv3_range_inval(SMMUState *s, Cmd *cmd, SMMUStage stage)
     }
 }
 
-static gboolean
-smmuv3_invalidate_ste(gpointer key, gpointer value, gpointer user_data)
-{
-    SMMUDevice *sdev = (SMMUDevice *)key;
-    uint32_t sid = smmu_get_sid(sdev);
-    SMMUSIDRange *sid_range = (SMMUSIDRange *)user_data;
-
-    if (sid < sid_range->start || sid > sid_range->end) {
-        return false;
-    }
-    trace_smmuv3_config_cache_inv(sid);
-    return true;
-}
-
 static int smmuv3_cmdq_consume(SMMUv3State *s)
 {
     SMMUState *bs = ARM_SMMU(s);
@@ -1373,8 +1359,7 @@ static int smmuv3_cmdq_consume(SMMUv3State *s)
             sid_range.end = sid_range.start + mask;
 
             trace_smmuv3_cmdq_cfgi_ste_range(sid_range.start, sid_range.end);
-            g_hash_table_foreach_remove(bs->configs, smmuv3_invalidate_ste,
-                                        &sid_range);
+            smmu_configs_inv_sid_range(bs, sid_range);
             break;
         }
         case SMMU_CMD_CFGI_CD:
diff --git a/hw/arm/trace-events b/hw/arm/trace-events
index f49cae1..f3386bd 100644
--- a/hw/arm/trace-events
+++ b/hw/arm/trace-events
@@ -22,6 +22,8 @@ smmu_iotlb_inv_asid_vmid(int asid, int vmid) "IOTLB invalidate asid=%d vmid=%d"
 smmu_iotlb_inv_vmid(int vmid) "IOTLB invalidate vmid=%d"
 smmu_iotlb_inv_vmid_s1(int vmid) "IOTLB invalidate vmid=%d"
 smmu_iotlb_inv_iova(int asid, uint64_t addr) "IOTLB invalidate asid=%d addr=0x%"PRIx64
+smmu_configs_inv_sid_range(uint32_t start, uint32_t end) "Config cache INV SID range from 0x%x to 0x%x"
+smmu_config_cache_inv(uint32_t sid) "Config cache INV for sid=0x%x"
 smmu_inv_notifiers_mr(const char *name) "iommu mr=%s"
 smmu_iotlb_lookup_hit(int asid, int vmid, uint64_t addr, uint32_t hit, uint32_t miss, uint32_t p) "IOTLB cache HIT asid=%d vmid=%d addr=0x%"PRIx64" hit=%d miss=%d hit rate=%d"
 smmu_iotlb_lookup_miss(int asid, int vmid, uint64_t addr, uint32_t hit, uint32_t miss, uint32_t p) "IOTLB cache MISS asid=%d vmid=%d addr=0x%"PRIx64" hit=%d miss=%d hit rate=%d"
@@ -59,7 +61,6 @@ smmuv3_cmdq_tlbi_nh(int vmid) "vmid=%d"
 smmuv3_cmdq_tlbi_nsnh(void) ""
 smmuv3_cmdq_tlbi_nh_asid(int asid) "asid=%d"
 smmuv3_cmdq_tlbi_s12_vmid(int vmid) "vmid=%d"
-smmuv3_config_cache_inv(uint32_t sid) "Config cache INV for sid=0x%x"
 smmuv3_notify_flag_add(const char *iommu) "ADD SMMUNotifier node for iommu mr=%s"
 smmuv3_notify_flag_del(const char *iommu) "DEL SMMUNotifier node for iommu mr=%s"
 smmuv3_inv_notifiers_iova(const char *name, int asid, int vmid, uint64_t iova, uint8_t tg, uint64_t num_pages, int stage) "iommu mr=%s asid=%d vmid=%d iova=0x%"PRIx64" tg=%d num_pages=0x%"PRIx64" stage=%d"
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index 904c698..a96452f 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -882,6 +882,8 @@ static void create_gic(VirtMachineState *vms, MemoryRegion *mem)
             [GTIMER_HYP]  = ARCH_TIMER_NS_EL2_IRQ,
             [GTIMER_SEC]  = ARCH_TIMER_S_EL1_IRQ,
             [GTIMER_HYPVIRT] = ARCH_TIMER_NS_EL2_VIRT_IRQ,
+            [GTIMER_S_EL2_PHYS] = ARCH_TIMER_S_EL2_IRQ,
+            [GTIMER_S_EL2_VIRT] = ARCH_TIMER_S_EL2_VIRT_IRQ,
         };
 
         for (unsigned irq = 0; irq < ARRAY_SIZE(timer_irq); irq++) {
diff --git a/hw/gpio/npcm7xx_gpio.c b/hw/gpio/npcm7xx_gpio.c
index 23e6742..2916056 100644
--- a/hw/gpio/npcm7xx_gpio.c
+++ b/hw/gpio/npcm7xx_gpio.c
@@ -220,8 +220,6 @@ static void npcm7xx_gpio_regs_write(void *opaque, hwaddr addr, uint64_t v,
         return;
     }
 
-    diff = s->regs[reg] ^ value;
-
     switch (reg) {
     case NPCM7XX_GPIO_TLOCK1:
     case NPCM7XX_GPIO_TLOCK2:
@@ -242,6 +240,7 @@ static void npcm7xx_gpio_regs_write(void *opaque, hwaddr addr, uint64_t v,
     case NPCM7XX_GPIO_PU:
     case NPCM7XX_GPIO_PD:
     case NPCM7XX_GPIO_IEM:
+        diff = s->regs[reg] ^ value;
         s->regs[reg] = value;
         npcm7xx_gpio_update_pins(s, diff);
         break;
diff --git a/include/exec/memop.h b/include/exec/memop.h
index acdb40a..407a47d 100644
--- a/include/exec/memop.h
+++ b/include/exec/memop.h
@@ -91,8 +91,12 @@ typedef enum MemOp {
      *    Depending on alignment, one or both will be single-copy atomic.
      *    This is the atomicity e.g. of Arm FEAT_LSE2 LDP.
      * MO_ATOM_SUBALIGN: the operation is single-copy atomic by parts
-     *    by the alignment.  E.g. if the address is 0 mod 4, then each
-     *    4-byte subobject is single-copy atomic.
+     *    by the alignment.  E.g. if an 8-byte value is accessed at an
+     *    address which is 0 mod 8, then the whole 8-byte access is
+     *    single-copy atomic; otherwise, if it is accessed at 0 mod 4
+     *    then each 4-byte subobject is single-copy atomic; otherwise
+     *    if it is accessed at 0 mod 2 then the four 2-byte subobjects
+     *    are single-copy atomic.
      *    This is the atomicity e.g. of IBM Power.
      * MO_ATOM_NONE: the operation has no atomicity requirements.
      *
diff --git a/include/hw/arm/bsa.h b/include/hw/arm/bsa.h
index 8eaab60..13ed2d2 100644
--- a/include/hw/arm/bsa.h
+++ b/include/hw/arm/bsa.h
@@ -22,6 +22,8 @@
 #define QEMU_ARM_BSA_H
 
 /* These are architectural INTID values */
+#define ARCH_TIMER_S_EL2_VIRT_IRQ  19
+#define ARCH_TIMER_S_EL2_IRQ       20
 #define VIRTUAL_PMU_IRQ            23
 #define ARCH_GIC_MAINT_IRQ         25
 #define ARCH_TIMER_NS_EL2_IRQ      26
diff --git a/include/hw/arm/smmu-common.h b/include/hw/arm/smmu-common.h
index d1a4a64..e5e2d09 100644
--- a/include/hw/arm/smmu-common.h
+++ b/include/hw/arm/smmu-common.h
@@ -110,7 +110,6 @@ typedef struct SMMUTransCfg {
     /* Used by stage-1 only. */
     bool aa64;                 /* arch64 or aarch32 translation table */
     bool record_faults;        /* record fault events */
-    uint64_t ttb;              /* TT base address */
     uint8_t oas;               /* output address width */
     uint8_t tbi;               /* Top Byte Ignore */
     int asid;
@@ -143,6 +142,11 @@ typedef struct SMMUIOTLBKey {
     uint8_t level;
 } SMMUIOTLBKey;
 
+typedef struct SMMUSIDRange {
+    uint32_t start;
+    uint32_t end;
+} SMMUSIDRange;
+
 struct SMMUState {
     /* <private> */
     SysBusDevice  dev;
@@ -220,6 +224,7 @@ void smmu_iotlb_inv_iova(SMMUState *s, int asid, int vmid, dma_addr_t iova,
                          uint8_t tg, uint64_t num_pages, uint8_t ttl);
 void smmu_iotlb_inv_ipa(SMMUState *s, int vmid, dma_addr_t ipa, uint8_t tg,
                         uint64_t num_pages, uint8_t ttl);
+void smmu_configs_inv_sid_range(SMMUState *s, SMMUSIDRange sid_range);
 /* Unmap the range of all the notifiers registered to any IOMMU mr */
 void smmu_inv_notifiers_all(SMMUState *s);
 
diff --git a/target/arm/cpu.c b/target/arm/cpu.c
index 948defa..cacbbc6 100644
--- a/target/arm/cpu.c
+++ b/target/arm/cpu.c
@@ -2069,6 +2069,10 @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp)
                                               arm_gt_stimer_cb, cpu);
         cpu->gt_timer[GTIMER_HYPVIRT] = timer_new(QEMU_CLOCK_VIRTUAL, scale,
                                                   arm_gt_hvtimer_cb, cpu);
+        cpu->gt_timer[GTIMER_S_EL2_PHYS] = timer_new(QEMU_CLOCK_VIRTUAL, scale,
+                                                     arm_gt_sel2timer_cb, cpu);
+        cpu->gt_timer[GTIMER_S_EL2_VIRT] = timer_new(QEMU_CLOCK_VIRTUAL, scale,
+                                                     arm_gt_sel2vtimer_cb, cpu);
     }
 #endif
 
diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index 215845c..8f52380 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -1171,6 +1171,8 @@ void arm_gt_vtimer_cb(void *opaque);
 void arm_gt_htimer_cb(void *opaque);
 void arm_gt_stimer_cb(void *opaque);
 void arm_gt_hvtimer_cb(void *opaque);
+void arm_gt_sel2timer_cb(void *opaque);
+void arm_gt_sel2vtimer_cb(void *opaque);
 
 unsigned int gt_cntfrq_period_ns(ARMCPU *cpu);
 void gt_rme_post_el_change(ARMCPU *cpu, void *opaque);
diff --git a/target/arm/debug_helper.c b/target/arm/debug_helper.c
index 36bffde..a9a619b 100644
--- a/target/arm/debug_helper.c
+++ b/target/arm/debug_helper.c
@@ -1037,7 +1037,7 @@ static const ARMCPRegInfo debug_cp_reginfo[] = {
     { .name = "DBGVCR",
       .cp = 14, .opc1 = 0, .crn = 0, .crm = 7, .opc2 = 0,
       .access = PL1_RW, .accessfn = access_tda,
-      .type = ARM_CP_NOP },
+      .type = ARM_CP_CONST, .resetvalue = 0 },
     /*
      * Dummy MDCCINT_EL1, since we don't implement the Debug Communications
      * Channel but Linux may try to access this register. The 32-bit
@@ -1046,7 +1046,7 @@ static const ARMCPRegInfo debug_cp_reginfo[] = {
     { .name = "MDCCINT_EL1", .state = ARM_CP_STATE_BOTH,
       .cp = 14, .opc0 = 2, .opc1 = 0, .crn = 0, .crm = 2, .opc2 = 0,
       .access = PL1_RW, .accessfn = access_tdcc,
-      .type = ARM_CP_NOP },
+      .type = ARM_CP_CONST, .resetvalue = 0 },
     /*
      * Dummy DBGCLAIM registers.
      * "The architecture does not define any functionality for the CLAIM tag bits.",
@@ -1075,7 +1075,8 @@ static const ARMCPRegInfo debug_aa32_el1_reginfo[] = {
     { .name = "DBGVCR32_EL2", .state = ARM_CP_STATE_AA64,
       .opc0 = 2, .opc1 = 4, .crn = 0, .crm = 7, .opc2 = 0,
       .access = PL2_RW, .accessfn = access_dbgvcr32,
-      .type = ARM_CP_NOP | ARM_CP_EL3_NO_EL2_KEEP },
+      .type = ARM_CP_CONST | ARM_CP_EL3_NO_EL2_KEEP,
+      .resetvalue = 0 },
 };
 
 static const ARMCPRegInfo debug_lpae_cp_reginfo[] = {
diff --git a/target/arm/gtimer.h b/target/arm/gtimer.h
index b992941..d49c63c 100644
--- a/target/arm/gtimer.h
+++ b/target/arm/gtimer.h
@@ -10,12 +10,14 @@
 #define TARGET_ARM_GTIMER_H
 
 enum {
-    GTIMER_PHYS     = 0,
-    GTIMER_VIRT     = 1,
-    GTIMER_HYP      = 2,
-    GTIMER_SEC      = 3,
-    GTIMER_HYPVIRT  = 4,
-#define NUM_GTIMERS   5
+    GTIMER_PHYS     = 0, /* CNTP_* ; EL1 physical timer */
+    GTIMER_VIRT     = 1, /* CNTV_* ; EL1 virtual timer */
+    GTIMER_HYP      = 2, /* CNTHP_* ; EL2 physical timer */
+    GTIMER_SEC      = 3, /* CNTPS_* ; EL3 physical timer */
+    GTIMER_HYPVIRT  = 4, /* CNTHV_* ; EL2 virtual timer ; only if FEAT_VHE */
+    GTIMER_S_EL2_PHYS = 5, /* CNTHPS_* ; only if FEAT_SEL2 */
+    GTIMER_S_EL2_VIRT = 6, /* CNTHVS_* ; only if FEAT_SEL2 */
+#define NUM_GTIMERS   7
 };
 
 #endif
diff --git a/target/arm/helper.c b/target/arm/helper.c
index 71dead7..407efe9 100644
--- a/target/arm/helper.c
+++ b/target/arm/helper.c
@@ -2387,6 +2387,9 @@ static CPAccessResult gt_stimer_access(CPUARMState *env,
         if (!arm_is_secure(env)) {
             return CP_ACCESS_UNDEFINED;
         }
+        if (arm_is_el2_enabled(env)) {
+            return CP_ACCESS_UNDEFINED;
+        }
         if (!(env->cp15.scr_el3 & SCR_ST)) {
             return CP_ACCESS_TRAP_EL3;
         }
@@ -2401,6 +2404,45 @@ static CPAccessResult gt_stimer_access(CPUARMState *env,
     }
 }
 
+static CPAccessResult gt_sel2timer_access(CPUARMState *env,
+                                          const ARMCPRegInfo *ri,
+                                          bool isread)
+{
+    /*
+     * The AArch64 register view of the secure EL2 timers are mostly
+     * accessible from EL3 and EL2 although can also be trapped to EL2
+     * from EL1 depending on nested virt config.
+     */
+    switch (arm_current_el(env)) {
+    case 0: /* UNDEFINED */
+        return CP_ACCESS_UNDEFINED;
+    case 1:
+        if (!arm_is_secure(env)) {
+            /* UNDEFINED */
+            return CP_ACCESS_UNDEFINED;
+        } else if (arm_hcr_el2_eff(env) & HCR_NV) {
+            /* Aarch64.SystemAccessTrap(EL2, 0x18) */
+            return CP_ACCESS_TRAP_EL2;
+        }
+        /* UNDEFINED */
+        return CP_ACCESS_UNDEFINED;
+    case 2:
+        if (!arm_is_secure(env)) {
+            /* UNDEFINED */
+            return CP_ACCESS_UNDEFINED;
+        }
+        return CP_ACCESS_OK;
+    case 3:
+        if (env->cp15.scr_el3 & SCR_EEL2) {
+            return CP_ACCESS_OK;
+        } else {
+            return CP_ACCESS_UNDEFINED;
+        }
+    default:
+        g_assert_not_reached();
+    }
+}
+
 uint64_t gt_get_countervalue(CPUARMState *env)
 {
     ARMCPU *cpu = env_archcpu(env);
@@ -2452,12 +2494,80 @@ static uint64_t gt_phys_raw_cnt_offset(CPUARMState *env)
     return 0;
 }
 
-static uint64_t gt_phys_cnt_offset(CPUARMState *env)
+static uint64_t gt_indirect_access_timer_offset(CPUARMState *env, int timeridx)
+{
+    /*
+     * Return the timer offset to use for indirect accesses to the timer.
+     * This is the Offset value as defined in D12.2.4.1 "Operation of the
+     * CompareValue views of the timers".
+     *
+     * The condition here is not always the same as the condition for
+     * whether to apply an offset register when doing a direct read of
+     * the counter sysreg; those conditions are described in the
+     * access pseudocode for each counter register.
+     */
+    switch (timeridx) {
+    case GTIMER_PHYS:
+        return gt_phys_raw_cnt_offset(env);
+    case GTIMER_VIRT:
+        return env->cp15.cntvoff_el2;
+    case GTIMER_HYP:
+    case GTIMER_SEC:
+    case GTIMER_HYPVIRT:
+    case GTIMER_S_EL2_PHYS:
+    case GTIMER_S_EL2_VIRT:
+        return 0;
+    default:
+        g_assert_not_reached();
+    }
+}
+
+uint64_t gt_direct_access_timer_offset(CPUARMState *env, int timeridx)
 {
-    if (arm_current_el(env) >= 2) {
+    /*
+     * Return the timer offset to use for direct accesses to the
+     * counter registers CNTPCT and CNTVCT, and for direct accesses
+     * to the CNT*_TVAL registers.
+     *
+     * This isn't exactly the same as the indirect-access offset,
+     * because here we also care about what EL the register access
+     * is being made from.
+     *
+     * This corresponds to the access pseudocode for the registers.
+     */
+    uint64_t hcr;
+
+    switch (timeridx) {
+    case GTIMER_PHYS:
+        if (arm_current_el(env) >= 2) {
+            return 0;
+        }
+        return gt_phys_raw_cnt_offset(env);
+    case GTIMER_VIRT:
+        switch (arm_current_el(env)) {
+        case 2:
+            hcr = arm_hcr_el2_eff(env);
+            if (hcr & HCR_E2H) {
+                return 0;
+            }
+            break;
+        case 0:
+            hcr = arm_hcr_el2_eff(env);
+            if ((hcr & (HCR_E2H | HCR_TGE)) == (HCR_E2H | HCR_TGE)) {
+                return 0;
+            }
+            break;
+        }
+        return env->cp15.cntvoff_el2;
+    case GTIMER_HYP:
+    case GTIMER_SEC:
+    case GTIMER_HYPVIRT:
+    case GTIMER_S_EL2_PHYS:
+    case GTIMER_S_EL2_VIRT:
         return 0;
+    default:
+        g_assert_not_reached();
     }
-    return gt_phys_raw_cnt_offset(env);
 }
 
 static void gt_recalc_timer(ARMCPU *cpu, int timeridx)
@@ -2469,8 +2579,7 @@ static void gt_recalc_timer(ARMCPU *cpu, int timeridx)
          * Timer enabled: calculate and set current ISTATUS, irq, and
          * reset timer to when ISTATUS next has to change
          */
-        uint64_t offset = timeridx == GTIMER_VIRT ?
-            cpu->env.cp15.cntvoff_el2 : gt_phys_raw_cnt_offset(&cpu->env);
+        uint64_t offset = gt_indirect_access_timer_offset(&cpu->env, timeridx);
         uint64_t count = gt_get_countervalue(&cpu->env);
         /* Note that this must be unsigned 64 bit arithmetic: */
         int istatus = count - offset >= gt->cval;
@@ -2533,34 +2642,14 @@ static void gt_timer_reset(CPUARMState *env, const ARMCPRegInfo *ri,
 
 static uint64_t gt_cnt_read(CPUARMState *env, const ARMCPRegInfo *ri)
 {
-    return gt_get_countervalue(env) - gt_phys_cnt_offset(env);
-}
-
-uint64_t gt_virt_cnt_offset(CPUARMState *env)
-{
-    uint64_t hcr;
-
-    switch (arm_current_el(env)) {
-    case 2:
-        hcr = arm_hcr_el2_eff(env);
-        if (hcr & HCR_E2H) {
-            return 0;
-        }
-        break;
-    case 0:
-        hcr = arm_hcr_el2_eff(env);
-        if ((hcr & (HCR_E2H | HCR_TGE)) == (HCR_E2H | HCR_TGE)) {
-            return 0;
-        }
-        break;
-    }
-
-    return env->cp15.cntvoff_el2;
+    uint64_t offset = gt_direct_access_timer_offset(env, GTIMER_PHYS);
+    return gt_get_countervalue(env) - offset;
 }
 
 static uint64_t gt_virt_cnt_read(CPUARMState *env, const ARMCPRegInfo *ri)
 {
-    return gt_get_countervalue(env) - gt_virt_cnt_offset(env);
+    uint64_t offset = gt_direct_access_timer_offset(env, GTIMER_VIRT);
+    return gt_get_countervalue(env) - offset;
 }
 
 static void gt_cval_write(CPUARMState *env, const ARMCPRegInfo *ri,
@@ -2572,47 +2661,38 @@ static void gt_cval_write(CPUARMState *env, const ARMCPRegInfo *ri,
     gt_recalc_timer(env_archcpu(env), timeridx);
 }
 
-static uint64_t gt_tval_read(CPUARMState *env, const ARMCPRegInfo *ri,
-                             int timeridx)
+static uint64_t do_tval_read(CPUARMState *env, int timeridx, uint64_t offset)
 {
-    uint64_t offset = 0;
-
-    switch (timeridx) {
-    case GTIMER_VIRT:
-    case GTIMER_HYPVIRT:
-        offset = gt_virt_cnt_offset(env);
-        break;
-    case GTIMER_PHYS:
-        offset = gt_phys_cnt_offset(env);
-        break;
-    }
-
     return (uint32_t)(env->cp15.c14_timer[timeridx].cval -
                       (gt_get_countervalue(env) - offset));
 }
 
-static void gt_tval_write(CPUARMState *env, const ARMCPRegInfo *ri,
-                          int timeridx,
-                          uint64_t value)
+static uint64_t gt_tval_read(CPUARMState *env, const ARMCPRegInfo *ri,
+                             int timeridx)
 {
-    uint64_t offset = 0;
+    uint64_t offset = gt_direct_access_timer_offset(env, timeridx);
 
-    switch (timeridx) {
-    case GTIMER_VIRT:
-    case GTIMER_HYPVIRT:
-        offset = gt_virt_cnt_offset(env);
-        break;
-    case GTIMER_PHYS:
-        offset = gt_phys_cnt_offset(env);
-        break;
-    }
+    return do_tval_read(env, timeridx, offset);
+}
 
+static void do_tval_write(CPUARMState *env, int timeridx, uint64_t value,
+                          uint64_t offset)
+{
     trace_arm_gt_tval_write(timeridx, value);
     env->cp15.c14_timer[timeridx].cval = gt_get_countervalue(env) - offset +
                                          sextract64(value, 0, 32);
     gt_recalc_timer(env_archcpu(env), timeridx);
 }
 
+static void gt_tval_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                          int timeridx,
+                          uint64_t value)
+{
+    uint64_t offset = gt_direct_access_timer_offset(env, timeridx);
+
+    do_tval_write(env, timeridx, value, offset);
+}
+
 static void gt_ctl_write(CPUARMState *env, const ARMCPRegInfo *ri,
                          int timeridx,
                          uint64_t value)
@@ -2742,13 +2822,21 @@ static void gt_virt_cval_write(CPUARMState *env, const ARMCPRegInfo *ri,
 
 static uint64_t gt_virt_tval_read(CPUARMState *env, const ARMCPRegInfo *ri)
 {
-    return gt_tval_read(env, ri, GTIMER_VIRT);
+    /*
+     * This is CNTV_TVAL_EL02; unlike the underlying CNTV_TVAL_EL0
+     * we always apply CNTVOFF_EL2. Special case that here rather
+     * than going into the generic gt_tval_read() and then having
+     * to re-detect that it's this register.
+     * Note that the accessfn/perms mean we know we're at EL2 or EL3 here.
+     */
+    return do_tval_read(env, GTIMER_VIRT, env->cp15.cntvoff_el2);
 }
 
 static void gt_virt_tval_write(CPUARMState *env, const ARMCPRegInfo *ri,
                                uint64_t value)
 {
-    gt_tval_write(env, ri, GTIMER_VIRT, value);
+    /* Similarly for writes to CNTV_TVAL_EL02 */
+    do_tval_write(env, GTIMER_VIRT, value, env->cp15.cntvoff_el2);
 }
 
 static void gt_virt_ctl_write(CPUARMState *env, const ARMCPRegInfo *ri,
@@ -2908,6 +2996,62 @@ static void gt_sec_ctl_write(CPUARMState *env, const ARMCPRegInfo *ri,
     gt_ctl_write(env, ri, GTIMER_SEC, value);
 }
 
+static void gt_sec_pel2_timer_reset(CPUARMState *env, const ARMCPRegInfo *ri)
+{
+    gt_timer_reset(env, ri, GTIMER_S_EL2_PHYS);
+}
+
+static void gt_sec_pel2_cval_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                                   uint64_t value)
+{
+    gt_cval_write(env, ri, GTIMER_S_EL2_PHYS, value);
+}
+
+static uint64_t gt_sec_pel2_tval_read(CPUARMState *env, const ARMCPRegInfo *ri)
+{
+    return gt_tval_read(env, ri, GTIMER_S_EL2_PHYS);
+}
+
+static void gt_sec_pel2_tval_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                              uint64_t value)
+{
+    gt_tval_write(env, ri, GTIMER_S_EL2_PHYS, value);
+}
+
+static void gt_sec_pel2_ctl_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                              uint64_t value)
+{
+    gt_ctl_write(env, ri, GTIMER_S_EL2_PHYS, value);
+}
+
+static void gt_sec_vel2_timer_reset(CPUARMState *env, const ARMCPRegInfo *ri)
+{
+    gt_timer_reset(env, ri, GTIMER_S_EL2_VIRT);
+}
+
+static void gt_sec_vel2_cval_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                              uint64_t value)
+{
+    gt_cval_write(env, ri, GTIMER_S_EL2_VIRT, value);
+}
+
+static uint64_t gt_sec_vel2_tval_read(CPUARMState *env, const ARMCPRegInfo *ri)
+{
+    return gt_tval_read(env, ri, GTIMER_S_EL2_VIRT);
+}
+
+static void gt_sec_vel2_tval_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                                   uint64_t value)
+{
+    gt_tval_write(env, ri, GTIMER_S_EL2_VIRT, value);
+}
+
+static void gt_sec_vel2_ctl_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                              uint64_t value)
+{
+    gt_ctl_write(env, ri, GTIMER_S_EL2_VIRT, value);
+}
+
 static void gt_hv_timer_reset(CPUARMState *env, const ARMCPRegInfo *ri)
 {
     gt_timer_reset(env, ri, GTIMER_HYPVIRT);
@@ -2964,6 +3108,20 @@ void arm_gt_stimer_cb(void *opaque)
     gt_recalc_timer(cpu, GTIMER_SEC);
 }
 
+void arm_gt_sel2timer_cb(void *opaque)
+{
+    ARMCPU *cpu = opaque;
+
+    gt_recalc_timer(cpu, GTIMER_S_EL2_PHYS);
+}
+
+void arm_gt_sel2vtimer_cb(void *opaque)
+{
+    ARMCPU *cpu = opaque;
+
+    gt_recalc_timer(cpu, GTIMER_S_EL2_VIRT);
+}
+
 void arm_gt_hvtimer_cb(void *opaque)
 {
     ARMCPU *cpu = opaque;
@@ -5688,6 +5846,56 @@ static const ARMCPRegInfo el2_sec_cp_reginfo[] = {
       .access = PL2_RW, .accessfn = sel2_access,
       .nv2_redirect_offset = 0x48,
       .fieldoffset = offsetof(CPUARMState, cp15.vstcr_el2) },
+#ifndef CONFIG_USER_ONLY
+    /* Secure EL2 Physical Timer */
+    { .name = "CNTHPS_TVAL_EL2", .state = ARM_CP_STATE_AA64,
+      .opc0 = 3, .opc1 = 4, .crn = 14, .crm = 5, .opc2 = 0,
+      .type = ARM_CP_NO_RAW | ARM_CP_IO, .access = PL2_RW,
+      .accessfn = gt_sel2timer_access,
+      .readfn = gt_sec_pel2_tval_read,
+      .writefn = gt_sec_pel2_tval_write,
+      .resetfn = gt_sec_pel2_timer_reset,
+    },
+    { .name = "CNTHPS_CTL_EL2", .state = ARM_CP_STATE_AA64,
+      .opc0 = 3, .opc1 = 4, .crn = 14, .crm = 5, .opc2 = 1,
+      .type = ARM_CP_IO, .access = PL2_RW,
+      .accessfn = gt_sel2timer_access,
+      .fieldoffset = offsetof(CPUARMState, cp15.c14_timer[GTIMER_S_EL2_PHYS].ctl),
+      .resetvalue = 0,
+      .writefn = gt_sec_pel2_ctl_write, .raw_writefn = raw_write,
+    },
+    { .name = "CNTHPS_CVAL_EL2", .state = ARM_CP_STATE_AA64,
+      .opc0 = 3, .opc1 = 4, .crn = 14, .crm = 5, .opc2 = 2,
+      .type = ARM_CP_IO, .access = PL2_RW,
+      .accessfn = gt_sel2timer_access,
+      .fieldoffset = offsetof(CPUARMState, cp15.c14_timer[GTIMER_S_EL2_PHYS].cval),
+      .writefn = gt_sec_pel2_cval_write, .raw_writefn = raw_write,
+    },
+    /* Secure EL2 Virtual Timer */
+    { .name = "CNTHVS_TVAL_EL2", .state = ARM_CP_STATE_AA64,
+      .opc0 = 3, .opc1 = 4, .crn = 14, .crm = 4, .opc2 = 0,
+      .type = ARM_CP_NO_RAW | ARM_CP_IO, .access = PL2_RW,
+      .accessfn = gt_sel2timer_access,
+      .readfn = gt_sec_vel2_tval_read,
+      .writefn = gt_sec_vel2_tval_write,
+      .resetfn = gt_sec_vel2_timer_reset,
+    },
+    { .name = "CNTHVS_CTL_EL2", .state = ARM_CP_STATE_AA64,
+      .opc0 = 3, .opc1 = 4, .crn = 14, .crm = 4, .opc2 = 1,
+      .type = ARM_CP_IO, .access = PL2_RW,
+      .accessfn = gt_sel2timer_access,
+      .fieldoffset = offsetof(CPUARMState, cp15.c14_timer[GTIMER_S_EL2_VIRT].ctl),
+      .resetvalue = 0,
+      .writefn = gt_sec_vel2_ctl_write, .raw_writefn = raw_write,
+    },
+    { .name = "CNTHVS_CVAL_EL2", .state = ARM_CP_STATE_AA64,
+      .opc0 = 3, .opc1 = 4, .crn = 14, .crm = 4, .opc2 = 2,
+      .type = ARM_CP_IO, .access = PL2_RW,
+      .accessfn = gt_sel2timer_access,
+      .fieldoffset = offsetof(CPUARMState, cp15.c14_timer[GTIMER_S_EL2_VIRT].cval),
+      .writefn = gt_sec_vel2_cval_write, .raw_writefn = raw_write,
+    },
+#endif
 };
 
 static CPAccessResult nsacr_access(CPUARMState *env, const ARMCPRegInfo *ri,
diff --git a/target/arm/internals.h b/target/arm/internals.h
index a6ff228..bb962389 100644
--- a/target/arm/internals.h
+++ b/target/arm/internals.h
@@ -1819,9 +1819,10 @@ int delete_hw_watchpoint(target_ulong addr, target_ulong len, int type);
 uint64_t gt_get_countervalue(CPUARMState *env);
 /*
  * Return the currently applicable offset between the system counter
- * and CNTVCT_EL0 (this will be either 0 or the value of CNTVOFF_EL2).
+ * and the counter for the specified timer, as used for direct register
+ * accesses.
  */
-uint64_t gt_virt_cnt_offset(CPUARMState *env);
+uint64_t gt_direct_access_timer_offset(CPUARMState *env, int timeridx);
 
 /*
  * Return mask of ARMMMUIdxBit values corresponding to an "invalidate
diff --git a/target/arm/tcg/op_helper.c b/target/arm/tcg/op_helper.c
index 02c375d..30786fd 100644
--- a/target/arm/tcg/op_helper.c
+++ b/target/arm/tcg/op_helper.c
@@ -427,7 +427,13 @@ void HELPER(wfit)(CPUARMState *env, uint64_t timeout)
     int target_el = check_wfx_trap(env, false, &excp);
     /* The WFIT should time out when CNTVCT_EL0 >= the specified value. */
     uint64_t cntval = gt_get_countervalue(env);
-    uint64_t offset = gt_virt_cnt_offset(env);
+    /*
+     * We want the value that we would get if we read CNTVCT_EL0 from
+     * the current exception level, so the direct_access offset, not
+     * the indirect_access one. Compare the pseudocode LocalTimeoutEvent(),
+     * which calls VirtualCounterTimer().
+     */
+    uint64_t offset = gt_direct_access_timer_offset(env, GTIMER_VIRT);
     uint64_t cntvct = cntval - offset;
     uint64_t nexttick;
 
diff --git a/target/arm/tcg/translate.c b/target/arm/tcg/translate.c
index d8225b7..d280018 100644
--- a/target/arm/tcg/translate.c
+++ b/target/arm/tcg/translate.c
@@ -4941,7 +4941,7 @@ static TCGv_i32 op_addr_rr_pre(DisasContext *s, arg_ldst_rr *a)
 }
 
 static void op_addr_rr_post(DisasContext *s, arg_ldst_rr *a,
-                            TCGv_i32 addr, int address_offset)
+                            TCGv_i32 addr)
 {
     if (!a->p) {
         TCGv_i32 ofs = load_reg(s, a->rm);
@@ -4954,7 +4954,6 @@ static void op_addr_rr_post(DisasContext *s, arg_ldst_rr *a,
     } else if (!a->w) {
         return;
     }
-    tcg_gen_addi_i32(addr, addr, address_offset);
     store_reg(s, a->rn, addr);
 }
 
@@ -4974,7 +4973,7 @@ static bool op_load_rr(DisasContext *s, arg_ldst_rr *a,
      * Perform base writeback before the loaded value to
      * ensure correct behavior with overlapping index registers.
      */
-    op_addr_rr_post(s, a, addr, 0);
+    op_addr_rr_post(s, a, addr);
     store_reg_from_load(s, a->rt, tmp);
     return true;
 }
@@ -4999,14 +4998,53 @@ static bool op_store_rr(DisasContext *s, arg_ldst_rr *a,
     gen_aa32_st_i32(s, tmp, addr, mem_idx, mop);
     disas_set_da_iss(s, mop, issinfo);
 
-    op_addr_rr_post(s, a, addr, 0);
+    op_addr_rr_post(s, a, addr);
     return true;
 }
 
-static bool trans_LDRD_rr(DisasContext *s, arg_ldst_rr *a)
+static void do_ldrd_load(DisasContext *s, TCGv_i32 addr, int rt, int rt2)
 {
+    /*
+     * LDRD is required to be an atomic 64-bit access if the
+     * address is 8-aligned, two atomic 32-bit accesses if
+     * it's only 4-aligned, and to give an alignment fault
+     * if it's not 4-aligned. This is MO_ALIGN_4 | MO_ATOM_SUBALIGN.
+     * Rt is always the word from the lower address, and Rt2 the
+     * data from the higher address, regardless of endianness.
+     * So (like gen_load_exclusive) we avoid gen_aa32_ld_i64()
+     * so we don't get its SCTLR_B check, and instead do a 64-bit access
+     * using MO_BE if appropriate and then split the two halves.
+     *
+     * For M-profile, and for A-profile before LPAE, the 64-bit
+     * atomicity is not required. We could model that using
+     * the looser MO_ATOM_IFALIGN_PAIR, but providing a higher
+     * level of atomicity than required is harmless (we would not
+     * currently generate better code for IFALIGN_PAIR here).
+     *
+     * This also gives us the correct behaviour of not updating
+     * rt if the load of rt2 faults; this is required for cases
+     * like "ldrd r2, r3, [r2]" where rt is also the base register.
+     */
     int mem_idx = get_mem_index(s);
-    TCGv_i32 addr, tmp;
+    MemOp opc = MO_64 | MO_ALIGN_4 | MO_ATOM_SUBALIGN | s->be_data;
+    TCGv taddr = gen_aa32_addr(s, addr, opc);
+    TCGv_i64 t64 = tcg_temp_new_i64();
+    TCGv_i32 tmp = tcg_temp_new_i32();
+    TCGv_i32 tmp2 = tcg_temp_new_i32();
+
+    tcg_gen_qemu_ld_i64(t64, taddr, mem_idx, opc);
+    if (s->be_data == MO_BE) {
+        tcg_gen_extr_i64_i32(tmp2, tmp, t64);
+    } else {
+        tcg_gen_extr_i64_i32(tmp, tmp2, t64);
+    }
+    store_reg(s, rt, tmp);
+    store_reg(s, rt2, tmp2);
+}
+
+static bool trans_LDRD_rr(DisasContext *s, arg_ldst_rr *a)
+{
+    TCGv_i32 addr;
 
     if (!ENABLE_ARCH_5TE) {
         return false;
@@ -5017,25 +5055,49 @@ static bool trans_LDRD_rr(DisasContext *s, arg_ldst_rr *a)
     }
     addr = op_addr_rr_pre(s, a);
 
-    tmp = tcg_temp_new_i32();
-    gen_aa32_ld_i32(s, tmp, addr, mem_idx, MO_UL | MO_ALIGN);
-    store_reg(s, a->rt, tmp);
-
-    tcg_gen_addi_i32(addr, addr, 4);
-
-    tmp = tcg_temp_new_i32();
-    gen_aa32_ld_i32(s, tmp, addr, mem_idx, MO_UL | MO_ALIGN);
-    store_reg(s, a->rt + 1, tmp);
+    do_ldrd_load(s, addr, a->rt, a->rt + 1);
 
     /* LDRD w/ base writeback is undefined if the registers overlap.  */
-    op_addr_rr_post(s, a, addr, -4);
+    op_addr_rr_post(s, a, addr);
     return true;
 }
 
-static bool trans_STRD_rr(DisasContext *s, arg_ldst_rr *a)
+static void do_strd_store(DisasContext *s, TCGv_i32 addr, int rt, int rt2)
 {
+    /*
+     * STRD is required to be an atomic 64-bit access if the
+     * address is 8-aligned, two atomic 32-bit accesses if
+     * it's only 4-aligned, and to give an alignment fault
+     * if it's not 4-aligned.
+     * Rt is always the word from the lower address, and Rt2 the
+     * data from the higher address, regardless of endianness.
+     * So (like gen_store_exclusive) we avoid gen_aa32_ld_i64()
+     * so we don't get its SCTLR_B check, and instead do a 64-bit access
+     * using MO_BE if appropriate, using a value constructed
+     * by putting the two halves together in the right order.
+     *
+     * As with LDRD, the 64-bit atomicity is not required for
+     * M-profile, or for A-profile before LPAE, and we provide
+     * the higher guarantee always for simplicity.
+     */
     int mem_idx = get_mem_index(s);
-    TCGv_i32 addr, tmp;
+    MemOp opc = MO_64 | MO_ALIGN_4 | MO_ATOM_SUBALIGN | s->be_data;
+    TCGv taddr = gen_aa32_addr(s, addr, opc);
+    TCGv_i32 t1 = load_reg(s, rt);
+    TCGv_i32 t2 = load_reg(s, rt2);
+    TCGv_i64 t64 = tcg_temp_new_i64();
+
+    if (s->be_data == MO_BE) {
+        tcg_gen_concat_i32_i64(t64, t2, t1);
+    } else {
+        tcg_gen_concat_i32_i64(t64, t1, t2);
+    }
+    tcg_gen_qemu_st_i64(t64, taddr, mem_idx, opc);
+}
+
+static bool trans_STRD_rr(DisasContext *s, arg_ldst_rr *a)
+{
+    TCGv_i32 addr;
 
     if (!ENABLE_ARCH_5TE) {
         return false;
@@ -5046,15 +5108,9 @@ static bool trans_STRD_rr(DisasContext *s, arg_ldst_rr *a)
     }
     addr = op_addr_rr_pre(s, a);
 
-    tmp = load_reg(s, a->rt);
-    gen_aa32_st_i32(s, tmp, addr, mem_idx, MO_UL | MO_ALIGN);
-
-    tcg_gen_addi_i32(addr, addr, 4);
+    do_strd_store(s, addr, a->rt, a->rt + 1);
 
-    tmp = load_reg(s, a->rt + 1);
-    gen_aa32_st_i32(s, tmp, addr, mem_idx, MO_UL | MO_ALIGN);
-
-    op_addr_rr_post(s, a, addr, -4);
+    op_addr_rr_post(s, a, addr);
     return true;
 }
 
@@ -5090,13 +5146,14 @@ static TCGv_i32 op_addr_ri_pre(DisasContext *s, arg_ldst_ri *a)
 }
 
 static void op_addr_ri_post(DisasContext *s, arg_ldst_ri *a,
-                            TCGv_i32 addr, int address_offset)
+                            TCGv_i32 addr)
 {
+    int address_offset = 0;
     if (!a->p) {
         if (a->u) {
-            address_offset += a->imm;
+            address_offset = a->imm;
         } else {
-            address_offset -= a->imm;
+            address_offset = -a->imm;
         }
     } else if (!a->w) {
         return;
@@ -5121,7 +5178,7 @@ static bool op_load_ri(DisasContext *s, arg_ldst_ri *a,
      * Perform base writeback before the loaded value to
      * ensure correct behavior with overlapping index registers.
      */
-    op_addr_ri_post(s, a, addr, 0);
+    op_addr_ri_post(s, a, addr);
     store_reg_from_load(s, a->rt, tmp);
     return true;
 }
@@ -5146,29 +5203,20 @@ static bool op_store_ri(DisasContext *s, arg_ldst_ri *a,
     gen_aa32_st_i32(s, tmp, addr, mem_idx, mop);
     disas_set_da_iss(s, mop, issinfo);
 
-    op_addr_ri_post(s, a, addr, 0);
+    op_addr_ri_post(s, a, addr);
     return true;
 }
 
 static bool op_ldrd_ri(DisasContext *s, arg_ldst_ri *a, int rt2)
 {
-    int mem_idx = get_mem_index(s);
-    TCGv_i32 addr, tmp;
+    TCGv_i32 addr;
 
     addr = op_addr_ri_pre(s, a);
 
-    tmp = tcg_temp_new_i32();
-    gen_aa32_ld_i32(s, tmp, addr, mem_idx, MO_UL | MO_ALIGN);
-    store_reg(s, a->rt, tmp);
-
-    tcg_gen_addi_i32(addr, addr, 4);
-
-    tmp = tcg_temp_new_i32();
-    gen_aa32_ld_i32(s, tmp, addr, mem_idx, MO_UL | MO_ALIGN);
-    store_reg(s, rt2, tmp);
+    do_ldrd_load(s, addr, a->rt, rt2);
 
     /* LDRD w/ base writeback is undefined if the registers overlap.  */
-    op_addr_ri_post(s, a, addr, -4);
+    op_addr_ri_post(s, a, addr);
     return true;
 }
 
@@ -5191,20 +5239,13 @@ static bool trans_LDRD_ri_t32(DisasContext *s, arg_ldst_ri2 *a)
 
 static bool op_strd_ri(DisasContext *s, arg_ldst_ri *a, int rt2)
 {
-    int mem_idx = get_mem_index(s);
-    TCGv_i32 addr, tmp;
+    TCGv_i32 addr;
 
     addr = op_addr_ri_pre(s, a);
 
-    tmp = load_reg(s, a->rt);
-    gen_aa32_st_i32(s, tmp, addr, mem_idx, MO_UL | MO_ALIGN);
-
-    tcg_gen_addi_i32(addr, addr, 4);
-
-    tmp = load_reg(s, rt2);
-    gen_aa32_st_i32(s, tmp, addr, mem_idx, MO_UL | MO_ALIGN);
+    do_strd_store(s, addr, a->rt, rt2);
 
-    op_addr_ri_post(s, a, addr, -4);
+    op_addr_ri_post(s, a, addr);
     return true;
 }
 
diff --git a/target/rx/helper.c b/target/rx/helper.c
index 7f28e72..e8aabf4 100644
--- a/target/rx/helper.c
+++ b/target/rx/helper.c
@@ -88,7 +88,7 @@ void rx_cpu_do_interrupt(CPUState *cs)
         cpu_stl_data(env, env->isp, env->pc);
 
         if (vec < 0x100) {
-            env->pc = cpu_ldl_data(env, 0xffffffc0 + vec * 4);
+            env->pc = cpu_ldl_data(env, 0xffffff80 + vec * 4);
         } else {
             env->pc = cpu_ldl_data(env, env->intb + (vec & 0xff) * 4);
         }
diff --git a/target/rx/helper.h b/target/rx/helper.h
index ebb4739..8cc38b0 100644
--- a/target/rx/helper.h
+++ b/target/rx/helper.h
@@ -4,27 +4,27 @@ DEF_HELPER_1(raise_privilege_violation, noreturn, env)
 DEF_HELPER_1(wait, noreturn, env)
 DEF_HELPER_2(rxint, noreturn, env, i32)
 DEF_HELPER_1(rxbrk, noreturn, env)
-DEF_HELPER_FLAGS_3(fadd, TCG_CALL_NO_WG, f32, env, f32, f32)
-DEF_HELPER_FLAGS_3(fsub, TCG_CALL_NO_WG, f32, env, f32, f32)
-DEF_HELPER_FLAGS_3(fmul, TCG_CALL_NO_WG, f32, env, f32, f32)
-DEF_HELPER_FLAGS_3(fdiv, TCG_CALL_NO_WG, f32, env, f32, f32)
-DEF_HELPER_FLAGS_3(fcmp, TCG_CALL_NO_WG, void, env, f32, f32)
-DEF_HELPER_FLAGS_2(ftoi, TCG_CALL_NO_WG, i32, env, f32)
-DEF_HELPER_FLAGS_2(round, TCG_CALL_NO_WG, i32, env, f32)
-DEF_HELPER_FLAGS_2(itof, TCG_CALL_NO_WG, f32, env, i32)
+DEF_HELPER_3(fadd, f32, env, f32, f32)
+DEF_HELPER_3(fsub, f32, env, f32, f32)
+DEF_HELPER_3(fmul, f32, env, f32, f32)
+DEF_HELPER_3(fdiv, f32, env, f32, f32)
+DEF_HELPER_3(fcmp, void, env, f32, f32)
+DEF_HELPER_2(ftoi, i32, env, f32)
+DEF_HELPER_2(round, i32, env, f32)
+DEF_HELPER_2(itof, f32, env, i32)
 DEF_HELPER_2(set_fpsw, void, env, i32)
-DEF_HELPER_FLAGS_2(racw, TCG_CALL_NO_WG, void, env, i32)
-DEF_HELPER_FLAGS_2(set_psw_rte, TCG_CALL_NO_WG, void, env, i32)
-DEF_HELPER_FLAGS_2(set_psw, TCG_CALL_NO_WG, void, env, i32)
+DEF_HELPER_2(racw, void, env, i32)
+DEF_HELPER_2(set_psw_rte, void, env, i32)
+DEF_HELPER_2(set_psw, void, env, i32)
 DEF_HELPER_1(pack_psw, i32, env)
-DEF_HELPER_FLAGS_3(div, TCG_CALL_NO_WG, i32, env, i32, i32)
-DEF_HELPER_FLAGS_3(divu, TCG_CALL_NO_WG, i32, env, i32, i32)
-DEF_HELPER_FLAGS_1(scmpu, TCG_CALL_NO_WG, void, env)
+DEF_HELPER_3(div, i32, env, i32, i32)
+DEF_HELPER_3(divu, i32, env, i32, i32)
+DEF_HELPER_1(scmpu, void, env)
 DEF_HELPER_1(smovu, void, env)
 DEF_HELPER_1(smovf, void, env)
 DEF_HELPER_1(smovb, void, env)
 DEF_HELPER_2(sstr, void, env, i32)
-DEF_HELPER_FLAGS_2(swhile, TCG_CALL_NO_WG, void, env, i32)
-DEF_HELPER_FLAGS_2(suntil, TCG_CALL_NO_WG, void, env, i32)
-DEF_HELPER_FLAGS_2(rmpa, TCG_CALL_NO_WG, void, env, i32)
+DEF_HELPER_2(swhile, void, env, i32)
+DEF_HELPER_2(suntil, void, env, i32)
+DEF_HELPER_2(rmpa, void, env, i32)
 DEF_HELPER_1(satr, void, env)
diff --git a/tests/functional/test_arm_sx1.py b/tests/functional/test_arm_sx1.py
index 4dd1e18..25800b3 100755
--- a/tests/functional/test_arm_sx1.py
+++ b/tests/functional/test_arm_sx1.py
@@ -43,7 +43,8 @@ class SX1Test(LinuxKernelTest):
         self.vm.add_args('-append', f'kunit.enable=0 rdinit=/sbin/init {self.CONSOLE_ARGS}')
         self.vm.add_args('-no-reboot')
         self.launch_kernel(zimage_path,
-                           initrd=initrd_path)
+                           initrd=initrd_path,
+                           wait_for='Boot successful')
         self.vm.wait(timeout=120)
 
     def test_arm_sx1_sd(self):
@@ -54,7 +55,7 @@ class SX1Test(LinuxKernelTest):
         self.vm.add_args('-no-reboot')
         self.vm.add_args('-snapshot')
         self.vm.add_args('-drive', f'format=raw,if=sd,file={sd_fs_path}')
-        self.launch_kernel(zimage_path)
+        self.launch_kernel(zimage_path, wait_for='Boot successful')
         self.vm.wait(timeout=120)
 
     def test_arm_sx1_flash(self):
@@ -65,7 +66,7 @@ class SX1Test(LinuxKernelTest):
         self.vm.add_args('-no-reboot')
         self.vm.add_args('-snapshot')
         self.vm.add_args('-drive', f'format=raw,if=pflash,file={flash_path}')
-        self.launch_kernel(zimage_path)
+        self.launch_kernel(zimage_path, wait_for='Boot successful')
         self.vm.wait(timeout=120)
 
 if __name__ == '__main__':
diff --git a/util/qemu-timer.c b/util/qemu-timer.c
index 3243d2c..788466f 100644
--- a/util/qemu-timer.c
+++ b/util/qemu-timer.c
@@ -409,10 +409,6 @@ static bool timer_mod_ns_locked(QEMUTimerList *timer_list,
 
 static void timerlist_rearm(QEMUTimerList *timer_list)
 {
-    /* Interrupt execution to force deadline recalculation.  */
-    if (icount_enabled() && timer_list->clock->type == QEMU_CLOCK_VIRTUAL) {
-        icount_start_warp_timer();
-    }
     timerlist_notify(timer_list);
 }