diff --git a/executables/nr-gnb.c b/executables/nr-gnb.c
index e8720d00ad..707297e419 100644
--- a/executables/nr-gnb.c
+++ b/executables/nr-gnb.c
@@ -111,42 +111,63 @@ time_stats_t softmodem_stats_rx_sf; // total rx time
 #define TICK_TO_US(ts) (ts.trials==0?0:ts.diff/ts.trials)
 #define L1STATSSTRLEN 16384
 
-
-void tx_func(void *param) 
+static void tx_func(void *param)
 {
   processingData_L1tx_t *info = (processingData_L1tx_t *) param;
-  PHY_VARS_gNB *gNB = info->gNB;
+
   int frame_tx = info->frame;
   int slot_tx = info->slot;
-  int cumul_samples = gNB->frame_parms.get_samples_per_slot(0, &gNB->frame_parms);
-  int i = 1;
-  for (; i < gNB->frame_parms.slots_per_subframe / 2; i++)
-    cumul_samples += gNB->frame_parms.get_samples_per_slot(i, &gNB->frame_parms);
-  int samples = cumul_samples / i;
-  int absslot_tx = info->timestamp_tx / samples;
-  int absslot_rx = absslot_tx - gNB->RU_list[0]->sl_ahead;
-  int rt_prof_idx = absslot_rx % RT_PROF_DEPTH;
-  start_meas(&gNB->phy_proc_tx);
+  int frame_rx = info->frame_rx;
+  int slot_rx = info->slot_rx;
+  int absslot_tx = info->timestamp_tx / info->gNB->frame_parms.get_samples_per_slot(slot_tx, &info->gNB->frame_parms);
+  int absslot_rx = absslot_tx - info->gNB->RU_list[0]->sl_ahead;
 
-  clock_gettime(CLOCK_MONOTONIC, &gNB->rt_L1_profiling.start_L1_TX[rt_prof_idx]);
-  phy_procedures_gNB_TX(info,
-                        frame_tx,
-                        slot_tx,
-                        1);
-  clock_gettime(CLOCK_MONOTONIC, &gNB->rt_L1_profiling.return_L1_TX[rt_prof_idx]);
+  LOG_D(NR_PHY, "%d.%d running tx_func\n", frame_tx, slot_tx);
+  PHY_VARS_gNB *gNB = info->gNB;
+  module_id_t module_id = gNB->Mod_id;
+  uint8_t CC_id = gNB->CC_id;
+  NR_IF_Module_t *ifi = gNB->if_inst;
+  nfapi_nr_config_request_scf_t *cfg = &gNB->gNB_config;
 
-  if (get_softmodem_params()->reorder_thread_disable) {
+  T(T_GNB_PHY_DL_TICK, T_INT(gNB->Mod_id), T_INT(frame_tx), T_INT(slot_tx));
+
+  ifi->NR_slot_indication(module_id, CC_id, frame_tx, slot_tx);
+  gNB->msgDataTx->timestamp_tx = info->timestamp_tx;
+  info = gNB->msgDataTx;
+  info->gNB = gNB;
+
+  // At this point, MAC scheduler just ran, including scheduling
+  // PRACH/PUCCH/PUSCH, so trigger RX chain processing
+  LOG_D(NR_PHY, "%s() trigger RX for %d.%d\n", __func__, frame_rx, slot_rx);
+  notifiedFIFO_elt_t *res = newNotifiedFIFO_elt(sizeof(processingData_L1_t), 0, &gNB->resp_L1, NULL);
+  processingData_L1_t *syncMsg = NotifiedFifoData(res);
+  syncMsg->gNB = gNB;
+  syncMsg->frame_rx = frame_rx;
+  syncMsg->slot_rx = slot_rx;
+  syncMsg->timestamp_tx = info->timestamp_tx;
+  res->key = slot_rx;
+  pushNotifiedFIFO(&gNB->resp_L1, res);
+
+  int tx_slot_type = nr_slot_select(cfg, frame_tx, slot_tx);
+  if (tx_slot_type == NR_DOWNLINK_SLOT || tx_slot_type == NR_MIXED_SLOT || get_softmodem_params()->continuous_tx) {
+    start_meas(&info->gNB->phy_proc_tx);
+    phy_procedures_gNB_TX(info, frame_tx, slot_tx, 1);
+    const int rt_prof_idx = absslot_rx % RT_PROF_DEPTH;
+    clock_gettime(CLOCK_MONOTONIC, &info->gNB->rt_L1_profiling.return_L1_TX[rt_prof_idx]);
+
+    PHY_VARS_gNB *gNB = info->gNB;
     processingData_RU_t syncMsgRU;
     syncMsgRU.frame_tx = frame_tx;
     syncMsgRU.slot_tx = slot_tx;
     syncMsgRU.ru = gNB->RU_list[0];
     syncMsgRU.timestamp_tx = info->timestamp_tx;
-    LOG_D(PHY,"gNB: %d.%d : calling RU TX function\n",syncMsgRU.frame_tx,syncMsgRU.slot_tx);
-    ru_tx_func((void*)&syncMsgRU);
+    LOG_D(PHY, "gNB: %d.%d : calling RU TX function\n", syncMsgRU.frame_tx, syncMsgRU.slot_tx);
+    ru_tx_func((void *)&syncMsgRU);
+    stop_meas(&info->gNB->phy_proc_tx);
   }
   /* this thread is done with the sched_info, decrease the reference counter */
+  LOG_D(NR_PHY, "Calling deref_sched_response for id %d (tx_func) in %d.%d\n", info->sched_response_id, frame_tx, slot_tx);
   deref_sched_response(info->sched_response_id);
-  stop_meas(&gNB->phy_proc_tx);
 }
 
 
@@ -164,27 +185,27 @@ void *L1_rx_thread(void *arg)
   }
   return NULL;
 }
-/* to be added for URLLC, requires MAC scheduling to be split from UL indication 
+// Added for URLLC, requires MAC scheduling to be split from UL indication
 void *L1_tx_thread(void *arg) {
   PHY_VARS_gNB *gNB = (PHY_VARS_gNB*)arg;
 
   while (oai_exit == 0) {
      notifiedFIFO_elt_t *res = pullNotifiedFIFO(&gNB->L1_tx_out);
+     if (res == NULL) // stopping condition, happens only when queue is freed
+       break;
      processingData_L1tx_t *info = (processingData_L1tx_t *)NotifiedFifoData(res);
      tx_func(info);
      delNotifiedFIFO_elt(res);
   }
   return NULL;
 }
-*/
+
 void rx_func(void *param)
 {
   processingData_L1_t *info = (processingData_L1_t *) param;
   PHY_VARS_gNB *gNB = info->gNB;
   int frame_rx = info->frame_rx;
   int slot_rx = info->slot_rx;
-  int frame_tx = info->frame_tx;
-  int slot_tx = info->slot_tx;
   nfapi_nr_config_request_scf_t *cfg = &gNB->gNB_config;
   int cumul_samples = gNB->frame_parms.get_samples_per_slot(0, &gNB->frame_parms);
   int i = 1;
@@ -209,14 +230,11 @@ void rx_func(void *param)
   }
   // ****************************************
 
-  T(T_GNB_PHY_DL_TICK, T_INT(gNB->Mod_id), T_INT(frame_tx), T_INT(slot_tx));
-
-  reset_active_stats(gNB, frame_tx);
-  reset_active_ulsch(gNB, frame_tx);
-
   // RX processing
   int rx_slot_type = nr_slot_select(cfg, frame_rx, slot_rx);
   if (rx_slot_type == NR_UPLINK_SLOT || rx_slot_type == NR_MIXED_SLOT) {
+    LOG_D(NR_PHY, "%d.%d Starting RX processing\n", frame_rx, slot_rx);
+
     // UE-specific RX processing for subframe n
     // TODO: check if this is correct for PARALLEL_RU_L1_TRX_SPLIT
 
@@ -239,57 +257,30 @@ void rx_func(void *param)
       }
     }
     phy_procedures_gNB_uespec_RX(gNB, frame_rx, slot_rx);
-  }
 
-  stop_meas( &softmodem_stats_rxtx_sf );
-  LOG_D(PHY,"%s() Exit proc[rx:%d%d tx:%d%d]\n", __FUNCTION__, frame_rx, slot_rx, frame_tx, slot_tx);
-  clock_gettime(CLOCK_MONOTONIC,&info->gNB->rt_L1_profiling.return_L1_RX[rt_prof_idx]);
+    // Call the scheduler
+    start_meas(&gNB->ul_indication_stats);
+    gNB->UL_INFO.frame = frame_rx;
+    gNB->UL_INFO.slot = slot_rx;
+    gNB->UL_INFO.module_id = gNB->Mod_id;
+    gNB->UL_INFO.CC_id = gNB->CC_id;
+    gNB->if_inst->NR_UL_indication(&gNB->UL_INFO);
+    stop_meas(&gNB->ul_indication_stats);
 
-  // Call the scheduler
-  start_meas(&gNB->ul_indication_stats);
-  gNB->UL_INFO.frame     = frame_rx;
-  gNB->UL_INFO.slot      = slot_rx;
-  gNB->UL_INFO.module_id = gNB->Mod_id;
-  gNB->UL_INFO.CC_id     = gNB->CC_id;
-  gNB->if_inst->NR_UL_indication(&gNB->UL_INFO);
-  stop_meas(&gNB->ul_indication_stats);
-
-  int tx_slot_type = nr_slot_select(cfg,frame_tx,slot_tx);
-  if ((tx_slot_type == NR_DOWNLINK_SLOT || tx_slot_type == NR_MIXED_SLOT) && NFAPI_MODE != NFAPI_MODE_PNF) {
-    notifiedFIFO_elt_t *res;
-    processingData_L1tx_t *syncMsg;
-    // Its a FIFO so it maitains the order in which the MAC fills the messages
-    // so no need for checking for right slot
-    if (get_softmodem_params()->reorder_thread_disable) {
-      // call the TX function directly from this thread
-      syncMsg = gNB->msgDataTx;
-      syncMsg->gNB = gNB; 
-      syncMsg->timestamp_tx = info->timestamp_tx;
-      tx_func(syncMsg);
-    } else {
-      res = pullTpool(&gNB->L1_tx_filled, &gNB->threadPool);
-      if (res == NULL)
-        return; // Tpool has been stopped
-      syncMsg = (processingData_L1tx_t *)NotifiedFifoData(res);
-      syncMsg->gNB = gNB;
-      syncMsg->timestamp_tx = info->timestamp_tx;
-      res->key = slot_tx;
-      pushTpool(&gNB->threadPool, res);
-    }
-  } else if (get_softmodem_params()->continuous_tx) {
-    notifiedFIFO_elt_t *res = pullNotifiedFIFO(&gNB->L1_tx_free);
-    if (res == NULL)
-      return; // Tpool has been stopped
-    processingData_L1tx_t *syncMsg = (processingData_L1tx_t *)NotifiedFifoData(res);
+    notifiedFIFO_elt_t *res = newNotifiedFIFO_elt(sizeof(processingData_L1_t), 0, &gNB->L1_rx_out, NULL);
+    processingData_L1_t *syncMsg = NotifiedFifoData(res);
     syncMsg->gNB = gNB;
-    syncMsg->timestamp_tx = info->timestamp_tx;
-    syncMsg->frame = frame_tx;
-    syncMsg->slot = slot_tx;
-    res->key = slot_tx;
-    pushNotifiedFIFO(&gNB->L1_tx_out, res);
+    syncMsg->frame_rx = frame_rx;
+    syncMsg->slot_rx = slot_rx;
+    res->key = slot_rx;
+    LOG_D(NR_PHY, "Signaling completion for %d.%d (mod_slot %d) on L1_rx_out\n", frame_rx, slot_rx, slot_rx % RU_RX_SLOT_DEPTH);
+    pushNotifiedFIFO(&gNB->L1_rx_out, res);
   }
 
+  stop_meas(&softmodem_stats_rxtx_sf);
+  clock_gettime(CLOCK_MONOTONIC, &info->gNB->rt_L1_profiling.return_L1_RX[rt_prof_idx]);
 }
+
 static size_t dump_L1_meas_stats(PHY_VARS_gNB *gNB, RU_t *ru, char *output, size_t outputlen) {
   const char *begin = output;
   const char *end = output + outputlen;
@@ -367,60 +358,6 @@ void *nrL1_stats_thread(void *param) {
   return(NULL);
 }
 
-// This thread reads the finished L1 tx jobs from threaPool
-// and pushes RU tx thread in the right order. It works only
-// two parallel L1 tx threads.
-void *tx_reorder_thread(void* param) {
-  PHY_VARS_gNB *gNB = (PHY_VARS_gNB *)param;
-  
-  notifiedFIFO_elt_t *resL1Reserve = pullNotifiedFIFO(&gNB->L1_tx_out);
-  AssertFatal(resL1Reserve != NULL, "pullTpool() did not return start message in %s\n", __func__);
-  int next_tx_slot=((processingData_L1tx_t *)NotifiedFifoData(resL1Reserve))->slot;
-  
-  LOG_I(PHY,"tx_reorder_thread started\n");
-  
-  while (!oai_exit) {
-    notifiedFIFO_elt_t *resL1;
-    if (resL1Reserve) {
-       resL1=resL1Reserve;
-       if (((processingData_L1tx_t *)NotifiedFifoData(resL1))->slot != next_tx_slot) {
-         LOG_E(PHY,"order mistake\n");
-         resL1Reserve = NULL;
-         resL1 = pullNotifiedFIFO(&gNB->L1_tx_out);
-       }
-     } else {
-       resL1 = pullNotifiedFIFO(&gNB->L1_tx_out);
-       if (resL1 != NULL && ((processingData_L1tx_t *)NotifiedFifoData(resL1))->slot != next_tx_slot) {
-          if (resL1Reserve)
-              LOG_E(PHY,"error, have a stored packet, then a second one\n");
-          resL1Reserve = resL1;
-          resL1 = pullNotifiedFIFO(&gNB->L1_tx_out);
-          if (((processingData_L1tx_t *)NotifiedFifoData(resL1))->slot != next_tx_slot)
-            LOG_E(PHY,"error, pull two msg, none is good\n");
-       }
-    }
-    if (resL1 == NULL)
-      break; // Tpool has been stopped
-    processingData_L1tx_t *syncMsgL1= (processingData_L1tx_t *)NotifiedFifoData(resL1);
-    processingData_RU_t syncMsgRU;
-    syncMsgRU.frame_tx = syncMsgL1->frame;
-    syncMsgRU.slot_tx = syncMsgL1->slot;
-    syncMsgRU.timestamp_tx = syncMsgL1->timestamp_tx;
-    syncMsgRU.ru = gNB->RU_list[0];
-    if (get_softmodem_params()->continuous_tx) {
-      int slots_per_frame = gNB->frame_parms.slots_per_frame;
-      next_tx_slot = (syncMsgRU.slot_tx + 1) % slots_per_frame;
-    } else
-      next_tx_slot = get_next_downlink_slot(gNB, &gNB->gNB_config, syncMsgRU.frame_tx, syncMsgRU.slot_tx);
-    pushNotifiedFIFO(&gNB->L1_tx_free, resL1);
-    if (resL1==resL1Reserve)
-       resL1Reserve=NULL;
-    LOG_D(PHY,"gNB: %d.%d : calling RU TX function\n",syncMsgL1->frame,syncMsgL1->slot);
-    ru_tx_func((void*)&syncMsgRU);
-  }
-  return(NULL);
-}
-
 void init_gNB_Tpool(int inst) {
   PHY_VARS_gNB *gNB;
   gNB = RC.gNB[inst];
@@ -433,47 +370,26 @@ void init_gNB_Tpool(int inst) {
   initNotifiedFIFO(&gNB->respPuschSymb);
   initNotifiedFIFO(&gNB->respDecode);
 
-  // L1 RX result FIFO 
+  // L1 RX result FIFO
   initNotifiedFIFO(&gNB->resp_L1);
-  if (!get_softmodem_params()->reorder_thread_disable) {
-    notifiedFIFO_elt_t *msg = newNotifiedFIFO_elt(sizeof(processingData_L1_t), 0, &gNB->resp_L1, rx_func);
-    pushNotifiedFIFO(&gNB->resp_L1, msg); // to unblock the process in the beginning
-  }
   // L1 TX result FIFO 
   initNotifiedFIFO(&gNB->L1_tx_free);
   initNotifiedFIFO(&gNB->L1_tx_filled);
   initNotifiedFIFO(&gNB->L1_tx_out);
- 
-  if (get_softmodem_params()->reorder_thread_disable) {
-    // create the RX thread responsible for triggering RX processing and then TX processing if a single thread is used	  
-    threadCreate(&gNB->L1_rx_thread, L1_rx_thread, (void *)gNB, "L1_rx_thread",
-                 gNB->L1_rx_thread_core, OAI_PRIORITY_RT_MAX);
-    // if separate threads are used for RX and TX, create the TX thread
- // threadCreate(&gNB->L1_tx_thread, L1_tx_thread, (void *)gNB, "L1_tx_thread",
- //              gNB->L1_tx_thread_core, OAI_PRIORITY_RT_MAX);
+  initNotifiedFIFO(&gNB->L1_rx_out);
 
-    notifiedFIFO_elt_t *msgL1Tx = newNotifiedFIFO_elt(sizeof(processingData_L1tx_t), 0, &gNB->L1_tx_out, tx_func);
-    processingData_L1tx_t *msgDataTx = (processingData_L1tx_t *)NotifiedFifoData(msgL1Tx);
-    memset(msgDataTx, 0, sizeof(processingData_L1tx_t));
-    init_DLSCH_struct(gNB, msgDataTx);
-    memset(msgDataTx->ssb, 0, 64*sizeof(NR_gNB_SSB_t));
-    // this will be removed when the msgDataTx is not necessary anymore
-    gNB->msgDataTx = msgDataTx;
-  } else {
-    // we create 2 threads for L1 tx processing
-    for (int i=0; i < 2; i++) {
-      notifiedFIFO_elt_t *msgL1Tx = newNotifiedFIFO_elt(sizeof(processingData_L1tx_t), 0, &gNB->L1_tx_out, tx_func);
-      processingData_L1tx_t *msgDataTx = (processingData_L1tx_t *)NotifiedFifoData(msgL1Tx);
-      memset(msgDataTx, 0, sizeof(processingData_L1tx_t));
-      init_DLSCH_struct(gNB, msgDataTx);
-      memset(msgDataTx->ssb, 0, 64*sizeof(NR_gNB_SSB_t));
-      pushNotifiedFIFO(&gNB->L1_tx_free, msgL1Tx); // to unblock the process in the beginning
-    }
-  
-    LOG_I(PHY,"Creating thread for TX reordering and dispatching to RU\n");
-    threadCreate(&proc->pthread_tx_reorder, tx_reorder_thread, (void *)gNB, "thread_tx_reorder",
-                  gNB->RU_list[0] ? gNB->RU_list[0]->tpcores[1] : -1, OAI_PRIORITY_RT_MAX);
-  }
+  // create the RX thread responsible for RX processing start event (resp_L1 msg queue), then launch rx_func()
+  threadCreate(&gNB->L1_rx_thread, L1_rx_thread, (void *)gNB, "L1_rx_thread", gNB->L1_rx_thread_core, OAI_PRIORITY_RT_MAX);
+  // create the TX thread responsible for TX processing start event (L1_tx_out msg queue), then launch tx_func()
+  threadCreate(&gNB->L1_tx_thread, L1_tx_thread, (void *)gNB, "L1_tx_thread", gNB->L1_tx_thread_core, OAI_PRIORITY_RT_MAX);
+
+  notifiedFIFO_elt_t *msgL1Tx = newNotifiedFIFO_elt(sizeof(processingData_L1tx_t), 0, &gNB->L1_tx_out, tx_func);
+  processingData_L1tx_t *msgDataTx = (processingData_L1tx_t *)NotifiedFifoData(msgL1Tx);
+  memset(msgDataTx, 0, sizeof(processingData_L1tx_t));
+  init_DLSCH_struct(gNB, msgDataTx);
+  memset(msgDataTx->ssb, 0, 64 * sizeof(NR_gNB_SSB_t));
+  // this will be removed when the msgDataTx is not necessary anymore
+  gNB->msgDataTx = msgDataTx;
 
   if ((!get_softmodem_params()->emulate_l1) && (!IS_SOFTMODEM_NOSTATS_BIT) && (NFAPI_MODE!=NFAPI_MODE_VNF))
      threadCreate(&proc->L1_stats_thread,nrL1_stats_thread,(void*)gNB,"L1_stats",-1,OAI_PRIORITY_RT_LOW);
@@ -489,12 +405,11 @@ void term_gNB_Tpool(int inst) {
   abortNotifiedFIFO(&gNB->L1_tx_free);
   abortNotifiedFIFO(&gNB->L1_tx_filled);
   abortNotifiedFIFO(&gNB->L1_tx_out);
+  abortNotifiedFIFO(&gNB->L1_rx_out);
 
   gNB_L1_proc_t *proc = &gNB->proc;
   if (!get_softmodem_params()->emulate_l1)
     pthread_join(proc->L1_stats_thread, NULL);
-  if (!get_softmodem_params()->reorder_thread_disable)
-    pthread_join(proc->pthread_tx_reorder, NULL);
 }
 
 void reset_opp_meas(void) {
@@ -534,7 +449,6 @@ void init_eNB_afterRU(void) {
 
     gNB = RC.gNB[inst];
     gNB->ldpc_offload_flag = get_softmodem_params()->ldpc_offload_flag;
-    gNB->reorder_thread_disable = get_softmodem_params()->reorder_thread_disable;
 
     phy_init_nr_gNB(gNB);
 
diff --git a/executables/nr-ru.c b/executables/nr-ru.c
index 03ebab6b2e..413daf9fe0 100644
--- a/executables/nr-ru.c
+++ b/executables/nr-ru.c
@@ -624,7 +624,8 @@ void *emulatedRF_thread(void *param) {
   return 0;
 }
 
-void rx_rf(RU_t *ru,int *frame,int *slot) {
+static void rx_rf(RU_t *ru, int *frame, int *slot)
+{
   RU_proc_t *proc = &ru->proc;
   NR_DL_FRAME_PARMS *fp = ru->nr_frame_parms;
   openair0_config_t *cfg   = &ru->openair0_cfg;
@@ -662,13 +663,17 @@ void rx_rf(RU_t *ru,int *frame,int *slot) {
 
   //AssertFatal(rxs == fp->samples_per_subframe,
   //"rx_rf: Asked for %d samples, got %d from USRP\n",fp->samples_per_subframe,rxs);
-  if (rxs != samples_per_slot) LOG_E(PHY, "rx_rf: Asked for %d samples, got %d from USRP\n",samples_per_slot,rxs);
+  if (rxs != samples_per_slot)
+    LOG_E(PHY, "rx_rf: Asked for %d samples, got %d from USRP\n", samples_per_slot, rxs);
 
   if (proc->first_rx != 1) {
     samples_per_slot_prev = fp->get_samples_per_slot((*slot-1)%fp->slots_per_frame,fp);
 
     if (proc->timestamp_rx - old_ts != samples_per_slot_prev) {
-      LOG_D(PHY,"rx_rf: rfdevice timing drift of %"PRId64" samples (ts_off %"PRId64")\n",proc->timestamp_rx - old_ts - samples_per_slot_prev,ru->ts_offset);
+      LOG_D(PHY,
+            "rx_rf: rfdevice timing drift of %" PRId64 " samples (ts_off %" PRId64 ")\n",
+            proc->timestamp_rx - old_ts - samples_per_slot_prev,
+            ru->ts_offset);
       ru->ts_offset += (proc->timestamp_rx - old_ts - samples_per_slot_prev);
       proc->timestamp_rx = ts-ru->ts_offset;
     }
@@ -705,8 +710,14 @@ void rx_rf(RU_t *ru,int *frame,int *slot) {
     }
 
     if (proc->frame_rx != *frame) {
-      LOG_E(PHY,"Received Timestamp (%llu) doesn't correspond to the time we think it is (proc->frame_rx %d frame %d, proc->tti_rx %d, slot %d)\n",(long long unsigned int)proc->timestamp_rx,proc->frame_rx,
-            *frame,proc->tti_rx,*slot);
+      LOG_E(PHY,
+            "Received Timestamp (%llu) doesn't correspond to the time we think it is (proc->frame_rx %d frame %d, proc->tti_rx %d, "
+            "slot %d)\n",
+            (long long unsigned int)proc->timestamp_rx,
+            proc->frame_rx,
+            *frame,
+            proc->tti_rx,
+            *slot);
       exit_fun("Exiting");
     }
   } else {
@@ -1169,6 +1180,7 @@ void *ru_thread( void *param ) {
   int                initial_wait=0;
   int                opp_enabled0 = opp_enabled;
 
+  bool rx_tti_busy[RU_RX_SLOT_DEPTH] = {false};
   nfapi_nr_config_request_scf_t *cfg = &ru->config;
   // set default return value
   ru_thread_status = 0;
@@ -1233,9 +1245,6 @@ void *ru_thread( void *param ) {
   pthread_mutex_unlock(&RC.ru_mutex);
   wait_sync("ru_thread");
 
-  processingData_L1_t *syncMsg;
-  notifiedFIFO_elt_t *res;
-
   if(!emulate_rf) {
     // Start RF device if any
     if (ru->start_rf) {
@@ -1299,14 +1308,13 @@ void *ru_thread( void *param ) {
     if (ru->fh_south_in) ru->fh_south_in(ru,&frame,&slot);
     else AssertFatal(1==0, "No fronthaul interface at south port");
 
-
-    if (initial_wait == 1 && proc->frame_rx < 300 && ru->fh_south_in == rx_rf) {
-       if (proc->frame_rx>0 && ((proc->frame_rx % 100) == 0) && proc->tti_rx==0) {
-          LOG_I(PHY,"delay processing to let RX stream settle, frame %d (trials %d)\n",proc->frame_rx,ru->rx_fhaul.trials);
-          print_meas(&ru->rx_fhaul,"rx_fhaul",NULL,NULL);
-          reset_meas(&ru->rx_fhaul);
-       }
-       continue;
+    if (initial_wait == 1 && proc->frame_rx < 300) {
+      if (proc->frame_rx > 0 && ((proc->frame_rx % 100) == 0) && proc->tti_rx == 0) {
+        LOG_D(PHY, "delay processing to let RX stream settle, frame %d (trials %d)\n", proc->frame_rx, ru->rx_fhaul.trials);
+        print_meas(&ru->rx_fhaul, "rx_fhaul", NULL, NULL);
+        reset_meas(&ru->rx_fhaul);
+      }
+      continue;
     }
     if (proc->frame_rx>=300)  {
       initial_wait=0;
@@ -1314,15 +1322,14 @@ void *ru_thread( void *param ) {
     }
     if (initial_wait == 0 && ru->rx_fhaul.trials > 1000) {
         reset_meas(&ru->rx_fhaul);
-        /*if (ru->if_south == REMOTE_IF5) reset_meas(&ru->ifdevice.tx_fhaul);
-        else*/ reset_meas(&ru->tx_fhaul);
+        reset_meas(&ru->tx_fhaul);
     }
     proc->timestamp_tx = proc->timestamp_rx;
     int sl=proc->tti_tx;
     for (int slidx=0;slidx<ru->sl_ahead;slidx++)
        proc->timestamp_tx += fp->get_samples_per_slot((sl+slidx)%fp->slots_per_frame,fp);
-    proc->frame_tx     = (proc->tti_rx > (fp->slots_per_frame-1-(ru->sl_ahead))) ? (proc->frame_rx+1)&1023 : proc->frame_rx;
-    proc->tti_tx      = (proc->tti_rx + ru->sl_ahead)%fp->slots_per_frame;
+    proc->frame_tx = (proc->tti_rx > (fp->slots_per_frame - 1 - (ru->sl_ahead))) ? (proc->frame_rx + 1) & 1023 : proc->frame_rx;
+    proc->tti_tx = (proc->tti_rx + ru->sl_ahead) % fp->slots_per_frame;
     int absslot_rx = proc->timestamp_rx/fp->get_samples_per_slot(proc->tti_rx,fp);
     int rt_prof_idx = absslot_rx % RT_PROF_DEPTH;
     clock_gettime(CLOCK_MONOTONIC,&ru->rt_ru_profiling.return_RU_south_in[rt_prof_idx]);
@@ -1333,14 +1340,62 @@ void *ru_thread( void *param ) {
           RC.gNB[0]->proc.frame_rx,RC.gNB[0]->proc.slot_rx,
           RC.gNB[0]->proc.frame_tx);
 
-    if (ru->idx!=0) proc->frame_tx = (proc->frame_tx+proc->frame_offset)&1023;
+    if (ru->idx != 0)
+      proc->frame_tx = (proc->frame_tx + proc->frame_offset) & 1023;
 
+    LOG_D(NR_PHY, "In %d.%d: Checking L1 status\n", proc->frame_rx, proc->tti_rx);
+    for (int n = 0; n < RU_RX_SLOT_DEPTH; n++)
+      LOG_D(NR_PHY, "slot n %d => %d\n", n, rx_tti_busy[n]);
+    // handle potential race by blocking if rxdataF is being used by L1
+    // collect all pending msg in L1 return fifo to not down the memory is available (rx_tti_busy[slot] boolean array)
+    notifiedFIFO_elt_t *res = pollNotifiedFIFO(&gNB->L1_rx_out);
+    LOG_D(NR_PHY, "%d.%d Polling L1_rx_out %p\n", proc->frame_rx, proc->tti_rx, res);
+    while (res) {
+      processingData_L1_t *info = (processingData_L1_t *)NotifiedFifoData(res);
+      LOG_D(NR_PHY,
+            "%d.%d res %d.%d completed, clearing %d\n",
+            proc->frame_rx,
+            proc->tti_rx,
+            info->frame_rx,
+            info->slot_rx,
+            info->slot_rx % RU_RX_SLOT_DEPTH);
+
+      rx_tti_busy[info->slot_rx % RU_RX_SLOT_DEPTH] = false;
+      res = pollNotifiedFIFO(&gNB->L1_rx_out);
+    }
+    LOG_D(NR_PHY, "%d.%d Done polling\n", proc->frame_rx, proc->tti_rx);
     // do RX front-end processing (frequency-shift, dft) if needed
-    int slot_type = nr_slot_select(cfg,proc->frame_rx,proc->tti_rx);
-
+    int slot_type = nr_slot_select(cfg, proc->frame_rx, proc->tti_rx);
     if (slot_type == NR_UPLINK_SLOT || slot_type == NR_MIXED_SLOT) {
       if (ru->feprx) {
+        if (rx_tti_busy[proc->tti_rx % RU_RX_SLOT_DEPTH]) {
+          bool not_done = true;
+          LOG_D(NR_PHY, "%d.%d Waiting to access RX slot %d\n", proc->frame_rx, proc->tti_rx, proc->tti_rx % RU_RX_SLOT_DEPTH);
+          // now we block and wait our slot memory zone is freed from previous slot processing
+          // as we can get other slots ending, we loop on the queue
+          while (not_done) {
+            res = pullNotifiedFIFO(&gNB->L1_rx_out);
+            if (!res)
+              break;
+            processingData_L1_t *info = (processingData_L1_t *)NotifiedFifoData(res);
+            LOG_D(NR_PHY,
+                  "%d.%d Got access to RX slot %d.%d (%d)\n",
+                  proc->frame_rx,
+                  proc->tti_rx,
+                  info->frame_rx,
+                  info->slot_rx,
+                  proc->tti_rx % RU_RX_SLOT_DEPTH);
+            rx_tti_busy[info->slot_rx % RU_RX_SLOT_DEPTH] = false;
+            if ((info->slot_rx % RU_RX_SLOT_DEPTH) == (proc->tti_rx % RU_RX_SLOT_DEPTH))
+              not_done = false;
+          }
+          if (!res)
+            break;
+        }
         ru->feprx(ru,proc->tti_rx);
+        // set the tti that was generated to busy
+        LOG_D(NR_PHY, "Setting %d.%d (%d) to busy\n", proc->frame_rx, proc->tti_rx, proc->tti_rx % RU_RX_SLOT_DEPTH);
+        rx_tti_busy[proc->tti_rx % RU_RX_SLOT_DEPTH] = true;
         clock_gettime(CLOCK_MONOTONIC,&ru->rt_ru_profiling.return_RU_feprx[rt_prof_idx]);
         //LOG_M("rxdata.m","rxs",ru->common.rxdata[0],1228800,1,1);
         LOG_D(PHY,"RU proc: frame_rx = %d, tti_rx = %d\n", proc->frame_rx, proc->tti_rx);
@@ -1383,26 +1438,16 @@ void *ru_thread( void *param ) {
       }
     } // end if (slot_type == NR_UPLINK_SLOT || slot_type == NR_MIXED_SLOT) {
 
-    // At this point, all information for subframe has been received on FH interface
-    if (!get_softmodem_params()->reorder_thread_disable) {
-      res = pullTpool(&gNB->resp_L1, &gNB->threadPool);
-      if (res == NULL)
-        break; // Tpool has been stopped
-    } else  {
-      res=newNotifiedFIFO_elt(sizeof(processingData_L1_t),0, &gNB->resp_L1,NULL);
-    }
-    syncMsg = (processingData_L1_t *)NotifiedFifoData(res);
-    syncMsg->gNB = gNB;
-    syncMsg->frame_rx = proc->frame_rx;
-    syncMsg->slot_rx = proc->tti_rx;
-    syncMsg->frame_tx = proc->frame_tx;
-    syncMsg->slot_tx = proc->tti_tx;
-    syncMsg->timestamp_tx = proc->timestamp_tx;
-    res->key = proc->tti_rx;
-    if (!get_softmodem_params()->reorder_thread_disable) 
-      pushTpool(&gNB->threadPool, res);
-    else 
-      pushNotifiedFIFO(&gNB->resp_L1, res);
+    notifiedFIFO_elt_t *resTx = newNotifiedFIFO_elt(sizeof(processingData_L1tx_t), 0, &gNB->L1_tx_out, NULL);
+    processingData_L1tx_t *syncMsgTx = NotifiedFifoData(resTx);
+    syncMsgTx->gNB = gNB;
+    syncMsgTx->frame = proc->frame_tx;
+    syncMsgTx->slot = proc->tti_tx;
+    syncMsgTx->frame_rx = proc->frame_rx;
+    syncMsgTx->slot_rx = proc->tti_rx;
+    syncMsgTx->timestamp_tx = proc->timestamp_tx;
+    resTx->key = proc->tti_tx;
+    pushNotifiedFIFO(&gNB->L1_tx_out, resTx);
   }
 
   printf( "Exiting ru_thread \n");
diff --git a/executables/softmodem-common.h b/executables/softmodem-common.h
index b856bf252c..851e0b64b1 100644
--- a/executables/softmodem-common.h
+++ b/executables/softmodem-common.h
@@ -44,7 +44,6 @@ extern "C"
   example: -1,3 launches two working threads one floating, the second set on core 3\n\
   default 8 floating threads\n\
   use N for no pool (runs in calling thread) recommended with rfsim.\n"
-#define CONFIG_HLP_REORDER       "Disable reorder thread\n"
 #define CONFIG_HLP_ULMAXE        "set the eNodeB max ULSCH erros\n"
 #define CONFIG_HLP_CALUER        "set UE RX calibration\n"
 #define CONFIG_HLP_CALUERM       ""
@@ -147,7 +146,6 @@ extern "C"
 #define NID2                softmodem_params.nid2
 #define LDPC_OFFLOAD_FLAG   softmodem_params.ldpc_offload_flag
 
-#define REORDER_THREAD_DISABLE    softmodem_params.reorder_thread_disable
 #define DEFAULT_RFCONFIG_FILE    "/usr/local/etc/syriq/ue.band7.tm1.PRB100.NR40.dat";
 
 extern int usrp_tx_thread;
@@ -155,7 +153,6 @@ extern int usrp_tx_thread;
 #define CMDLINE_PARAMS_DESC {  \
   {"rf-config-file",        CONFIG_HLP_RFCFGF,        0,              .strptr=&RF_CONFIG_FILE,                .defstrval=NULL,          TYPE_STRING, 0},  \
   {"thread-pool",           CONFIG_HLP_TPOOL,         0,              .strptr=&TP_CONFIG,                     .defstrval="-1,-1,-1,-1,-1,-1,-1,-1",  TYPE_STRING, 0},     \
-  {"reorder-thread-disable",CONFIG_HLP_REORDER,     PARAMFLAG_BOOL,   .iptr=&REORDER_THREAD_DISABLE,          .defintval=0,                          TYPE_INT,    0},                     \
   {"phy-test",              CONFIG_HLP_PHYTST,        PARAMFLAG_BOOL, .iptr=&PHY_TEST,                        .defintval=0,             TYPE_INT,    0},  \
   {"do-ra",                 CONFIG_HLP_DORA,          PARAMFLAG_BOOL, .iptr=&DO_RA,                           .defintval=0,             TYPE_INT,    0},  \
   {"sa",                    CONFIG_HLP_SA,            PARAMFLAG_BOOL, .iptr=&SA,                              .defintval=0,             TYPE_INT,    0},  \
@@ -232,7 +229,6 @@ extern int usrp_tx_thread;
     { .s5 = { NULL } },                     \
     { .s5 = { NULL } },                     \
     { .s5 = { NULL } },                     \
-    { .s5 = { NULL } },                     \
     { .s3a = { config_checkstr_assign_integer, \
                {"MONOLITHIC", "PNF", "VNF","UE_STUB_PNF","UE_STUB_OFFNET","STANDALONE_PNF"}, \
                {NFAPI_MONOLITHIC, NFAPI_MODE_PNF, NFAPI_MODE_VNF,NFAPI_UE_STUB_PNF,NFAPI_UE_STUB_OFFNET,NFAPI_MODE_STANDALONE_PNF}, \
@@ -326,8 +322,7 @@ typedef struct {
   uint64_t       optmask;
   //THREAD_STRUCT  thread_struct;
   char           *rf_config_file;
-  char           *threadPoolConfig;
-  int            reorder_thread_disable;
+  char *threadPoolConfig;
   int            phy_test;
   int            do_ra;
   int            sa;
@@ -375,7 +370,6 @@ extern uint16_t sl_ahead;
 extern uint16_t sf_ahead;
 extern int oai_exit;
 
-void tx_func(void *param);
 void rx_func(void *param);
 void ru_tx_func(void *param);
 extern uint8_t nfapi_mode;
diff --git a/openair1/PHY/NR_TRANSPORT/nr_prach.c b/openair1/PHY/NR_TRANSPORT/nr_prach.c
index 5f534ef500..95c2c8040b 100644
--- a/openair1/PHY/NR_TRANSPORT/nr_prach.c
+++ b/openair1/PHY/NR_TRANSPORT/nr_prach.c
@@ -76,8 +76,7 @@ void nr_fill_prach(PHY_VARS_gNB *gNB,
 		   nfapi_nr_prach_pdu_t *prach_pdu) {
 
   int prach_id = find_nr_prach(gNB,SFN,Slot,SEARCH_EXIST_OR_FREE);
-  AssertFatal( ((prach_id>=0) && (prach_id<NUMBER_OF_NR_PRACH_MAX)) || (prach_id < 0),
-              "illegal or no prach_id found!!! prach_id %d\n",prach_id);
+  AssertFatal(((prach_id >= 0) && (prach_id < NUMBER_OF_NR_PRACH_MAX)), "illegal or no prach_id found!!! prach_id %d\n", prach_id);
 
   gNB->prach_vars.list[prach_id].frame=SFN;
   gNB->prach_vars.list[prach_id].slot=Slot;
diff --git a/openair1/PHY/NR_TRANSPORT/nr_ulsch.c b/openair1/PHY/NR_TRANSPORT/nr_ulsch.c
index 352967c7f5..7e7562ff22 100644
--- a/openair1/PHY/NR_TRANSPORT/nr_ulsch.c
+++ b/openair1/PHY/NR_TRANSPORT/nr_ulsch.c
@@ -74,8 +74,8 @@ void nr_fill_ulsch(PHY_VARS_gNB *gNB, int frame, int slot, nfapi_nr_pusch_pdu_t
   NR_UL_gNB_HARQ_t *harq = ulsch->harq_process;
   if (ulsch_pdu->pusch_data.new_data_indicator)
     harq->harq_to_be_cleared = true;
-  LOG_D(PHY,
-        "%d.%d RNTI %x HARQ PID %d new data indicator %d\n",
+  LOG_D(NR_PHY,
+        "NEW ULSCH %d.%d RNTI %x HARQ PID %d new data indicator %d\n",
         frame,
         slot,
         ulsch_pdu->rnti,
@@ -98,8 +98,17 @@ void reset_active_ulsch(PHY_VARS_gNB *gNB, int frame)
   // assuming UE disconnected or some other error occurred
   for (int i = 0; i < gNB->max_nb_pusch; i++) {
     NR_gNB_ULSCH_t *ulsch = &gNB->ulsch[i];
-    if (ulsch->active && (((frame - ulsch->frame + 1024) % 1024) > NUMBER_FRAMES_PHY_UE_INACTIVE))
+    int diff = (frame - ulsch->frame + 1024) & 1023;
+    if (ulsch->active && diff > NUMBER_FRAMES_PHY_UE_INACTIVE && diff < 100) {
       ulsch->active = false;
+      LOG_D(NR_PHY,
+            "Frame %d: resetting ulsch %d harq %d (programmed in %d.%d)\n",
+            frame,
+            i,
+            ulsch->harq_pid,
+            ulsch->frame,
+            ulsch->slot);
+    }
   }
 }
 
diff --git a/openair1/PHY/NR_TRANSPORT/nr_ulsch_demodulation.c b/openair1/PHY/NR_TRANSPORT/nr_ulsch_demodulation.c
index 217d6bbc88..c76365f4ac 100644
--- a/openair1/PHY/NR_TRANSPORT/nr_ulsch_demodulation.c
+++ b/openair1/PHY/NR_TRANSPORT/nr_ulsch_demodulation.c
@@ -1409,7 +1409,7 @@ static void nr_pusch_symbol_processing(void *arg)
 
     if (gNB->pusch_vars[ulsch_id].ul_valid_re_per_slot[symbol] == 0) 
       continue;
-    int soffset = (slot&3)*frame_parms->symbols_per_slot*frame_parms->ofdm_symbol_size;
+    int soffset = (slot % RU_RX_SLOT_DEPTH) * frame_parms->symbols_per_slot * frame_parms->ofdm_symbol_size;
     inner_rx(gNB,
              ulsch_id,
              slot,
@@ -1591,7 +1591,7 @@ int nr_rx_pusch_tp(PHY_VARS_gNB *gNB,
 
   // extract the first dmrs for the channel level computation
   // extract the data in the OFDM frame, to the start of the array
-  int soffset = (slot&3)*frame_parms->symbols_per_slot*frame_parms->ofdm_symbol_size;
+  int soffset = (slot % RU_RX_SLOT_DEPTH) * frame_parms->symbols_per_slot * frame_parms->ofdm_symbol_size;
 
   nb_re_pusch = (nb_re_pusch + 15) & ~15;
 
diff --git a/openair1/PHY/NR_TRANSPORT/pucch_rx.c b/openair1/PHY/NR_TRANSPORT/pucch_rx.c
index e878a3c0bb..35b5b1be3d 100644
--- a/openair1/PHY/NR_TRANSPORT/pucch_rx.c
+++ b/openair1/PHY/NR_TRANSPORT/pucch_rx.c
@@ -501,7 +501,7 @@ void nr_decode_pucch1(c16_t **rxdataF,
    * Implement TS 38.211 Subclause 6.3.2.4.1 Sequence modulation
    *
    */
-  const int soffset = (nr_tti_tx & 3) * frame_parms->symbols_per_slot * frame_parms->ofdm_symbol_size;
+  const int soffset = (nr_tti_tx % RU_RX_SLOT_DEPTH) * frame_parms->symbols_per_slot * frame_parms->ofdm_symbol_size;
   // lprime is the index of the OFDM symbol in the slot that corresponds to the first OFDM symbol of the PUCCH transmission in the slot given by [5, TS 38.213]
   const int lprime = startingSymbolIndex;
   // mcs = 0 except for PUCCH format 0
@@ -1021,14 +1021,10 @@ void nr_decode_pucch2(PHY_VARS_gNB *gNB,
   //extract pucch and dmrs first
 
   int l2 = pucch_pdu->start_symbol_index;
-
-  int soffset = (slot & 3) * frame_parms->symbols_per_slot * frame_parms->ofdm_symbol_size;
-
+  int soffset = (slot % RU_RX_SLOT_DEPTH) * frame_parms->symbols_per_slot * frame_parms->ofdm_symbol_size;
   int re_offset[2];
   re_offset[0] =
       (12 * (pucch_pdu->prb_start + pucch_pdu->bwp_start) + frame_parms->first_carrier_offset) % frame_parms->ofdm_symbol_size;
-  if (re_offset[0]>= frame_parms->ofdm_symbol_size)
-    re_offset[0]-=frame_parms->ofdm_symbol_size;
   if (pucch_pdu->freq_hop_flag == 0)
     re_offset[1] = re_offset[0];
   else {
diff --git a/openair1/PHY/NR_TRANSPORT/srs_rx.c b/openair1/PHY/NR_TRANSPORT/srs_rx.c
index 989c5cf044..12eb6edda9 100644
--- a/openair1/PHY/NR_TRANSPORT/srs_rx.c
+++ b/openair1/PHY/NR_TRANSPORT/srs_rx.c
@@ -34,6 +34,7 @@
 #include "PHY/impl_defs_nr.h"
 #include "PHY/defs_nr_common.h"
 #include "PHY/defs_gNB.h"
+#include "PHY/defs_RU.h"
 #include "PHY/CODING/nrSmallBlock/nr_small_block_defs.h"
 #include "PHY/NR_UE_TRANSPORT/srs_modulation_nr.h"
 #include "common/utils/LOG/log.h"
@@ -75,7 +76,7 @@ int nr_get_srs_signal(PHY_VARS_gNB *gNB,
   c16_t **rxdataF = gNB->common_vars.rxdataF;
   const NR_DL_FRAME_PARMS *frame_parms = &gNB->frame_parms;
 
-  const uint16_t n_symbols = (slot&3)*frame_parms->symbols_per_slot;                    // number of symbols until this slot
+  const uint16_t n_symbols = (slot % RU_RX_SLOT_DEPTH) * frame_parms->symbols_per_slot; // number of symbols until this slot
   const uint8_t l0 = frame_parms->symbols_per_slot - 1 - srs_pdu->time_start_position;  // starting symbol in this slot
   const uint64_t symbol_offset = (n_symbols+l0)*frame_parms->ofdm_symbol_size;
   const uint64_t subcarrier_offset = frame_parms->first_carrier_offset + srs_pdu->bwp_start*NR_NB_SC_PER_RB;
diff --git a/openair1/PHY/defs_RU.h b/openair1/PHY/defs_RU.h
index b8cc7ae84c..2f564eac6b 100644
--- a/openair1/PHY/defs_RU.h
+++ b/openair1/PHY/defs_RU.h
@@ -197,7 +197,7 @@ typedef struct {
 
 #define NUMBER_OF_NR_RU_PRACH_MAX 8
 #define NUMBER_OF_NR_RU_PRACH_OCCASIONS_MAX 12
-
+#define RU_RX_SLOT_DEPTH 4
 typedef struct RU_proc_t_s {
   /// Pointer to associated RU descriptor
   struct RU_t_s *ru;
diff --git a/openair1/PHY/defs_gNB.h b/openair1/PHY/defs_gNB.h
index 4132642a46..3afb47490b 100644
--- a/openair1/PHY/defs_gNB.h
+++ b/openair1/PHY/defs_gNB.h
@@ -639,8 +639,6 @@ typedef struct PHY_VARS_gNB_s {
 
   int ldpc_offload_flag;
 
-  int reorder_thread_disable;
-
   int max_ldpc_iterations;
   /// indicate the channel estimation technique in time domain
   int chest_time;
@@ -718,6 +716,7 @@ typedef struct PHY_VARS_gNB_s {
   notifiedFIFO_t L1_tx_free;
   notifiedFIFO_t L1_tx_filled;
   notifiedFIFO_t L1_tx_out;
+  notifiedFIFO_t L1_rx_out;
   notifiedFIFO_t resp_RU_tx;
   tpool_t threadPool;
   int nbSymb;
@@ -795,9 +794,7 @@ union ldpcReqUnion {
 
 typedef struct processingData_L1 {
   int frame_rx;
-  int frame_tx;
   int slot_rx;
-  int slot_tx;
   openair0_timestamp timestamp_tx;
   PHY_VARS_gNB *gNB;
 } processingData_L1_t;
@@ -811,6 +808,8 @@ typedef enum {
 typedef struct processingData_L1tx {
   int frame;
   int slot;
+  int frame_rx;
+  int slot_rx;
   openair0_timestamp timestamp_tx;
   PHY_VARS_gNB *gNB;
   nfapi_nr_dl_tti_pdcch_pdu pdcch_pdu[NFAPI_NR_MAX_NB_CORESETS];
@@ -825,4 +824,9 @@ typedef struct processingData_L1tx {
   int sched_response_id;
 } processingData_L1tx_t;
 
+typedef struct processingData_L1rx {
+  int frame_rx;
+  int slot_rx;
+  PHY_VARS_gNB *gNB;
+} processingData_L1rx_t;
 #endif
diff --git a/openair1/SCHED_NR/fapi_nr_l1.c b/openair1/SCHED_NR/fapi_nr_l1.c
index 979acf2343..23f22a9f2a 100644
--- a/openair1/SCHED_NR/fapi_nr_l1.c
+++ b/openair1/SCHED_NR/fapi_nr_l1.c
@@ -156,21 +156,9 @@ void nr_schedule_response(NR_Sched_Rsp_t *Sched_INFO)
   uint8_t number_tx_data_pdu        = (TX_req == NULL) ? 0 : TX_req->Number_of_PDUs;
 
   if (NFAPI_MODE == NFAPI_MONOLITHIC){
-
     if (slot_type == NR_DOWNLINK_SLOT || slot_type == NR_MIXED_SLOT) {
-      notifiedFIFO_elt_t *res=NULL;
       processingData_L1tx_t *msgTx=NULL;
-      if (!gNB->reorder_thread_disable) {
-        res = pullNotifiedFIFO(&gNB->L1_tx_free);
-        if (res == NULL)
-          return; // Tpool has been stopped, nothing to process
-        msgTx = (processingData_L1tx_t *)NotifiedFifoData(res);
-      } else {
-        msgTx = gNB->msgDataTx; //newNotifiedFIFO_elt(sizeof(processingData_L1tx_t),0, &gNB->L1_tx_out,NULL);
-      }
-      /*const time_stats_t ts = exec_time_stats_NotifiedFIFO(res);
-      merge_meas(&gNB->phy_proc_tx, &ts);
-*/
+      msgTx = gNB->msgDataTx;
       msgTx->num_pdsch_slot = 0;
       msgTx->num_dl_pdcch = 0;
       msgTx->num_ul_pdcch = number_ul_dci_pdu;
@@ -222,8 +210,6 @@ void nr_schedule_response(NR_Sched_Rsp_t *Sched_INFO)
        * released only when both threads are done with it.
        */
       inc_ref_sched_response(Sched_INFO->sched_response_id);
-      if (!gNB->reorder_thread_disable)
-	pushNotifiedFIFO(&gNB->L1_tx_filled,res);
     }
 
     for (int i = 0; i < number_ul_tti_pdu; i++) {
@@ -267,7 +253,9 @@ void nr_schedule_response(NR_Sched_Rsp_t *Sched_INFO)
   }
 
   /* this thread is done with the sched_info, decrease the reference counter */
-  deref_sched_response(Sched_INFO->sched_response_id);
-
+  if (slot_type == NR_DOWNLINK_SLOT || slot_type == NR_MIXED_SLOT) {
+    LOG_D(NR_PHY, "Calling dref_sched_response for id %d in %d.%d (sched_response)\n", Sched_INFO->sched_response_id, frame, slot);
+    deref_sched_response(Sched_INFO->sched_response_id);
+  }
   stop_meas(&gNB->schedule_response_stats);
 }
diff --git a/openair1/SCHED_NR/nr_ru_procedures.c b/openair1/SCHED_NR/nr_ru_procedures.c
index fbf89e5101..93619732ae 100644
--- a/openair1/SCHED_NR/nr_ru_procedures.c
+++ b/openair1/SCHED_NR/nr_ru_procedures.c
@@ -242,7 +242,7 @@ void nr_fep_full(RU_t *ru, int slot) {
 
   // remove_7_5_kHz(ru,proc->tti_rx<<1);
   // remove_7_5_kHz(ru,1+(proc->tti_rx<<1));
-  int offset = (proc->tti_rx&3)*(fp->symbols_per_slot * fp->ofdm_symbol_size);
+  int offset = (proc->tti_rx % RU_RX_SLOT_DEPTH) * (fp->symbols_per_slot * fp->ofdm_symbol_size);
   for (l = 0; l < fp->symbols_per_slot; l++) {
     for (aa = 0; aa < fp->nb_antennas_rx; aa++) {
       nr_slot_fep_ul(fp,
@@ -378,7 +378,7 @@ void nr_fep(void* arg) {
 
   VCD_SIGNAL_DUMPER_DUMP_FUNCTION_BY_NAME(VCD_SIGNAL_DUMPER_FUNCTIONS_PHY_PROCEDURES_RU_FEPRX+aid, 1);
 
-  int offset = (tti_rx&3) * fp->symbols_per_slot * fp->ofdm_symbol_size;
+  int offset = (tti_rx % RU_RX_SLOT_DEPTH) * fp->symbols_per_slot * fp->ofdm_symbol_size;
   for (int l = startSymbol; l <= endSymbol; l++) 
       nr_slot_fep_ul(fp,
                      ru->common.rxdata[aid],
diff --git a/openair1/SCHED_NR/phy_procedures_nr_gNB.c b/openair1/SCHED_NR/phy_procedures_nr_gNB.c
index 47c0821b7d..26cfbaa034 100644
--- a/openair1/SCHED_NR/phy_procedures_nr_gNB.c
+++ b/openair1/SCHED_NR/phy_procedures_nr_gNB.c
@@ -272,10 +272,11 @@ static void nr_postDecode(PHY_VARS_gNB *gNB, notifiedFIFO_elt_t *req)
     }
 
     if (crc_valid && !check_abort(&ulsch_harq->abort_decode) && !gNB->pusch_vars[rdata->ulsch_id].DTX) {
-      LOG_D(PHY,
-            "[gNB %d] ULSCH: Setting ACK for SFN/SF %d.%d (rnti %x, pid %d, ndi %d, status %d, round %d, TBS %d, Max interation "
+      LOG_D(NR_PHY,
+            "[gNB %d] ULSCH %d: Setting ACK for SFN/SF %d.%d (rnti %x, pid %d, ndi %d, status %d, round %d, TBS %d, Max interation "
             "(all seg) %d)\n",
             gNB->Mod_id,
+            rdata->ulsch_id,
             ulsch->frame,
             ulsch->slot,
             ulsch->rnti,
@@ -316,7 +317,7 @@ static void nr_postDecode(PHY_VARS_gNB *gNB, notifiedFIFO_elt_t *req)
         if (ulsch_harq->ulsch_pdu.mcs_index == 0 && dumpsig==1) {
           int off = ((ulsch_harq->ulsch_pdu.rb_size&1) == 1)? 4:0;
 
-          LOG_M("rxsigF0.m","rxsF0",&gNB->common_vars.rxdataF[0][(ulsch_harq->slot&3)*gNB->frame_parms.ofdm_symbol_size*gNB->frame_parms.symbols_per_slot],gNB->frame_parms.ofdm_symbol_size*gNB->frame_parms.symbols_per_slot,1,1);
+          LOG_M("rxsigF0.m","rxsF0",&gNB->common_vars.rxdataF[0][(ulsch_harq->slot%RU_RX_SLOT_DEPTH)*gNB->frame_parms.ofdm_symbol_size*gNB->frame_parms.symbols_per_slot],gNB->frame_parms.ofdm_symbol_size*gNB->frame_parms.symbols_per_slot,1,1);
           LOG_M("rxsigF0_ext.m","rxsF0_ext",
                  &gNB->pusch_vars[0].rxdataF_ext[0][ulsch_harq->ulsch_pdu.start_symbol_index*NR_NB_SC_PER_RB *
        ulsch_harq->ulsch_pdu.rb_size],ulsch_harq->ulsch_pdu.nr_of_symbols*(off+(NR_NB_SC_PER_RB *
@@ -410,9 +411,6 @@ static int nr_ulsch_procedures(PHY_VARS_gNB *gNB, int frame_rx, int slot_rx, int
 
 void nr_fill_indication(PHY_VARS_gNB *gNB, int frame, int slot_rx, int ULSCH_id, uint8_t harq_pid, uint8_t crc_flag, int dtx_flag)
 {
-  if (!get_softmodem_params()->reorder_thread_disable) 
-    pthread_mutex_lock(&gNB->UL_INFO_mutex);
-
   NR_gNB_ULSCH_t *ulsch = &gNB->ulsch[ULSCH_id];
   NR_UL_gNB_HARQ_t *harq_process = ulsch->harq_process;
   NR_gNB_PHY_STATS_t *stats = get_phy_stats(gNB, ulsch->rnti);
@@ -467,7 +465,13 @@ void nr_fill_indication(PHY_VARS_gNB *gNB, int frame, int slot_rx, int ULSCH_id,
       __attribute__((unused))
       int off = ((pusch_pdu->rb_size&1) == 1)? 4:0;
 
-      LOG_M("rxsigF0.m","rxsF0",&gNB->common_vars.rxdataF[0][(slot_rx&3)*gNB->frame_parms.ofdm_symbol_size*gNB->frame_parms.symbols_per_slot],gNB->frame_parms.ofdm_symbol_size*gNB->frame_parms.symbols_per_slot,1,1);
+      LOG_M("rxsigF0.m",
+            "rxsF0",
+            &gNB->common_vars
+                 .rxdataF[0][(slot_rx % RU_RX_SLOT_DEPTH) * gNB->frame_parms.ofdm_symbol_size * gNB->frame_parms.symbols_per_slot],
+            gNB->frame_parms.ofdm_symbol_size * gNB->frame_parms.symbols_per_slot,
+            1,
+            1);
       LOG_M("chestF0.m",
             "chF0",
             &gNB->pusch_vars[0].ul_ch_estimates[0][pusch_pdu->start_symbol_index * gNB->frame_parms.ofdm_symbol_size],
@@ -494,7 +498,14 @@ void nr_fill_indication(PHY_VARS_gNB *gNB, int frame, int slot_rx, int ULSCH_id,
             1,
             0);
       if (gNB->frame_parms.nb_antennas_rx > 1) {
-        LOG_M("rxsigF1.m","rxsF1",&gNB->common_vars.rxdataF[1][(slot_rx&3)*gNB->frame_parms.ofdm_symbol_size*gNB->frame_parms.symbols_per_slot],gNB->frame_parms.ofdm_symbol_size*gNB->frame_parms.symbols_per_slot,1,1);
+        LOG_M(
+            "rxsigF1.m",
+            "rxsF1",
+            &gNB->common_vars
+                 .rxdataF[1][(slot_rx % RU_RX_SLOT_DEPTH) * gNB->frame_parms.ofdm_symbol_size * gNB->frame_parms.symbols_per_slot],
+            gNB->frame_parms.ofdm_symbol_size * gNB->frame_parms.symbols_per_slot,
+            1,
+            1);
         LOG_M("chestF1.m",
               "chF1",
               &gNB->pusch_vars[0].ul_ch_estimates[1][pusch_pdu->start_symbol_index * gNB->frame_parms.ofdm_symbol_size],
@@ -557,9 +568,6 @@ void nr_fill_indication(PHY_VARS_gNB *gNB, int frame, int slot_rx, int ULSCH_id,
   }
 
   gNB->UL_INFO.rx_ind.number_of_pdus++;
-
-  if (!get_softmodem_params()->reorder_thread_disable) 
-    pthread_mutex_unlock(&gNB->UL_INFO_mutex);
 }
 
 // Function to fill UL RB mask to be used for N0 measurements
@@ -834,9 +842,9 @@ int phy_procedures_gNB_uespec_RX(PHY_VARS_gNB *gNB, int frame_rx, int slot_rx)
     NR_gNB_ULSCH_t *ulsch = &gNB->ulsch[ULSCH_id];
     NR_UL_gNB_HARQ_t *ulsch_harq = ulsch->harq_process;
     AssertFatal(ulsch_harq != NULL, "harq_pid %d is not allocated\n", ulsch->harq_pid);
-
     if ((ulsch->active == true) && (ulsch->frame == frame_rx) && (ulsch->slot == slot_rx) && (ulsch->handled == 0)) {
       LOG_D(PHY, "PUSCH ID %d with RNTI %x detection started in frame %d slot %d\n", ULSCH_id, ulsch->rnti, frame_rx, slot_rx);
+  
       int num_dmrs = 0;
       for (int s = 0; s < NR_NUMBER_OF_SYMBOLS_PER_SLOT; s++)
         num_dmrs += (ulsch_harq->ulsch_pdu.ul_dmrs_symb_pos >> s) & 1;
diff --git a/openair1/SIMULATION/NR_PHY/dlsim.c b/openair1/SIMULATION/NR_PHY/dlsim.c
index 5e6b8c5f45..9cfe4941cd 100644
--- a/openair1/SIMULATION/NR_PHY/dlsim.c
+++ b/openair1/SIMULATION/NR_PHY/dlsim.c
@@ -895,6 +895,7 @@ int main(int argc, char **argv)
   msgDataTx->slot = slot;
   msgDataTx->frame = frame;
   memset(msgDataTx->ssb, 0, 64*sizeof(NR_gNB_SSB_t));
+  gNB->msgDataTx = msgDataTx;
 
   // Buffers to store internal memory of slot process
   int rx_size = (((14 * frame_parms->N_RB_DL * 12 * sizeof(int32_t)) + 15) >> 4) << 4;
diff --git a/openair1/SIMULATION/NR_PHY/ulsim.c b/openair1/SIMULATION/NR_PHY/ulsim.c
index cc043c7974..05e8fa8e22 100644
--- a/openair1/SIMULATION/NR_PHY/ulsim.c
+++ b/openair1/SIMULATION/NR_PHY/ulsim.c
@@ -563,6 +563,7 @@ int main(int argc, char *argv[])
   notifiedFIFO_elt_t *msgL1Tx = newNotifiedFIFO_elt(sizeof(processingData_L1tx_t), 0, &gNB->L1_tx_free, NULL);
   processingData_L1tx_t *msgDataTx = (processingData_L1tx_t *)NotifiedFifoData(msgL1Tx);
   msgDataTx->slot = -1;
+  gNB->msgDataTx = msgDataTx;
   //gNB_config = &gNB->gNB_config;
 
   //memset((void *)&gNB->UL_INFO,0,sizeof(gNB->UL_INFO));
diff --git a/openair2/NR_PHY_INTERFACE/NR_IF_Module.c b/openair2/NR_PHY_INTERFACE/NR_IF_Module.c
index 86ef7247c5..37bedddf46 100644
--- a/openair2/NR_PHY_INTERFACE/NR_IF_Module.c
+++ b/openair2/NR_PHY_INTERFACE/NR_IF_Module.c
@@ -486,21 +486,6 @@ void NR_UL_indication(NR_UL_IND_t *UL_info) {
   if (get_softmodem_params()->emulate_l1) {
     free_unqueued_nfapi_indications(rach_ind, uci_ind, rx_ind, crc_ind);
   }
-
-  if (NFAPI_MODE != NFAPI_MODE_PNF) {
-    gNB_MAC_INST *mac = RC.nrmac[module_id];
-
-    NR_IF_Module_t *ifi = nr_if_inst[module_id];
-    ifi->current_frame = UL_info->frame;
-    ifi->current_slot = UL_info->slot;
-
-    nfapi_nr_config_request_scf_t *cfg = &mac->config[CC_id];
-    int spf = get_spf(cfg);
-    int CC_id = 0;
-    int frame_tx = UL_info->frame + ((UL_info->slot > (spf - 1 - ifi->sl_ahead)) ? 1 : 0);
-    int slot_tx = (UL_info->slot + ifi->sl_ahead) % spf;
-    ifi->NR_slot_indication(module_id, CC_id, frame_tx, slot_tx);
-  }
 }
 
 NR_IF_Module_t *NR_IF_Module_init(int Mod_id) {