ath11k: optimizations in data path

index de8b632..b6ffe03 100644
@@ -77,7 +77,7 @@ const struct ce_attr ath11k_host_ce_config_ipq8074[] = {
 
 	/* CE8: target autonomous hif_memcpy */
 	{
-		.flags = CE_ATTR_FLAGS,
+		.flags = CE_ATTR_FLAGS | CE_ATTR_DIS_INTR,
 		.src_nentries = 0,
 		.src_sz_max = 0,
 		.dest_nentries = 0,

index 969bf1a..298c4dc 100644
@@ -71,6 +71,7 @@ static const struct ath11k_hw_params ath11k_hw_params[] = {
 		.supports_suspend = false,
 		.hal_desc_sz = sizeof(struct hal_rx_desc_ipq8074),
 		.fix_l1ss = true,
+		.alloc_cacheable_memory = true,
 	},
 	{
 		.hw_rev = ATH11K_HW_IPQ6018_HW10,

@@ -112,6 +113,7 @@ static const struct ath11k_hw_params ath11k_hw_params[] = {
 		.supports_suspend = false,
 		.hal_desc_sz = sizeof(struct hal_rx_desc_ipq8074),
 		.fix_l1ss = true,
+		.alloc_cacheable_memory = true,
 	},
 	{
 		.name = "qca6390 hw2.0",

@@ -152,6 +154,7 @@ static const struct ath11k_hw_params ath11k_hw_params[] = {
 		.supports_suspend = true,
 		.hal_desc_sz = sizeof(struct hal_rx_desc_ipq8074),
 		.fix_l1ss = true,
+		.alloc_cacheable_memory = false,
 	},
 	{
 		.name = "qcn9074 hw1.0",

@@ -190,6 +193,7 @@ static const struct ath11k_hw_params ath11k_hw_params[] = {
 		.supports_suspend = false,
 		.hal_desc_sz = sizeof(struct hal_rx_desc_qcn9074),
 		.fix_l1ss = true,
+		.alloc_cacheable_memory = true,
 	},
 	{
 		.name = "wcn6855 hw2.0",

@@ -230,6 +234,7 @@ static const struct ath11k_hw_params ath11k_hw_params[] = {
 		.supports_suspend = true,
 		.hal_desc_sz = sizeof(struct hal_rx_desc_wcn6855),
 		.fix_l1ss = false,
+		.alloc_cacheable_memory = false,
 	},
 };
 

index b0c8f62..943d0a7 100644
@@ -101,8 +101,11 @@ void ath11k_dp_srng_cleanup(struct ath11k_base *ab, struct dp_srng *ring)
 	if (!ring->vaddr_unaligned)
 		return;
 
-	dma_free_coherent(ab->dev, ring->size, ring->vaddr_unaligned,
-			  ring->paddr_unaligned);
+	if (ring->cached)
+		kfree(ring->vaddr_unaligned);
+	else
+		dma_free_coherent(ab->dev, ring->size, ring->vaddr_unaligned,
+				  ring->paddr_unaligned);
 
 	ring->vaddr_unaligned = NULL;
 }

@@ -222,6 +225,7 @@ int ath11k_dp_srng_setup(struct ath11k_base *ab, struct dp_srng *ring,
 	int entry_sz = ath11k_hal_srng_get_entrysize(ab, type);
 	int max_entries = ath11k_hal_srng_get_max_entries(ab, type);
 	int ret;
+	bool cached = false;
 
 	if (max_entries < 0 || entry_sz < 0)
 		return -EINVAL;

@@ -230,9 +234,28 @@ int ath11k_dp_srng_setup(struct ath11k_base *ab, struct dp_srng *ring,
 		num_entries = max_entries;
 
 	ring->size = (num_entries * entry_sz) + HAL_RING_BASE_ALIGN - 1;
-	ring->vaddr_unaligned = dma_alloc_coherent(ab->dev, ring->size,
-						   &ring->paddr_unaligned,
-						   GFP_KERNEL);
+
+	if (ab->hw_params.alloc_cacheable_memory) {
+		/* Allocate the reo dst and tx completion rings from cacheable memory */
+		switch (type) {
+		case HAL_REO_DST:
+			cached = true;
+			break;
+		default:
+			cached = false;
+		}
+
+		if (cached) {
+			ring->vaddr_unaligned = kzalloc(ring->size, GFP_KERNEL);
+			ring->paddr_unaligned = virt_to_phys(ring->vaddr_unaligned);
+		}
+	}
+
+	if (!cached)
+		ring->vaddr_unaligned = dma_alloc_coherent(ab->dev, ring->size,
+							   &ring->paddr_unaligned,
+							   GFP_KERNEL);
+
 	if (!ring->vaddr_unaligned)
 		return -ENOMEM;
 

@@ -292,6 +315,11 @@ int ath11k_dp_srng_setup(struct ath11k_base *ab, struct dp_srng *ring,
 		return -EINVAL;
 	}
 
+	if (cached) {
+		params.flags |= HAL_SRNG_FLAGS_CACHED;
+		ring->cached = 1;
+	}
+
 	ret = ath11k_hal_srng_setup(ab, type, ring_num, mac_id, &params);
 	if (ret < 0) {
 		ath11k_warn(ab, "failed to setup srng: %d ring_id %d\n",

index ee768cc..e659148 100644
@@ -64,6 +64,7 @@ struct dp_srng {
 	dma_addr_t paddr;
 	int size;
 	u32 ring_id;
+	u8 cached;
 };
 
 struct dp_rxdma_ring {

index eaa0edc..f04edaf 100644
@@ -627,6 +627,21 @@ u32 *ath11k_hal_srng_dst_peek(struct ath11k_base *ab, struct hal_srng *srng)
 	return NULL;
 }
 
+static void ath11k_hal_srng_prefetch_desc(struct ath11k_base *ab,
+					  struct hal_srng *srng)
+{
+	u32 *desc;
+
+	/* prefetch only if desc is available */
+	desc = ath11k_hal_srng_dst_peek(ab, srng);
+	if (likely(desc)) {
+		dma_sync_single_for_cpu(ab->dev, virt_to_phys(desc),
+					(srng->entry_size * sizeof(u32)),
+					DMA_FROM_DEVICE);
+		prefetch(desc);
+	}
+}
+
 u32 *ath11k_hal_srng_dst_get_next_entry(struct ath11k_base *ab,
 					struct hal_srng *srng)
 {

@@ -642,6 +657,10 @@ u32 *ath11k_hal_srng_dst_get_next_entry(struct ath11k_base *ab,
 	srng->u.dst_ring.tp = (srng->u.dst_ring.tp + srng->entry_size) %
 			      srng->ring_size;
 
+	/* Try to prefetch the next descriptor in the ring */
+	if (srng->flags & HAL_SRNG_FLAGS_CACHED)
+		ath11k_hal_srng_prefetch_desc(ab, srng);
+
 	return desc;
 }
 

@@ -775,11 +794,16 @@ void ath11k_hal_srng_access_begin(struct ath11k_base *ab, struct hal_srng *srng)
 {
 	lockdep_assert_held(&srng->lock);
 
-	if (srng->ring_dir == HAL_SRNG_DIR_SRC)
+	if (srng->ring_dir == HAL_SRNG_DIR_SRC) {
 		srng->u.src_ring.cached_tp =
 			*(volatile u32 *)srng->u.src_ring.tp_addr;
-	else
+	} else {
 		srng->u.dst_ring.cached_hp = *srng->u.dst_ring.hp_addr;
+
+		/* Try to prefetch the next descriptor in the ring */
+		if (srng->flags & HAL_SRNG_FLAGS_CACHED)
+			ath11k_hal_srng_prefetch_desc(ab, srng);
+	}
 }
 
 /* Update cached ring head/tail pointers to HW. ath11k_hal_srng_access_begin()

index 35ed3a1..0f4f9ce 100644
@@ -513,6 +513,7 @@ enum hal_srng_dir {
 #define HAL_SRNG_FLAGS_DATA_TLV_SWAP		0x00000020
 #define HAL_SRNG_FLAGS_LOW_THRESH_INTR_EN	0x00010000
 #define HAL_SRNG_FLAGS_MSI_INTR			0x00020000
+#define HAL_SRNG_FLAGS_CACHED                   0x20000000
 #define HAL_SRNG_FLAGS_LMAC_RING		0x80000000
 
 #define HAL_SRNG_TLV_HDR_TAG		GENMASK(9, 1)

index 62f5978..7fe8edb 100644
@@ -163,6 +163,7 @@ struct ath11k_hw_params {
 	bool supports_suspend;
 	u32 hal_desc_sz;
 	bool fix_l1ss;
+	bool alloc_cacheable_memory;
 };
 
 struct ath11k_hw_ops {

index 9a22481..b84c2db 100644
@@ -20,13 +20,15 @@
 
 #define ATH11K_DP_RX_FRAGMENT_TIMEOUT_MS (2 * HZ)
 
-static u8 *ath11k_dp_rx_h_80211_hdr(struct ath11k_base *ab, struct hal_rx_desc *desc)
+static inline
+u8 *ath11k_dp_rx_h_80211_hdr(struct ath11k_base *ab, struct hal_rx_desc *desc)
 {
 	return ab->hw_params.hw_ops->rx_desc_get_hdr_status(desc);
 }
 
-static enum hal_encrypt_type ath11k_dp_rx_h_mpdu_start_enctype(struct ath11k_base *ab,
-							       struct hal_rx_desc *desc)
+static inline
+enum hal_encrypt_type ath11k_dp_rx_h_mpdu_start_enctype(struct ath11k_base *ab,
+							struct hal_rx_desc *desc)
 {
 	if (!ab->hw_params.hw_ops->rx_desc_encrypt_valid(desc))
 		return HAL_ENCRYPT_TYPE_OPEN;

@@ -34,32 +36,34 @@ static enum hal_encrypt_type ath11k_dp_rx_h_mpdu_start_enctype(struct ath11k_bas
 	return ab->hw_params.hw_ops->rx_desc_get_encrypt_type(desc);
 }
 
-static u8 ath11k_dp_rx_h_msdu_start_decap_type(struct ath11k_base *ab,
-					       struct hal_rx_desc *desc)
+static inline u8 ath11k_dp_rx_h_msdu_start_decap_type(struct ath11k_base *ab,
+						      struct hal_rx_desc *desc)
 {
 	return ab->hw_params.hw_ops->rx_desc_get_decap_type(desc);
 }
 
-static u8 ath11k_dp_rx_h_msdu_start_mesh_ctl_present(struct ath11k_base *ab,
-						     struct hal_rx_desc *desc)
+static inline
+u8 ath11k_dp_rx_h_msdu_start_mesh_ctl_present(struct ath11k_base *ab,
+					      struct hal_rx_desc *desc)
 {
 	return ab->hw_params.hw_ops->rx_desc_get_mesh_ctl(desc);
 }
 
-static bool ath11k_dp_rx_h_mpdu_start_seq_ctrl_valid(struct ath11k_base *ab,
-						     struct hal_rx_desc *desc)
+static inline
+bool ath11k_dp_rx_h_mpdu_start_seq_ctrl_valid(struct ath11k_base *ab,
+					      struct hal_rx_desc *desc)
 {
 	return ab->hw_params.hw_ops->rx_desc_get_mpdu_seq_ctl_vld(desc);
 }
 
-static bool ath11k_dp_rx_h_mpdu_start_fc_valid(struct ath11k_base *ab,
-					       struct hal_rx_desc *desc)
+static inline bool ath11k_dp_rx_h_mpdu_start_fc_valid(struct ath11k_base *ab,
+						      struct hal_rx_desc *desc)
 {
 	return ab->hw_params.hw_ops->rx_desc_get_mpdu_fc_valid(desc);
 }
 
-static bool ath11k_dp_rx_h_mpdu_start_more_frags(struct ath11k_base *ab,
-						 struct sk_buff *skb)
+static inline bool ath11k_dp_rx_h_mpdu_start_more_frags(struct ath11k_base *ab,
+							struct sk_buff *skb)
 {
 	struct ieee80211_hdr *hdr;
 

@@ -67,8 +71,8 @@ static bool ath11k_dp_rx_h_mpdu_start_more_frags(struct ath11k_base *ab,
 	return ieee80211_has_morefrags(hdr->frame_control);
 }
 
-static u16 ath11k_dp_rx_h_mpdu_start_frag_no(struct ath11k_base *ab,
-					     struct sk_buff *skb)
+static inline u16 ath11k_dp_rx_h_mpdu_start_frag_no(struct ath11k_base *ab,
+						    struct sk_buff *skb)
 {
 	struct ieee80211_hdr *hdr;
 

@@ -76,37 +80,37 @@ static u16 ath11k_dp_rx_h_mpdu_start_frag_no(struct ath11k_base *ab,
 	return le16_to_cpu(hdr->seq_ctrl) & IEEE80211_SCTL_FRAG;
 }
 
-static u16 ath11k_dp_rx_h_mpdu_start_seq_no(struct ath11k_base *ab,
-					    struct hal_rx_desc *desc)
+static inline u16 ath11k_dp_rx_h_mpdu_start_seq_no(struct ath11k_base *ab,
+						   struct hal_rx_desc *desc)
 {
 	return ab->hw_params.hw_ops->rx_desc_get_mpdu_start_seq_no(desc);
 }
 
-static void *ath11k_dp_rx_get_attention(struct ath11k_base *ab,
-					struct hal_rx_desc *desc)
+static inline void *ath11k_dp_rx_get_attention(struct ath11k_base *ab,
+					       struct hal_rx_desc *desc)
 {
 	return ab->hw_params.hw_ops->rx_desc_get_attention(desc);
 }
 
-static bool ath11k_dp_rx_h_attn_msdu_done(struct rx_attention *attn)
+static inline bool ath11k_dp_rx_h_attn_msdu_done(struct rx_attention *attn)
 {
 	return !!FIELD_GET(RX_ATTENTION_INFO2_MSDU_DONE,
 			   __le32_to_cpu(attn->info2));
 }
 
-static bool ath11k_dp_rx_h_attn_l4_cksum_fail(struct rx_attention *attn)
+static inline bool ath11k_dp_rx_h_attn_l4_cksum_fail(struct rx_attention *attn)
 {
 	return !!FIELD_GET(RX_ATTENTION_INFO1_TCP_UDP_CKSUM_FAIL,
 			   __le32_to_cpu(attn->info1));
 }
 
-static bool ath11k_dp_rx_h_attn_ip_cksum_fail(struct rx_attention *attn)
+static inline bool ath11k_dp_rx_h_attn_ip_cksum_fail(struct rx_attention *attn)
 {
 	return !!FIELD_GET(RX_ATTENTION_INFO1_IP_CKSUM_FAIL,
 			   __le32_to_cpu(attn->info1));
 }
 
-static bool ath11k_dp_rx_h_attn_is_decrypted(struct rx_attention *attn)
+static inline bool ath11k_dp_rx_h_attn_is_decrypted(struct rx_attention *attn)
 {
 	return (FIELD_GET(RX_ATTENTION_INFO2_DCRYPT_STATUS_CODE,
 			  __le32_to_cpu(attn->info2)) ==

@@ -142,68 +146,68 @@ static u32 ath11k_dp_rx_h_attn_mpdu_err(struct rx_attention *attn)
 	return errmap;
 }
 
-static u16 ath11k_dp_rx_h_msdu_start_msdu_len(struct ath11k_base *ab,
-					      struct hal_rx_desc *desc)
+static inline u16 ath11k_dp_rx_h_msdu_start_msdu_len(struct ath11k_base *ab,
+						     struct hal_rx_desc *desc)
 {
 	return ab->hw_params.hw_ops->rx_desc_get_msdu_len(desc);
 }
 
-static u8 ath11k_dp_rx_h_msdu_start_sgi(struct ath11k_base *ab,
-					struct hal_rx_desc *desc)
+static inline u8 ath11k_dp_rx_h_msdu_start_sgi(struct ath11k_base *ab,
+					       struct hal_rx_desc *desc)
 {
 	return ab->hw_params.hw_ops->rx_desc_get_msdu_sgi(desc);
 }
 
-static u8 ath11k_dp_rx_h_msdu_start_rate_mcs(struct ath11k_base *ab,
-					     struct hal_rx_desc *desc)
+static inline u8 ath11k_dp_rx_h_msdu_start_rate_mcs(struct ath11k_base *ab,
+						    struct hal_rx_desc *desc)
 {
 	return ab->hw_params.hw_ops->rx_desc_get_msdu_rate_mcs(desc);
 }
 
-static u8 ath11k_dp_rx_h_msdu_start_rx_bw(struct ath11k_base *ab,
-					  struct hal_rx_desc *desc)
+static inline u8 ath11k_dp_rx_h_msdu_start_rx_bw(struct ath11k_base *ab,
+						 struct hal_rx_desc *desc)
 {
 	return ab->hw_params.hw_ops->rx_desc_get_msdu_rx_bw(desc);
 }
 
-static u32 ath11k_dp_rx_h_msdu_start_freq(struct ath11k_base *ab,
-					  struct hal_rx_desc *desc)
+static inline u32 ath11k_dp_rx_h_msdu_start_freq(struct ath11k_base *ab,
+						 struct hal_rx_desc *desc)
 {
 	return ab->hw_params.hw_ops->rx_desc_get_msdu_freq(desc);
 }
 
-static u8 ath11k_dp_rx_h_msdu_start_pkt_type(struct ath11k_base *ab,
-					     struct hal_rx_desc *desc)
+static inline u8 ath11k_dp_rx_h_msdu_start_pkt_type(struct ath11k_base *ab,
+						    struct hal_rx_desc *desc)
 {
 	return ab->hw_params.hw_ops->rx_desc_get_msdu_pkt_type(desc);
 }
 
-static u8 ath11k_dp_rx_h_msdu_start_nss(struct ath11k_base *ab,
-					struct hal_rx_desc *desc)
+static inline u8 ath11k_dp_rx_h_msdu_start_nss(struct ath11k_base *ab,
+					       struct hal_rx_desc *desc)
 {
 	return hweight8(ab->hw_params.hw_ops->rx_desc_get_msdu_nss(desc));
 }
 
-static u8 ath11k_dp_rx_h_mpdu_start_tid(struct ath11k_base *ab,
-					struct hal_rx_desc *desc)
+static inline u8 ath11k_dp_rx_h_mpdu_start_tid(struct ath11k_base *ab,
+					       struct hal_rx_desc *desc)
 {
 	return ab->hw_params.hw_ops->rx_desc_get_mpdu_tid(desc);
 }
 
-static u16 ath11k_dp_rx_h_mpdu_start_peer_id(struct ath11k_base *ab,
-					     struct hal_rx_desc *desc)
+static inline u16 ath11k_dp_rx_h_mpdu_start_peer_id(struct ath11k_base *ab,
+						    struct hal_rx_desc *desc)
 {
 	return ab->hw_params.hw_ops->rx_desc_get_mpdu_peer_id(desc);
 }
 
-static u8 ath11k_dp_rx_h_msdu_end_l3pad(struct ath11k_base *ab,
-					struct hal_rx_desc *desc)
+static inline u8 ath11k_dp_rx_h_msdu_end_l3pad(struct ath11k_base *ab,
+					       struct hal_rx_desc *desc)
 {
 	return ab->hw_params.hw_ops->rx_desc_get_l3_pad_bytes(desc);
 }
 
-static bool ath11k_dp_rx_h_msdu_end_first_msdu(struct ath11k_base *ab,
-					       struct hal_rx_desc *desc)
+static inline bool ath11k_dp_rx_h_msdu_end_first_msdu(struct ath11k_base *ab,
+						      struct hal_rx_desc *desc)
 {
 	return ab->hw_params.hw_ops->rx_desc_get_first_msdu(desc);
 }

@@ -221,14 +225,14 @@ static void ath11k_dp_rx_desc_end_tlv_copy(struct ath11k_base *ab,
 	ab->hw_params.hw_ops->rx_desc_copy_attn_end_tlv(fdesc, ldesc);
 }
 
-static u32 ath11k_dp_rxdesc_get_mpdulen_err(struct rx_attention *attn)
+static inline u32 ath11k_dp_rxdesc_get_mpdulen_err(struct rx_attention *attn)
 {
 	return FIELD_GET(RX_ATTENTION_INFO1_MPDU_LEN_ERR,
 			 __le32_to_cpu(attn->info1));
 }
 
-static u8 *ath11k_dp_rxdesc_get_80211hdr(struct ath11k_base *ab,
-					 struct hal_rx_desc *rx_desc)
+static inline u8 *ath11k_dp_rxdesc_get_80211hdr(struct ath11k_base *ab,
+						struct hal_rx_desc *rx_desc)
 {
 	u8 *rx_pkt_hdr;
 

@@ -237,8 +241,8 @@ static u8 *ath11k_dp_rxdesc_get_80211hdr(struct ath11k_base *ab,
 	return rx_pkt_hdr;
 }
 
-static bool ath11k_dp_rxdesc_mpdu_valid(struct ath11k_base *ab,
-					struct hal_rx_desc *rx_desc)
+static inline bool ath11k_dp_rxdesc_mpdu_valid(struct ath11k_base *ab,
+					       struct hal_rx_desc *rx_desc)
 {
 	u32 tlv_tag;
 

@@ -247,15 +251,15 @@ static bool ath11k_dp_rxdesc_mpdu_valid(struct ath11k_base *ab,
 	return tlv_tag == HAL_RX_MPDU_START;
 }
 
-static u32 ath11k_dp_rxdesc_get_ppduid(struct ath11k_base *ab,
-				       struct hal_rx_desc *rx_desc)
+static inline u32 ath11k_dp_rxdesc_get_ppduid(struct ath11k_base *ab,
+					      struct hal_rx_desc *rx_desc)
 {
 	return ab->hw_params.hw_ops->rx_desc_get_mpdu_ppdu_id(rx_desc);
 }
 
-static void ath11k_dp_rxdesc_set_msdu_len(struct ath11k_base *ab,
-					  struct hal_rx_desc *desc,
-					  u16 len)
+static inline void ath11k_dp_rxdesc_set_msdu_len(struct ath11k_base *ab,
+						 struct hal_rx_desc *desc,
+						 u16 len)
 {
 	ab->hw_params.hw_ops->rx_desc_set_msdu_len(desc, len);
 }

index b84c2db..994959b 100644
@@ -2623,7 +2623,6 @@ int ath11k_dp_process_rx(struct ath11k_base *ab, int ring_id,
 				 DMA_FROM_DEVICE);
 
 		num_buffs_reaped[mac_id]++;
-		total_msdu_reaped++;
 
 		push_reason = FIELD_GET(HAL_REO_DEST_RING_INFO0_PUSH_REASON,
 					desc.info0);

@@ -2646,10 +2645,15 @@ int ath11k_dp_process_rx(struct ath11k_base *ab, int ring_id,
 
 		__skb_queue_tail(&msdu_list, msdu);
 
-		if (total_msdu_reaped >= quota && !rxcb->is_continuation) {
+		if (rxcb->is_continuation) {
+			done = false;
+		} else {
+			total_msdu_reaped++;
 			done = true;
-			break;
 		}
+
+		if (total_msdu_reaped >= budget)
+			break;
 	}
 
 	/* Hw might have updated the head pointer after we cached it.

index 994959b..1d85e10 100644
@@ -2523,12 +2523,10 @@ static int ath11k_dp_rx_process_msdu(struct ath11k *ar,
 static void ath11k_dp_rx_process_received_packets(struct ath11k_base *ab,
 						  struct napi_struct *napi,
 						  struct sk_buff_head *msdu_list,
-						  int *quota, int ring_id)
+						  int *quota, int mac_id)
 {
-	struct ath11k_skb_rxcb *rxcb;
 	struct sk_buff *msdu;
 	struct ath11k *ar;
-	u8 mac_id;
 	int ret;
 
 	if (skb_queue_empty(msdu_list))

@@ -2536,20 +2534,20 @@ static void ath11k_dp_rx_process_received_packets(struct ath11k_base *ab,
 
 	rcu_read_lock();
 
-	while (*quota && (msdu = __skb_dequeue(msdu_list))) {
-		rxcb = ATH11K_SKB_RXCB(msdu);
-		mac_id = rxcb->mac_id;
-		ar = ab->pdevs[mac_id].ar;
-		if (!rcu_dereference(ab->pdevs_active[mac_id])) {
-			dev_kfree_skb_any(msdu);
-			continue;
-		}
+	ar = ab->pdevs[mac_id].ar;
+	if (!rcu_dereference(ab->pdevs_active[mac_id])) {
+		__skb_queue_purge(msdu_list);
+		rcu_read_unlock();
+		return;
+	}
 
-		if (test_bit(ATH11K_CAC_RUNNING, &ar->dev_flags)) {
-			dev_kfree_skb_any(msdu);
-			continue;
-		}
+	if (test_bit(ATH11K_CAC_RUNNING, &ar->dev_flags)) {
+		__skb_queue_purge(msdu_list);
+		rcu_read_unlock();
+		return;
+	}
 
+	while ((msdu = __skb_dequeue(msdu_list))) {
 		ret = ath11k_dp_rx_process_msdu(ar, msdu, msdu_list);
 		if (ret) {
 			ath11k_dbg(ab, ATH11K_DBG_DATA,

@@ -2571,7 +2569,7 @@ int ath11k_dp_process_rx(struct ath11k_base *ab, int ring_id,
 	struct ath11k_dp *dp = &ab->dp;
 	struct dp_rxdma_ring *rx_ring;
 	int num_buffs_reaped[MAX_RADIOS] = {0};
-	struct sk_buff_head msdu_list;
+	struct sk_buff_head msdu_list[MAX_RADIOS];
 	struct ath11k_skb_rxcb *rxcb;
 	int total_msdu_reaped = 0;
 	struct hal_srng *srng;

@@ -2580,10 +2578,13 @@ int ath11k_dp_process_rx(struct ath11k_base *ab, int ring_id,
 	bool done = false;
 	int buf_id, mac_id;
 	struct ath11k *ar;
-	u32 *rx_desc;
+	struct hal_reo_dest_ring *desc;
+	enum hal_reo_dest_ring_push_reason push_reason;
+	u32 cookie;
 	int i;
 
-	__skb_queue_head_init(&msdu_list);
+	for (i = 0; i < MAX_RADIOS; i++)
+		__skb_queue_head_init(&msdu_list[i]);
 
 	srng = &ab->hal.srng_list[dp->reo_dst_ring[ring_id].ring_id];
 

@@ -2592,13 +2593,11 @@ int ath11k_dp_process_rx(struct ath11k_base *ab, int ring_id,
 	ath11k_hal_srng_access_begin(ab, srng);
 
 try_again:
-	while ((rx_desc = ath11k_hal_srng_dst_get_next_entry(ab, srng))) {
-		struct hal_reo_dest_ring desc = *(struct hal_reo_dest_ring *)rx_desc;
-		enum hal_reo_dest_ring_push_reason push_reason;
-		u32 cookie;
-
+	while (likely(desc =
+	      (struct hal_reo_dest_ring *)ath11k_hal_srng_dst_get_next_entry(ab,
+									     srng))) {
 		cookie = FIELD_GET(BUFFER_ADDR_INFO1_SW_COOKIE,
-				   desc.buf_addr_info.info1);
+				   desc->buf_addr_info.info1);
 		buf_id = FIELD_GET(DP_RXDMA_BUF_COOKIE_BUF_ID,
 				   cookie);
 		mac_id = FIELD_GET(DP_RXDMA_BUF_COOKIE_PDEV_ID, cookie);

@@ -2625,7 +2624,7 @@ int ath11k_dp_process_rx(struct ath11k_base *ab, int ring_id,
 		num_buffs_reaped[mac_id]++;
 
 		push_reason = FIELD_GET(HAL_REO_DEST_RING_INFO0_PUSH_REASON,
-					desc.info0);
+					desc->info0);
 		if (push_reason !=
 		    HAL_REO_DEST_RING_PUSH_REASON_ROUTING_INSTRUCTION) {
 			dev_kfree_skb_any(msdu);

@@ -2633,17 +2632,17 @@ int ath11k_dp_process_rx(struct ath11k_base *ab, int ring_id,
 			continue;
 		}
 
-		rxcb->is_first_msdu = !!(desc.rx_msdu_info.info0 &
+		rxcb->is_first_msdu = !!(desc->rx_msdu_info.info0 &
 					 RX_MSDU_DESC_INFO0_FIRST_MSDU_IN_MPDU);
-		rxcb->is_last_msdu = !!(desc.rx_msdu_info.info0 &
+		rxcb->is_last_msdu = !!(desc->rx_msdu_info.info0 &
 					RX_MSDU_DESC_INFO0_LAST_MSDU_IN_MPDU);
-		rxcb->is_continuation = !!(desc.rx_msdu_info.info0 &
+		rxcb->is_continuation = !!(desc->rx_msdu_info.info0 &
 					   RX_MSDU_DESC_INFO0_MSDU_CONTINUATION);
 		rxcb->mac_id = mac_id;
 		rxcb->tid = FIELD_GET(HAL_REO_DEST_RING_INFO0_RX_QUEUE_NUM,
-				      desc.info0);
+				      desc->info0);
 
-		__skb_queue_tail(&msdu_list, msdu);
+		__skb_queue_tail(&msdu_list[mac_id], msdu);
 
 		if (rxcb->is_continuation) {
 			done = false;

@@ -2678,16 +2677,15 @@ int ath11k_dp_process_rx(struct ath11k_base *ab, int ring_id,
 		if (!num_buffs_reaped[i])
 			continue;
 
+		ath11k_dp_rx_process_received_packets(ab, napi, &msdu_list[i],
+						      &quota, i);
+
 		ar = ab->pdevs[i].ar;
 		rx_ring = &ar->dp.rx_refill_buf_ring;
 
 		ath11k_dp_rxbufs_replenish(ab, i, rx_ring, num_buffs_reaped[i],
 					   HAL_RX_BUF_RBM_SW3_BM);
 	}
-
-	ath11k_dp_rx_process_received_packets(ab, napi, &msdu_list,
-					      &quota, ring_id);
-
 exit:
 	return budget - quota;
 }

index 1d85e10..e105bdc 100644
@@ -2523,7 +2523,7 @@ static int ath11k_dp_rx_process_msdu(struct ath11k *ar,
 static void ath11k_dp_rx_process_received_packets(struct ath11k_base *ab,
 						  struct napi_struct *napi,
 						  struct sk_buff_head *msdu_list,
-						  int *quota, int mac_id)
+						  int mac_id)
 {
 	struct sk_buff *msdu;
 	struct ath11k *ar;

@@ -2557,7 +2557,6 @@ static void ath11k_dp_rx_process_received_packets(struct ath11k_base *ab,
 		}
 
 		ath11k_dp_rx_deliver_msdu(ar, napi, msdu);
-		(*quota)--;
 	}
 
 	rcu_read_unlock();

@@ -2574,7 +2573,6 @@ int ath11k_dp_process_rx(struct ath11k_base *ab, int ring_id,
 	int total_msdu_reaped = 0;
 	struct hal_srng *srng;
 	struct sk_buff *msdu;
-	int quota = budget;
 	bool done = false;
 	int buf_id, mac_id;
 	struct ath11k *ar;

@@ -2677,8 +2675,7 @@ int ath11k_dp_process_rx(struct ath11k_base *ab, int ring_id,
 		if (!num_buffs_reaped[i])
 			continue;
 
-		ath11k_dp_rx_process_received_packets(ab, napi, &msdu_list[i],
-						      &quota, i);
+		ath11k_dp_rx_process_received_packets(ab, napi, &msdu_list[i], i);
 
 		ar = ab->pdevs[i].ar;
 		rx_ring = &ar->dp.rx_refill_buf_ring;

@@ -2687,7 +2684,7 @@ int ath11k_dp_process_rx(struct ath11k_base *ab, int ring_id,
 					   HAL_RX_BUF_RBM_SW3_BM);
 	}
 exit:
-	return budget - quota;
+	return total_msdu_reaped;
 }
 
 static void ath11k_dp_rx_update_peer_stats(struct ath11k_sta *arsta,

index e105bdc..a362615 100644
@@ -2532,24 +2532,20 @@ static void ath11k_dp_rx_process_received_packets(struct ath11k_base *ab,
 	if (skb_queue_empty(msdu_list))
 		return;
 
-	rcu_read_lock();
-
-	ar = ab->pdevs[mac_id].ar;
-	if (!rcu_dereference(ab->pdevs_active[mac_id])) {
+	if (unlikely(!rcu_access_pointer(ab->pdevs_active[mac_id]))) {
 		__skb_queue_purge(msdu_list);
-		rcu_read_unlock();
 		return;
 	}
 
-	if (test_bit(ATH11K_CAC_RUNNING, &ar->dev_flags)) {
+	ar = ab->pdevs[mac_id].ar;
+	if (unlikely(test_bit(ATH11K_CAC_RUNNING, &ar->dev_flags))) {
 		__skb_queue_purge(msdu_list);
-		rcu_read_unlock();
 		return;
 	}
 
 	while ((msdu = __skb_dequeue(msdu_list))) {
 		ret = ath11k_dp_rx_process_msdu(ar, msdu, msdu_list);
-		if (ret) {
+		if (unlikely(ret)) {
 			ath11k_dbg(ab, ATH11K_DBG_DATA,
 				   "Unable to process msdu %d", ret);
 			dev_kfree_skb_any(msdu);

@@ -2558,8 +2554,6 @@ static void ath11k_dp_rx_process_received_packets(struct ath11k_base *ab,
 
 		ath11k_dp_rx_deliver_msdu(ar, napi, msdu);
 	}
-
-	rcu_read_unlock();
 }
 
 int ath11k_dp_process_rx(struct ath11k_base *ab, int ring_id,

@@ -2604,7 +2598,7 @@ int ath11k_dp_process_rx(struct ath11k_base *ab, int ring_id,
 		rx_ring = &ar->dp.rx_refill_buf_ring;
 		spin_lock_bh(&rx_ring->idr_lock);
 		msdu = idr_find(&rx_ring->bufs_idr, buf_id);
-		if (!msdu) {
+		if (unlikely(!msdu)) {
 			ath11k_warn(ab, "frame rx with invalid buf_id %d\n",
 				    buf_id);
 			spin_unlock_bh(&rx_ring->idr_lock);

@@ -2623,8 +2617,8 @@ int ath11k_dp_process_rx(struct ath11k_base *ab, int ring_id,
 
 		push_reason = FIELD_GET(HAL_REO_DEST_RING_INFO0_PUSH_REASON,
 					desc->info0);
-		if (push_reason !=
-		    HAL_REO_DEST_RING_PUSH_REASON_ROUTING_INSTRUCTION) {
+		if (unlikely(push_reason !=
+			     HAL_REO_DEST_RING_PUSH_REASON_ROUTING_INSTRUCTION)) {
 			dev_kfree_skb_any(msdu);
 			ab->soc_stats.hal_reo_error[dp->reo_dst_ring[ring_id].ring_id]++;
 			continue;

@@ -2659,7 +2653,7 @@ int ath11k_dp_process_rx(struct ath11k_base *ab, int ring_id,
 	 * head pointer so that we can reap complete MPDU in the current
 	 * rx processing.
 	 */
-	if (!done && ath11k_hal_srng_dst_num_free(ab, srng, true)) {
+	if (unlikely(!done && ath11k_hal_srng_dst_num_free(ab, srng, true))) {
 		ath11k_hal_srng_access_end(ab, srng);
 		goto try_again;
 	}

@@ -2668,7 +2662,7 @@ int ath11k_dp_process_rx(struct ath11k_base *ab, int ring_id,
 
 	spin_unlock_bh(&srng->lock);
 
-	if (!total_msdu_reaped)
+	if (unlikely(!total_msdu_reaped))
 		goto exit;
 
 	for (i = 0; i < ab->num_radios; i++) {

index 943d0a7..0278ff6 100644
@@ -239,6 +239,7 @@ int ath11k_dp_srng_setup(struct ath11k_base *ab, struct dp_srng *ring,
 		/* Allocate the reo dst and tx completion rings from cacheable memory */
 		switch (type) {
 		case HAL_REO_DST:
+		case HAL_WBM2SW_RELEASE:
 			cached = true;
 			break;
 		default:

index f04edaf..7cf9e23 100644
@@ -654,8 +654,11 @@ u32 *ath11k_hal_srng_dst_get_next_entry(struct ath11k_base *ab,
 
 	desc = srng->ring_base_vaddr + srng->u.dst_ring.tp;
 
-	srng->u.dst_ring.tp = (srng->u.dst_ring.tp + srng->entry_size) %
-			      srng->ring_size;
+	srng->u.dst_ring.tp += srng->entry_size;
+
+	/* wrap around to start of ring*/
+	if (srng->u.dst_ring.tp == srng->ring_size)
+		srng->u.dst_ring.tp = 0;
 
 	/* Try to prefetch the next descriptor in the ring */
 	if (srng->flags & HAL_SRNG_FLAGS_CACHED)

index 0278ff6..d553692 100644
@@ -770,13 +770,12 @@ int ath11k_dp_service_srng(struct ath11k_base *ab,
 	struct napi_struct *napi = &irq_grp->napi;
 	int grp_id = irq_grp->grp_id;
 	int work_done = 0;
-	int i = 0, j;
+	int i, j;
 	int tot_work_done = 0;
 
-	while (ab->hw_params.ring_mask->tx[grp_id] >> i) {
-		if (ab->hw_params.ring_mask->tx[grp_id] & BIT(i))
-			ath11k_dp_tx_completion_handler(ab, i);
-		i++;
+	if (ab->hw_params.ring_mask->tx[grp_id]) {
+		i = __fls(ab->hw_params.ring_mask->tx[grp_id]);
+		ath11k_dp_tx_completion_handler(ab, i);
 	}
 
 	if (ab->hw_params.ring_mask->rx_err[grp_id]) {

index 8bba523..602184b 100644
@@ -95,11 +95,11 @@ int ath11k_dp_tx(struct ath11k *ar, struct ath11k_vif *arvif,
 	u8 ring_selector = 0, ring_map = 0;
 	bool tcl_ring_retry;
 
-	if (test_bit(ATH11K_FLAG_CRASH_FLUSH, &ar->ab->dev_flags))
+	if (unlikely(test_bit(ATH11K_FLAG_CRASH_FLUSH, &ar->ab->dev_flags)))
 		return -ESHUTDOWN;
 
-	if (!(info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP) &&
-	    !ieee80211_is_data(hdr->frame_control))
+	if (unlikely(!(info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP) &&
+		     !ieee80211_is_data(hdr->frame_control)))
 		return -ENOTSUPP;
 
 	pool_id = skb_get_queue_mapping(skb) & (ATH11K_HW_MAX_QUEUES - 1);

@@ -130,7 +130,7 @@ int ath11k_dp_tx(struct ath11k *ar, struct ath11k_vif *arvif,
 			DP_TX_IDR_SIZE - 1, GFP_ATOMIC);
 	spin_unlock_bh(&tx_ring->tx_idr_lock);
 
-	if (ret < 0) {
+	if (unlikely(ret < 0)) {
 		if (ring_map == (BIT(DP_TCL_NUM_RING_MAX) - 1)) {
 			atomic_inc(&ab->soc_stats.tx_err.misc_fail);
 			return -ENOSPC;

@@ -147,7 +147,7 @@ int ath11k_dp_tx(struct ath11k *ar, struct ath11k_vif *arvif,
 	ti.encap_type = ath11k_dp_tx_get_encap_type(arvif, skb);
 	ti.meta_data_flags = arvif->tcl_metadata;
 
-	if (ti.encap_type == HAL_TCL_ENCAP_TYPE_RAW) {
+	if (unlikely(ti.encap_type == HAL_TCL_ENCAP_TYPE_RAW)) {
 		if (skb_cb->flags & ATH11K_SKB_CIPHER_SET) {
 			ti.encrypt_type =
 				ath11k_dp_tx_get_encrypt_type(skb_cb->cipher);

@@ -168,8 +168,8 @@ int ath11k_dp_tx(struct ath11k *ar, struct ath11k_vif *arvif,
 	ti.bss_ast_idx = arvif->ast_idx;
 	ti.dscp_tid_tbl_idx = 0;
 
-	if (skb->ip_summed == CHECKSUM_PARTIAL &&
-	    ti.encap_type != HAL_TCL_ENCAP_TYPE_RAW) {
+	if (likely(skb->ip_summed == CHECKSUM_PARTIAL &&
+		   ti.encap_type != HAL_TCL_ENCAP_TYPE_RAW)) {
 		ti.flags0 |= FIELD_PREP(HAL_TCL_DATA_CMD_INFO1_IP4_CKSUM_EN, 1) |
 			     FIELD_PREP(HAL_TCL_DATA_CMD_INFO1_UDP4_CKSUM_EN, 1) |
 			     FIELD_PREP(HAL_TCL_DATA_CMD_INFO1_UDP6_CKSUM_EN, 1) |

@@ -206,7 +206,7 @@ int ath11k_dp_tx(struct ath11k *ar, struct ath11k_vif *arvif,
 	}
 
 	ti.paddr = dma_map_single(ab->dev, skb->data, skb->len, DMA_TO_DEVICE);
-	if (dma_mapping_error(ab->dev, ti.paddr)) {
+	if (unlikely(dma_mapping_error(ab->dev, ti.paddr))) {
 		atomic_inc(&ab->soc_stats.tx_err.misc_fail);
 		ath11k_warn(ab, "failed to DMA map data Tx buffer\n");
 		ret = -ENOMEM;

@@ -226,7 +226,7 @@ int ath11k_dp_tx(struct ath11k *ar, struct ath11k_vif *arvif,
 	ath11k_hal_srng_access_begin(ab, tcl_ring);
 
 	hal_tcl_desc = (void *)ath11k_hal_srng_src_get_next_entry(ab, tcl_ring);
-	if (!hal_tcl_desc) {
+	if (unlikely(!hal_tcl_desc)) {
 		/* NOTE: It is highly unlikely we'll be running out of tcl_ring
 		 * desc because the desc is directly enqueued onto hw queue.
 		 */

@@ -240,8 +240,8 @@ int ath11k_dp_tx(struct ath11k *ar, struct ath11k_vif *arvif,
 		 * checking this ring earlier for each pkt tx.
 		 * Restart ring selection if some rings are not checked yet.
 		 */
-		if (ring_map != (BIT(DP_TCL_NUM_RING_MAX) - 1) &&
-		    !ar->ab->hw_params.tcl_0_only) {
+		if (unlikely(ring_map != (BIT(DP_TCL_NUM_RING_MAX) - 1) &&
+			     !ar->ab->hw_params.tcl_0_only)) {
 			tcl_ring_retry = true;
 			ring_selector++;
 		}

@@ -322,7 +322,7 @@ ath11k_dp_tx_htt_tx_complete_buf(struct ath11k_base *ab,
 
 	spin_lock_bh(&tx_ring->tx_idr_lock);
 	msdu = idr_find(&tx_ring->txbuf_idr, ts->msdu_id);
-	if (!msdu) {
+	if (unlikely(!msdu)) {
 		ath11k_warn(ab, "htt tx completion for unknown msdu_id %d\n",
 			    ts->msdu_id);
 		spin_unlock_bh(&tx_ring->tx_idr_lock);

@@ -430,16 +430,14 @@ static void ath11k_dp_tx_complete_msdu(struct ath11k *ar,
 
 	dma_unmap_single(ab->dev, skb_cb->paddr, msdu->len, DMA_TO_DEVICE);
 
-	rcu_read_lock();
-
-	if (!rcu_dereference(ab->pdevs_active[ar->pdev_idx])) {
+	if (unlikely(!rcu_access_pointer(ab->pdevs_active[ar->pdev_idx]))) {
 		dev_kfree_skb_any(msdu);
-		goto exit;
+		return;
 	}
 
-	if (!skb_cb->vif) {
+	if (unlikely(!skb_cb->vif)) {
 		dev_kfree_skb_any(msdu);
-		goto exit;
+		return;
 	}
 
 	info = IEEE80211_SKB_CB(msdu);

@@ -460,7 +458,7 @@ static void ath11k_dp_tx_complete_msdu(struct ath11k *ar,
 	    (info->flags & IEEE80211_TX_CTL_NO_ACK))
 		info->flags |= IEEE80211_TX_STAT_NOACK_TRANSMITTED;
 
-	if (ath11k_debugfs_is_extd_tx_stats_enabled(ar)) {
+	if (unlikely(ath11k_debugfs_is_extd_tx_stats_enabled(ar))) {
 		if (ts->flags & HAL_TX_STATUS_FLAGS_FIRST_MSDU) {
 			if (ar->last_ppdu_id == 0) {
 				ar->last_ppdu_id = ts->ppdu_id;

@@ -489,9 +487,6 @@ static void ath11k_dp_tx_complete_msdu(struct ath11k *ar,
 	 */
 
 	ieee80211_tx_status(ar->hw, msdu);
-
-exit:
-	rcu_read_unlock();
 }
 
 static inline void ath11k_dp_tx_status_parse(struct ath11k_base *ab,

@@ -500,11 +495,11 @@ static inline void ath11k_dp_tx_status_parse(struct ath11k_base *ab,
 {
 	ts->buf_rel_source =
 		FIELD_GET(HAL_WBM_RELEASE_INFO0_REL_SRC_MODULE, desc->info0);
-	if (ts->buf_rel_source != HAL_WBM_REL_SRC_MODULE_FW &&
-	    ts->buf_rel_source != HAL_WBM_REL_SRC_MODULE_TQM)
+	if (unlikely(ts->buf_rel_source != HAL_WBM_REL_SRC_MODULE_FW &&
+		     ts->buf_rel_source != HAL_WBM_REL_SRC_MODULE_TQM))
 		return;
 
-	if (ts->buf_rel_source == HAL_WBM_REL_SRC_MODULE_FW)
+	if (unlikely(ts->buf_rel_source == HAL_WBM_REL_SRC_MODULE_FW))
 		return;
 
 	ts->status = FIELD_GET(HAL_WBM_RELEASE_INFO0_TQM_RELEASE_REASON,

@@ -551,8 +546,9 @@ void ath11k_dp_tx_completion_handler(struct ath11k_base *ab, int ring_id)
 			ATH11K_TX_COMPL_NEXT(tx_ring->tx_status_head);
 	}
 
-	if ((ath11k_hal_srng_dst_peek(ab, status_ring) != NULL) &&
-	    (ATH11K_TX_COMPL_NEXT(tx_ring->tx_status_head) == tx_ring->tx_status_tail)) {
+	if (unlikely((ath11k_hal_srng_dst_peek(ab, status_ring) != NULL) &&
+		     (ATH11K_TX_COMPL_NEXT(tx_ring->tx_status_head) ==
+		      tx_ring->tx_status_tail))) {
 		/* TODO: Process pending tx_status messages when kfifo_is_full() */
 		ath11k_warn(ab, "Unable to process some of the tx_status ring desc because status_fifo is full\n");
 	}

@@ -575,7 +571,7 @@ void ath11k_dp_tx_completion_handler(struct ath11k_base *ab, int ring_id)
 		mac_id = FIELD_GET(DP_TX_DESC_ID_MAC_ID, desc_id);
 		msdu_id = FIELD_GET(DP_TX_DESC_ID_MSDU_ID, desc_id);
 
-		if (ts.buf_rel_source == HAL_WBM_REL_SRC_MODULE_FW) {
+		if (unlikely(ts.buf_rel_source == HAL_WBM_REL_SRC_MODULE_FW)) {
 			ath11k_dp_tx_process_htt_tx_complete(ab,
 							     (void *)tx_status,
 							     mac_id, msdu_id,

@@ -585,7 +581,7 @@ void ath11k_dp_tx_completion_handler(struct ath11k_base *ab, int ring_id)
 
 		spin_lock_bh(&tx_ring->tx_idr_lock);
 		msdu = idr_find(&tx_ring->txbuf_idr, msdu_id);
-		if (!msdu) {
+		if (unlikely(!msdu)) {
 			ath11k_warn(ab, "tx completion for unknown msdu_id %d\n",
 				    msdu_id);
 			spin_unlock_bh(&tx_ring->tx_idr_lock);

index e9b3689..7c4bf51 100644
@@ -4339,7 +4339,7 @@ static void ath11k_mac_op_tx(struct ieee80211_hw *hw,
 	}
 
 	ret = ath11k_dp_tx(ar, arvif, skb);
-	if (ret) {
+	if (unlikely(ret)) {
 		ath11k_warn(ar->ab, "failed to transmit frame %d\n", ret);
 		ieee80211_free_txskb(ar->hw, skb);
 	}

index 602184b..05bd86f 100644
@@ -288,20 +288,18 @@ static void ath11k_dp_tx_free_txbuf(struct ath11k_base *ab, u8 mac_id,
 	struct sk_buff *msdu;
 	struct ath11k_skb_cb *skb_cb;
 
-	spin_lock_bh(&tx_ring->tx_idr_lock);
-	msdu = idr_find(&tx_ring->txbuf_idr, msdu_id);
-	if (!msdu) {
+	spin_lock(&tx_ring->tx_idr_lock);
+	msdu = idr_remove(&tx_ring->txbuf_idr, msdu_id);
+	spin_unlock(&tx_ring->tx_idr_lock);
+
+	if (unlikely(!msdu)) {
 		ath11k_warn(ab, "tx completion for unknown msdu_id %d\n",
 			    msdu_id);
-		spin_unlock_bh(&tx_ring->tx_idr_lock);
 		return;
 	}
 
 	skb_cb = ATH11K_SKB_CB(msdu);
 
-	idr_remove(&tx_ring->txbuf_idr, msdu_id);
-	spin_unlock_bh(&tx_ring->tx_idr_lock);
-
 	dma_unmap_single(ab->dev, skb_cb->paddr, msdu->len, DMA_TO_DEVICE);
 	dev_kfree_skb_any(msdu);
 

@@ -320,12 +318,13 @@ ath11k_dp_tx_htt_tx_complete_buf(struct ath11k_base *ab,
 	struct ath11k_skb_cb *skb_cb;
 	struct ath11k *ar;
 
-	spin_lock_bh(&tx_ring->tx_idr_lock);
-	msdu = idr_find(&tx_ring->txbuf_idr, ts->msdu_id);
+	spin_lock(&tx_ring->tx_idr_lock);
+	msdu = idr_remove(&tx_ring->txbuf_idr, ts->msdu_id);
+	spin_unlock(&tx_ring->tx_idr_lock);
+
 	if (unlikely(!msdu)) {
 		ath11k_warn(ab, "htt tx completion for unknown msdu_id %d\n",
 			    ts->msdu_id);
-		spin_unlock_bh(&tx_ring->tx_idr_lock);
 		return;
 	}
 

@@ -334,9 +333,6 @@ ath11k_dp_tx_htt_tx_complete_buf(struct ath11k_base *ab,
 
 	ar = skb_cb->ar;
 
-	idr_remove(&tx_ring->txbuf_idr, ts->msdu_id);
-	spin_unlock_bh(&tx_ring->tx_idr_lock);
-
 	if (atomic_dec_and_test(&ar->dp.num_tx_pending))
 		wake_up(&ar->dp.tx_empty_waitq);
 

@@ -579,16 +575,16 @@ void ath11k_dp_tx_completion_handler(struct ath11k_base *ab, int ring_id)
 			continue;
 		}
 
-		spin_lock_bh(&tx_ring->tx_idr_lock);
-		msdu = idr_find(&tx_ring->txbuf_idr, msdu_id);
+		spin_lock(&tx_ring->tx_idr_lock);
+		msdu = idr_remove(&tx_ring->txbuf_idr, msdu_id);
 		if (unlikely(!msdu)) {
 			ath11k_warn(ab, "tx completion for unknown msdu_id %d\n",
 				    msdu_id);
-			spin_unlock_bh(&tx_ring->tx_idr_lock);
+			spin_unlock(&tx_ring->tx_idr_lock);
 			continue;
 		}
-		idr_remove(&tx_ring->txbuf_idr, msdu_id);
-		spin_unlock_bh(&tx_ring->tx_idr_lock);
+
+		spin_unlock(&tx_ring->tx_idr_lock);
 
 		ar = ab->pdevs[mac_id].ar;