Merge ath-next from git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/ath.git

ath.git patches for v5.8. Major changes:

ath11k

* add 802.11 encapsulation offload on hardware support

* add htt_peer_stats_reset debugfs file

ath10k

* sdio: decrease power consumption

* sdio: add HTT TX bundle support to increase throughput

* sdio: add rx bitrate reporting

ath9k

* improvements to AR9002 calibration logic

carl9170

* remove buggy P2P_GO support

53 files changed, 1788 insertions, 302 deletions

diff --git a/drivers/net/wireless/ath/ath10k/bmi.c b/drivers/net/wireless/ath/ath10k/bmi.c
index ea908107581d..5b6db6e66f65 100644
--- a/drivers/net/wireless/ath/ath10k/bmi.c
+++ b/drivers/net/wireless/ath/ath10k/bmi.c
@@ -380,6 +380,7 @@ static int ath10k_bmi_lz_data_large(struct ath10k *ar, const void *buffer, u32 l
 						  NULL, NULL);
 		if (ret) {
 			ath10k_warn(ar, "unable to write to the device\n");
+			kfree(cmd);
 			return ret;
 		}
 
diff --git a/drivers/net/wireless/ath/ath10k/ce.h b/drivers/net/wireless/ath/ath10k/ce.h
index a7478c240f78..9711f0eb9117 100644
--- a/drivers/net/wireless/ath/ath10k/ce.h
+++ b/drivers/net/wireless/ath/ath10k/ce.h
@@ -419,7 +419,7 @@ struct ce_pipe_config {
 #define PIPEDIR_INOUT   3  /* bidirectional */
 
 /* Establish a mapping between a service/direction and a pipe. */
-struct service_to_pipe {
+struct ce_service_to_pipe {
 	__le32 service_id;
 	__le32 pipedir;
 	__le32 pipenum;
diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c
index 52472bbcee1f..22b6937ac225 100644
--- a/drivers/net/wireless/ath/ath10k/core.c
+++ b/drivers/net/wireless/ath/ath10k/core.c
@@ -190,6 +190,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.uart_pin_workaround = true,
 		.tx_stats_over_pktlog = false,
 		.bmi_large_size_download = true,
+		.supports_peer_stats_info = true,
 	},
 	{
 		.id = QCA6174_HW_2_1_VERSION,
@@ -725,10 +726,10 @@ static int ath10k_init_sdio(struct ath10k *ar, enum ath10k_firmware_mode mode)
 
 	param |= HI_ACS_FLAGS_SDIO_REDUCE_TX_COMPL_SET;
 
-	/* Alternate credit size of 1544 as used by SDIO firmware is
-	 * not big enough for mac80211 / native wifi frames. disable it
-	 */
-	param &= ~HI_ACS_FLAGS_ALT_DATA_CREDIT_SIZE;
+	if (mode == ATH10K_FIRMWARE_MODE_NORMAL)
+		param |= HI_ACS_FLAGS_ALT_DATA_CREDIT_SIZE;
+	else
+		param &= ~HI_ACS_FLAGS_ALT_DATA_CREDIT_SIZE;
 
 	if (mode == ATH10K_FIRMWARE_MODE_UTF)
 		param &= ~HI_ACS_FLAGS_SDIO_SWAP_MAILBOX_SET;
@@ -2714,7 +2715,7 @@ int ath10k_core_start(struct ath10k *ar, enum ath10k_firmware_mode mode,
 		goto err_hif_stop;
 	}
 
-	status = ath10k_hif_swap_mailbox(ar);
+	status = ath10k_hif_start_post(ar);
 	if (status) {
 		ath10k_err(ar, "failed to swap mailbox: %d\n", status);
 		goto err_hif_stop;
@@ -3277,6 +3278,7 @@ struct ath10k *ath10k_core_create(size_t priv_size, struct device *dev,
 	init_completion(&ar->thermal.wmi_sync);
 	init_completion(&ar->bss_survey_done);
 	init_completion(&ar->peer_delete_done);
+	init_completion(&ar->peer_stats_info_complete);
 
 	INIT_DELAYED_WORK(&ar->scan.timeout, ath10k_scan_timeout_work);
 
@@ -3288,6 +3290,11 @@ struct ath10k *ath10k_core_create(size_t priv_size, struct device *dev,
 	if (!ar->workqueue_aux)
 		goto err_free_wq;
 
+	ar->workqueue_tx_complete =
+		create_singlethread_workqueue("ath10k_tx_complete_wq");
+	if (!ar->workqueue_tx_complete)
+		goto err_free_aux_wq;
+
 	mutex_init(&ar->conf_mutex);
 	mutex_init(&ar->dump_mutex);
 	spin_lock_init(&ar->data_lock);
@@ -3315,7 +3322,7 @@ struct ath10k *ath10k_core_create(size_t priv_size, struct device *dev,
 
 	ret = ath10k_coredump_create(ar);
 	if (ret)
-		goto err_free_aux_wq;
+		goto err_free_tx_complete;
 
 	ret = ath10k_debug_create(ar);
 	if (ret)
@@ -3325,12 +3332,12 @@ struct ath10k *ath10k_core_create(size_t priv_size, struct device *dev,
 
 err_free_coredump:
 	ath10k_coredump_destroy(ar);
-
+err_free_tx_complete:
+	destroy_workqueue(ar->workqueue_tx_complete);
 err_free_aux_wq:
 	destroy_workqueue(ar->workqueue_aux);
 err_free_wq:
 	destroy_workqueue(ar->workqueue);
-
 err_free_mac:
 	ath10k_mac_destroy(ar);
 
@@ -3346,6 +3353,9 @@ void ath10k_core_destroy(struct ath10k *ar)
 	flush_workqueue(ar->workqueue_aux);
 	destroy_workqueue(ar->workqueue_aux);
 
+	flush_workqueue(ar->workqueue_tx_complete);
+	destroy_workqueue(ar->workqueue_tx_complete);
+
 	ath10k_debug_destroy(ar);
 	ath10k_coredump_destroy(ar);
 	ath10k_htt_tx_destroy(&ar->htt);
diff --git a/drivers/net/wireless/ath/ath10k/core.h b/drivers/net/wireless/ath/ath10k/core.h
index bd8ef576c590..ceac76553b8f 100644
--- a/drivers/net/wireless/ath/ath10k/core.h
+++ b/drivers/net/wireless/ath/ath10k/core.h
@@ -149,6 +149,26 @@ static inline u32 host_interest_item_address(u32 item_offset)
 	return QCA988X_HOST_INTEREST_ADDRESS + item_offset;
 }
 
+enum ath10k_phy_mode {
+	ATH10K_PHY_MODE_LEGACY = 0,
+	ATH10K_PHY_MODE_HT = 1,
+	ATH10K_PHY_MODE_VHT = 2,
+};
+
+/* Data rate 100KBPS based on IE Index */
+struct ath10k_index_ht_data_rate_type {
+	u8   beacon_rate_index;
+	u16  supported_rate[4];
+};
+
+/* Data rate 100KBPS based on IE Index */
+struct ath10k_index_vht_data_rate_type {
+	u8   beacon_rate_index;
+	u16  supported_VHT80_rate[2];
+	u16  supported_VHT40_rate[2];
+	u16  supported_VHT20_rate[2];
+};
+
 struct ath10k_bmi {
 	bool done_sent;
 };
@@ -500,8 +520,14 @@ struct ath10k_sta {
 	u16 peer_id;
 	struct rate_info txrate;
 	struct ieee80211_tx_info tx_info;
+	u32 tx_retries;
+	u32 tx_failed;
 	u32 last_tx_bitrate;
 
+	u32 rx_rate_code;
+	u32 rx_bitrate_kbps;
+	u32 tx_rate_code;
+	u32 tx_bitrate_kbps;
 	struct work_struct update_wk;
 	u64 rx_duration;
 	struct ath10k_htt_tx_stats *tx_stats;
@@ -949,6 +975,11 @@ struct ath10k {
 	struct ieee80211_hw *hw;
 	struct ieee80211_ops *ops;
 	struct device *dev;
+	struct msa_region {
+		dma_addr_t paddr;
+		u32 mem_size;
+		void *vaddr;
+	} msa;
 	u8 mac_addr[ETH_ALEN];
 
 	enum ath10k_hw_rev hw_rev;
@@ -1087,11 +1118,12 @@ struct ath10k {
 	int last_wmi_vdev_start_status;
 	struct completion vdev_setup_done;
 	struct completion vdev_delete_done;
+	struct completion peer_stats_info_complete;
 
 	struct workqueue_struct *workqueue;
 	/* Auxiliary workqueue */
 	struct workqueue_struct *workqueue_aux;
-
+	struct workqueue_struct *workqueue_tx_complete;
 	/* prevents concurrent FW reconfiguration */
 	struct mutex conf_mutex;
 
@@ -1132,6 +1164,8 @@ struct ath10k {
 
 	struct work_struct register_work;
 	struct work_struct restart_work;
+	struct work_struct bundle_tx_work;
+	struct work_struct tx_complete_work;
 
 	/* cycle count is reported twice for each visited channel during scan.
 	 * access protected by data_lock
diff --git a/drivers/net/wireless/ath/ath10k/debug.c b/drivers/net/wireless/ath/ath10k/debug.c
index f811e6940fb0..e8250a665433 100644
--- a/drivers/net/wireless/ath/ath10k/debug.c
+++ b/drivers/net/wireless/ath/ath10k/debug.c
@@ -349,7 +349,7 @@ free:
 	spin_unlock_bh(&ar->data_lock);
 }
 
-static int ath10k_debug_fw_stats_request(struct ath10k *ar)
+int ath10k_debug_fw_stats_request(struct ath10k *ar)
 {
 	unsigned long timeout, time_left;
 	int ret;
@@ -778,7 +778,7 @@ static ssize_t ath10k_mem_value_read(struct file *file,
 
 	ret = ath10k_hif_diag_read(ar, *ppos, buf, count);
 	if (ret) {
-		ath10k_warn(ar, "failed to read address 0x%08x via diagnose window fnrom debugfs: %d\n",
+		ath10k_warn(ar, "failed to read address 0x%08x via diagnose window from debugfs: %d\n",
 			    (u32)(*ppos), ret);
 		goto exit;
 	}
diff --git a/drivers/net/wireless/ath/ath10k/debug.h b/drivers/net/wireless/ath/ath10k/debug.h
index 82f7eb8583d9..4cbfd9279d6f 100644
--- a/drivers/net/wireless/ath/ath10k/debug.h
+++ b/drivers/net/wireless/ath/ath10k/debug.h
@@ -125,6 +125,9 @@ static inline int ath10k_debug_is_extd_tx_stats_enabled(struct ath10k *ar)
 {
 	return ar->debug.enable_extd_tx_stats;
 }
+
+int ath10k_debug_fw_stats_request(struct ath10k *ar);
+
 #else
 
 static inline int ath10k_debug_start(struct ath10k *ar)
@@ -192,6 +195,11 @@ static inline int ath10k_debug_is_extd_tx_stats_enabled(struct ath10k *ar)
 	return 0;
 }
 
+static inline int ath10k_debug_fw_stats_request(struct ath10k *ar)
+{
+	return 0;
+}
+
 #define ATH10K_DFS_STAT_INC(ar, c) do { } while (0)
 
 #define ath10k_debug_get_et_strings NULL
diff --git a/drivers/net/wireless/ath/ath10k/hif.h b/drivers/net/wireless/ath/ath10k/hif.h
index 0dd8973d0acf..9e45fd9073a6 100644
--- a/drivers/net/wireless/ath/ath10k/hif.h
+++ b/drivers/net/wireless/ath/ath10k/hif.h
@@ -54,7 +54,7 @@ struct ath10k_hif_ops {
 	 */
 	void (*stop)(struct ath10k *ar);
 
-	int (*swap_mailbox)(struct ath10k *ar);
+	int (*start_post)(struct ath10k *ar);
 
 	int (*get_htt_tx_complete)(struct ath10k *ar);
 
@@ -139,10 +139,10 @@ static inline void ath10k_hif_stop(struct ath10k *ar)
 	return ar->hif.ops->stop(ar);
 }
 
-static inline int ath10k_hif_swap_mailbox(struct ath10k *ar)
+static inline int ath10k_hif_start_post(struct ath10k *ar)
 {
-	if (ar->hif.ops->swap_mailbox)
-		return ar->hif.ops->swap_mailbox(ar);
+	if (ar->hif.ops->start_post)
+		return ar->hif.ops->start_post(ar);
 	return 0;
 }
 
@@ -170,7 +170,8 @@ static inline void ath10k_hif_get_default_pipe(struct ath10k *ar,
 static inline void ath10k_hif_send_complete_check(struct ath10k *ar,
 						  u8 pipe_id, int force)
 {
-	ar->hif.ops->send_complete_check(ar, pipe_id, force);
+	if (ar->hif.ops->send_complete_check)
+		ar->hif.ops->send_complete_check(ar, pipe_id, force);
 }
 
 static inline u16 ath10k_hif_get_free_queue_number(struct ath10k *ar,
diff --git a/drivers/net/wireless/ath/ath10k/htc.c b/drivers/net/wireless/ath/ath10k/htc.c
index 61ee413d902a..31df6dd04bf6 100644
--- a/drivers/net/wireless/ath/ath10k/htc.c
+++ b/drivers/net/wireless/ath/ath10k/htc.c
@@ -51,10 +51,12 @@ void ath10k_htc_notify_tx_completion(struct ath10k_htc_ep *ep,
 				     struct sk_buff *skb)
 {
 	struct ath10k *ar = ep->htc->ar;
+	struct ath10k_htc_hdr *hdr;
 
 	ath10k_dbg(ar, ATH10K_DBG_HTC, "%s: ep %d skb %pK\n", __func__,
 		   ep->eid, skb);
 
+	hdr = (struct ath10k_htc_hdr *)skb->data;
 	ath10k_htc_restore_tx_skb(ep->htc, skb);
 
 	if (!ep->ep_ops.ep_tx_complete) {
@@ -63,6 +65,11 @@ void ath10k_htc_notify_tx_completion(struct ath10k_htc_ep *ep,
 		return;
 	}
 
+	if (hdr->flags & ATH10K_HTC_FLAG_SEND_BUNDLE) {
+		dev_kfree_skb_any(skb);
+		return;
+	}
+
 	ep->ep_ops.ep_tx_complete(ep->htc->ar, skb);
 }
 EXPORT_SYMBOL(ath10k_htc_notify_tx_completion);
@@ -78,7 +85,7 @@ static void ath10k_htc_prepare_tx_skb(struct ath10k_htc_ep *ep,
 	hdr->eid = ep->eid;
 	hdr->len = __cpu_to_le16(skb->len - sizeof(*hdr));
 	hdr->flags = 0;
-	if (ep->tx_credit_flow_enabled)
+	if (ep->tx_credit_flow_enabled && !ep->bundle_tx)
 		hdr->flags |= ATH10K_HTC_FLAG_NEED_CREDIT_UPDATE;
 
 	spin_lock_bh(&ep->htc->tx_lock);
@@ -86,6 +93,63 @@ static void ath10k_htc_prepare_tx_skb(struct ath10k_htc_ep *ep,
 	spin_unlock_bh(&ep->htc->tx_lock);
 }
 
+static int ath10k_htc_consume_credit(struct ath10k_htc_ep *ep,
+				     unsigned int len,
+				     bool consume)
+{
+	struct ath10k_htc *htc = ep->htc;
+	struct ath10k *ar = htc->ar;
+	enum ath10k_htc_ep_id eid = ep->eid;
+	int credits, ret = 0;
+
+	if (!ep->tx_credit_flow_enabled)
+		return 0;
+
+	credits = DIV_ROUND_UP(len, ep->tx_credit_size);
+	spin_lock_bh(&htc->tx_lock);
+
+	if (ep->tx_credits < credits) {
+		ath10k_dbg(ar, ATH10K_DBG_HTC,
+			   "htc insufficient credits ep %d required %d available %d consume %d\n",
+			   eid, credits, ep->tx_credits, consume);
+		ret = -EAGAIN;
+		goto unlock;
+	}
+
+	if (consume) {
+		ep->tx_credits -= credits;
+		ath10k_dbg(ar, ATH10K_DBG_HTC,
+			   "htc ep %d consumed %d credits total %d\n",
+			   eid, credits, ep->tx_credits);
+	}
+
+unlock:
+	spin_unlock_bh(&htc->tx_lock);
+	return ret;
+}
+
+static void ath10k_htc_release_credit(struct ath10k_htc_ep *ep, unsigned int len)
+{
+	struct ath10k_htc *htc = ep->htc;
+	struct ath10k *ar = htc->ar;
+	enum ath10k_htc_ep_id eid = ep->eid;
+	int credits;
+
+	if (!ep->tx_credit_flow_enabled)
+		return;
+
+	credits = DIV_ROUND_UP(len, ep->tx_credit_size);
+	spin_lock_bh(&htc->tx_lock);
+	ep->tx_credits += credits;
+	ath10k_dbg(ar, ATH10K_DBG_HTC,
+		   "htc ep %d reverted %d credits back total %d\n",
+		   eid, credits, ep->tx_credits);
+	spin_unlock_bh(&htc->tx_lock);
+
+	if (ep->ep_ops.ep_tx_credits)
+		ep->ep_ops.ep_tx_credits(htc->ar);
+}
+
 int ath10k_htc_send(struct ath10k_htc *htc,
 		    enum ath10k_htc_ep_id eid,
 		    struct sk_buff *skb)
@@ -95,8 +159,8 @@ int ath10k_htc_send(struct ath10k_htc *htc,
 	struct ath10k_skb_cb *skb_cb = ATH10K_SKB_CB(skb);
 	struct ath10k_hif_sg_item sg_item;
 	struct device *dev = htc->ar->dev;
-	int credits = 0;
 	int ret;
+	unsigned int skb_len;
 
 	if (htc->ar->state == ATH10K_STATE_WEDGED)
 		return -ECOMM;
@@ -108,23 +172,10 @@ int ath10k_htc_send(struct ath10k_htc *htc,
 
 	skb_push(skb, sizeof(struct ath10k_htc_hdr));
 
-	if (ep->tx_credit_flow_enabled) {
-		credits = DIV_ROUND_UP(skb->len, htc->target_credit_size);
-		spin_lock_bh(&htc->tx_lock);
-		if (ep->tx_credits < credits) {
-			ath10k_dbg(ar, ATH10K_DBG_HTC,
-				   "htc insufficient credits ep %d required %d available %d\n",
-				   eid, credits, ep->tx_credits);
-			spin_unlock_bh(&htc->tx_lock);
-			ret = -EAGAIN;
-			goto err_pull;
-		}
-		ep->tx_credits -= credits;
-		ath10k_dbg(ar, ATH10K_DBG_HTC,
-			   "htc ep %d consumed %d credits (total %d)\n",
-			   eid, credits, ep->tx_credits);
-		spin_unlock_bh(&htc->tx_lock);
-	}
+	skb_len = skb->len;
+	ret = ath10k_htc_consume_credit(ep, skb_len, true);
+	if (ret)
+		goto err_pull;
 
 	ath10k_htc_prepare_tx_skb(ep, skb);
 
@@ -155,17 +206,7 @@ err_unmap:
 	if (ar->bus_param.dev_type != ATH10K_DEV_TYPE_HL)
 		dma_unmap_single(dev, skb_cb->paddr, skb->len, DMA_TO_DEVICE);
 err_credits:
-	if (ep->tx_credit_flow_enabled) {
-		spin_lock_bh(&htc->tx_lock);
-		ep->tx_credits += credits;
-		ath10k_dbg(ar, ATH10K_DBG_HTC,
-			   "htc ep %d reverted %d credits back (total %d)\n",
-			   eid, credits, ep->tx_credits);
-		spin_unlock_bh(&htc->tx_lock);
-
-		if (ep->ep_ops.ep_tx_credits)
-			ep->ep_ops.ep_tx_credits(htc->ar);
-	}
+	ath10k_htc_release_credit(ep, skb_len);
 err_pull:
 	skb_pull(skb, sizeof(struct ath10k_htc_hdr));
 	return ret;
@@ -581,6 +622,278 @@ static u8 ath10k_htc_get_credit_allocation(struct ath10k_htc *htc,
 	return allocation;
 }
 
+static int ath10k_htc_send_bundle(struct ath10k_htc_ep *ep,
+				  struct sk_buff *bundle_skb,
+				  struct sk_buff_head *tx_save_head)
+{
+	struct ath10k_hif_sg_item sg_item;
+	struct ath10k_htc *htc = ep->htc;
+	struct ath10k *ar = htc->ar;
+	struct sk_buff *skb;
+	int ret, cn = 0;
+	unsigned int skb_len;
+
+	ath10k_dbg(ar, ATH10K_DBG_HTC, "bundle skb len %d\n", bundle_skb->len);
+	skb_len = bundle_skb->len;
+	ret = ath10k_htc_consume_credit(ep, skb_len, true);
+
+	if (!ret) {
+		sg_item.transfer_id = ep->eid;
+		sg_item.transfer_context = bundle_skb;
+		sg_item.vaddr = bundle_skb->data;
+		sg_item.len = bundle_skb->len;
+
+		ret = ath10k_hif_tx_sg(htc->ar, ep->ul_pipe_id, &sg_item, 1);
+		if (ret)
+			ath10k_htc_release_credit(ep, skb_len);
+	}
+
+	if (ret)
+		dev_kfree_skb_any(bundle_skb);
+
+	for (cn = 0; (skb = skb_dequeue_tail(tx_save_head)); cn++) {
+		if (ret) {
+			skb_pull(skb, sizeof(struct ath10k_htc_hdr));
+			skb_queue_head(&ep->tx_req_head, skb);
+		} else {
+			skb_queue_tail(&ep->tx_complete_head, skb);
+		}
+	}
+
+	if (!ret)
+		queue_work(ar->workqueue_tx_complete, &ar->tx_complete_work);
+
+	ath10k_dbg(ar, ATH10K_DBG_HTC,
+		   "bundle tx status %d eid %d req count %d count %d len %d\n",
+		   ret, ep->eid, skb_queue_len(&ep->tx_req_head), cn, bundle_skb->len);
+	return ret;
+}
+
+static void ath10k_htc_send_one_skb(struct ath10k_htc_ep *ep, struct sk_buff *skb)
+{
+	struct ath10k_htc *htc = ep->htc;
+	struct ath10k *ar = htc->ar;
+	int ret;
+
+	ret = ath10k_htc_send(htc, ep->eid, skb);
+
+	if (ret)
+		skb_queue_head(&ep->tx_req_head, skb);
+
+	ath10k_dbg(ar, ATH10K_DBG_HTC, "tx one status %d eid %d len %d pending count %d\n",
+		   ret, ep->eid, skb->len, skb_queue_len(&ep->tx_req_head));
+}
+
+static int ath10k_htc_send_bundle_skbs(struct ath10k_htc_ep *ep)
+{
+	struct ath10k_htc *htc = ep->htc;
+	struct sk_buff *bundle_skb, *skb;
+	struct sk_buff_head tx_save_head;
+	struct ath10k_htc_hdr *hdr;
+	u8 *bundle_buf;
+	int ret = 0, credit_pad, credit_remainder, trans_len, bundles_left = 0;
+
+	if (htc->ar->state == ATH10K_STATE_WEDGED)
+		return -ECOMM;
+
+	if (ep->tx_credit_flow_enabled &&
+	    ep->tx_credits < ATH10K_MIN_CREDIT_PER_HTC_TX_BUNDLE)
+		return 0;
+
+	bundles_left = ATH10K_MAX_MSG_PER_HTC_TX_BUNDLE * ep->tx_credit_size;
+	bundle_skb = dev_alloc_skb(bundles_left);
+
+	if (!bundle_skb)
+		return -ENOMEM;
+
+	bundle_buf = bundle_skb->data;
+	skb_queue_head_init(&tx_save_head);
+
+	while (true) {
+		skb = skb_dequeue(&ep->tx_req_head);
+		if (!skb)
+			break;
+
+		credit_pad = 0;
+		trans_len = skb->len + sizeof(*hdr);
+		credit_remainder = trans_len % ep->tx_credit_size;
+
+		if (credit_remainder != 0) {
+			credit_pad = ep->tx_credit_size - credit_remainder;
+			trans_len += credit_pad;
+		}
+
+		ret = ath10k_htc_consume_credit(ep,
+						bundle_buf + trans_len - bundle_skb->data,
+						false);
+		if (ret) {
+			skb_queue_head(&ep->tx_req_head, skb);
+			break;
+		}
+
+		if (bundles_left < trans_len) {
+			bundle_skb->len = bundle_buf - bundle_skb->data;
+			ret = ath10k_htc_send_bundle(ep, bundle_skb, &tx_save_head);
+
+			if (ret) {
+				skb_queue_head(&ep->tx_req_head, skb);
+				return ret;
+			}
+
+			if (skb_queue_len(&ep->tx_req_head) == 0) {
+				ath10k_htc_send_one_skb(ep, skb);
+				return ret;
+			}
+
+			if (ep->tx_credit_flow_enabled &&
+			    ep->tx_credits < ATH10K_MIN_CREDIT_PER_HTC_TX_BUNDLE) {
+				skb_queue_head(&ep->tx_req_head, skb);
+				return 0;
+			}
+
+			bundles_left =
+				ATH10K_MAX_MSG_PER_HTC_TX_BUNDLE * ep->tx_credit_size;
+			bundle_skb = dev_alloc_skb(bundles_left);
+
+			if (!bundle_skb) {
+				skb_queue_head(&ep->tx_req_head, skb);
+				return -ENOMEM;
+			}
+			bundle_buf = bundle_skb->data;
+			skb_queue_head_init(&tx_save_head);
+		}
+
+		skb_push(skb, sizeof(struct ath10k_htc_hdr));
+		ath10k_htc_prepare_tx_skb(ep, skb);
+
+		memcpy(bundle_buf, skb->data, skb->len);
+		hdr = (struct ath10k_htc_hdr *)bundle_buf;
+		hdr->flags |= ATH10K_HTC_FLAG_SEND_BUNDLE;
+		hdr->pad_len = __cpu_to_le16(credit_pad);
+		bundle_buf += trans_len;
+		bundles_left -= trans_len;
+		skb_queue_tail(&tx_save_head, skb);
+	}
+
+	if (bundle_buf != bundle_skb->data) {
+		bundle_skb->len = bundle_buf - bundle_skb->data;
+		ret = ath10k_htc_send_bundle(ep, bundle_skb, &tx_save_head);
+	} else {
+		dev_kfree_skb_any(bundle_skb);
+	}
+
+	return ret;
+}
+
+static void ath10k_htc_bundle_tx_work(struct work_struct *work)
+{
+	struct ath10k *ar = container_of(work, struct ath10k, bundle_tx_work);
+	struct ath10k_htc_ep *ep;
+	struct sk_buff *skb;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(ar->htc.endpoint); i++) {
+		ep = &ar->htc.endpoint[i];
+
+		if (!ep->bundle_tx)
+			continue;
+
+		ath10k_dbg(ar, ATH10K_DBG_HTC, "bundle tx work eid %d count %d\n",
+			   ep->eid, skb_queue_len(&ep->tx_req_head));
+
+		if (skb_queue_len(&ep->tx_req_head) >=
+		    ATH10K_MIN_MSG_PER_HTC_TX_BUNDLE) {
+			ath10k_htc_send_bundle_skbs(ep);
+		} else {
+			skb = skb_dequeue(&ep->tx_req_head);
+
+			if (!skb)
+				continue;
+			ath10k_htc_send_one_skb(ep, skb);
+		}
+	}
+}
+
+static void ath10k_htc_tx_complete_work(struct work_struct *work)
+{
+	struct ath10k *ar = container_of(work, struct ath10k, tx_complete_work);
+	struct ath10k_htc_ep *ep;
+	enum ath10k_htc_ep_id eid;
+	struct sk_buff *skb;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(ar->htc.endpoint); i++) {