Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:
 "This is a re-do of the net-next pull request for the current merge
  window.  The only difference from the one I made the other day is that
  this has Eliezer's interface renames and the timeout handling changes
  made based upon your feedback, as well as a few bug fixes that have
  trickeled in.

  Highlights:

   1) Low latency device polling, eliminating the cost of interrupt
      handling and context switches.  Allows direct polling of a network
      device from socket operations, such as recvmsg() and poll().

      Currently ixgbe, mlx4, and bnx2x support this feature.

      Full high level description, performance numbers, and design in
      commit 0a4db187a999 ("Merge branch 'll_poll'")

      From Eliezer Tamir.

   2) With the routing cache removed, ip_check_mc_rcu() gets exercised
      more than ever before in the case where we have lots of multicast
      addresses.  Use a hash table instead of a simple linked list, from
      Eric Dumazet.

   3) Add driver for Atheros CQA98xx 802.11ac wireless devices, from
      Bartosz Markowski, Janusz Dziedzic, Kalle Valo, Marek Kwaczynski,
      Marek Puzyniak, Michal Kazior, and Sujith Manoharan.

   4) Support reporting the TUN device persist flag to userspace, from
      Pavel Emelyanov.

   5) Allow controlling network device VF link state using netlink, from
      Rony Efraim.

   6) Support GRE tunneling in openvswitch, from Pravin B Shelar.

   7) Adjust SOCK_MIN_RCVBUF and SOCK_MIN_SNDBUF for modern times, from
      Daniel Borkmann and Eric Dumazet.

   8) Allow controlling of TCP quickack behavior on a per-route basis,
      from Cong Wang.

   9) Several bug fixes and improvements to vxlan from Stephen
      Hemminger, Pravin B Shelar, and Mike Rapoport.  In particular,
      support receiving on multiple UDP ports.

  10) Major cleanups, particular in the area of debugging and cookie
      lifetime handline, to the SCTP protocol code.  From Daniel
      Borkmann.

  11) Allow packets to cross network namespaces when traversing tunnel
      devices.  From Nicolas Dichtel.

  12) Allow monitoring netlink traffic via AF_PACKET sockets, in a
      manner akin to how we monitor real network traffic via ptype_all.
      From Daniel Borkmann.

  13) Several bug fixes and improvements for the new alx device driver,
      from Johannes Berg.

  14) Fix scalability issues in the netem packet scheduler's time queue,
      by using an rbtree.  From Eric Dumazet.

  15) Several bug fixes in TCP loss recovery handling, from Yuchung
      Cheng.

  16) Add support for GSO segmentation of MPLS packets, from Simon
      Horman.

  17) Make network notifiers have a real data type for the opaque
      pointer that's passed into them.  Use this to properly handle
      network device flag changes in arp_netdev_event().  From Jiri
      Pirko and Timo Teräs.

  18) Convert several drivers over to module_pci_driver(), from Peter
      Huewe.

  19) tcp_fixup_rcvbuf() can loop 500 times over loopback, just use a
      O(1) calculation instead.  From Eric Dumazet.

  20) Support setting of explicit tunnel peer addresses in ipv6, just
      like ipv4.  From Nicolas Dichtel.

  21) Protect x86 BPF JIT against spraying attacks, from Eric Dumazet.

  22) Prevent a single high rate flow from overruning an individual cpu
      during RX packet processing via selective flow shedding.  From
      Willem de Bruijn.

  23) Don't use spinlocks in TCP md5 signing fast paths, from Eric
      Dumazet.

  24) Don't just drop GSO packets which are above the TBF scheduler's
      burst limit, chop them up so they are in-bounds instead.  Also
      from Eric Dumazet.

  25) VLAN offloads are missed when configured on top of a bridge, fix
      from Vlad Yasevich.

  26) Support IPV6 in ping sockets.  From Lorenzo Colitti.

  27) Receive flow steering targets should be updated at poll() time
      too, from David Majnemer.

  28) Fix several corner case regressions in PMTU/redirect handling due
      to the routing cache removal, from Timo Teräs.

  29) We have to be mindful of ipv4 mapped ipv6 sockets in
      upd_v6_push_pending_frames().  From Hannes Frederic Sowa.

  30) Fix L2TP sequence number handling bugs, from James Chapman."

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1214 commits)
  drivers/net: caif: fix wrong rtnl_is_locked() usage
  drivers/net: enic: release rtnl_lock on error-path
  vhost-net: fix use-after-free in vhost_net_flush
  net: mv643xx_eth: do not use port number as platform device id
  net: sctp: confirm route during forward progress
  virtio_net: fix race in RX VQ processing
  virtio: support unlocked queue poll
  net/cadence/macb: fix bug/typo in extracting gem_irq_read_clear bit
  Documentation: Fix references to defunct linux-net@vger.kernel.org
  net/fs: change busy poll time accounting
  net: rename low latency sockets functions to busy poll
  bridge: fix some kernel warning in multicast timer
  sfc: Fix memory leak when discarding scattered packets
  sit: fix tunnel update via netlink
  dt:net:stmmac: Add dt specific phy reset callback support.
  dt:net:stmmac: Add support to dwmac version 3.610 and 3.710
  dt:net:stmmac: Allocate platform data only if its NULL.
  net:stmmac: fix memleak in the open method
  ipv6: rt6_check_neigh should successfully verify neigh if no NUD information are available
  net: ipv6: fix wrong ping_v6_sendmsg return value
  ...

1 files changed, 510 insertions, 0 deletions

diff --git a/drivers/net/wireless/ath/ath10k/htt_tx.c b/drivers/net/wireless/ath/ath10k/htt_tx.c
new file mode 100644
index 000000000000..ef79106db247
--- /dev/null
+++ b/drivers/net/wireless/ath/ath10k/htt_tx.c
@@ -0,0 +1,510 @@
+/*
+ * Copyright (c) 2005-2011 Atheros Communications Inc.
+ * Copyright (c) 2011-2013 Qualcomm Atheros, Inc.
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include <linux/etherdevice.h>
+#include "htt.h"
+#include "mac.h"
+#include "hif.h"
+#include "txrx.h"
+#include "debug.h"
+
+void __ath10k_htt_tx_dec_pending(struct ath10k_htt *htt)
+{
+	htt->num_pending_tx--;
+	if (htt->num_pending_tx == htt->max_num_pending_tx - 1)
+		ieee80211_wake_queues(htt->ar->hw);
+}
+
+static void ath10k_htt_tx_dec_pending(struct ath10k_htt *htt)
+{
+	spin_lock_bh(&htt->tx_lock);
+	__ath10k_htt_tx_dec_pending(htt);
+	spin_unlock_bh(&htt->tx_lock);
+}
+
+static int ath10k_htt_tx_inc_pending(struct ath10k_htt *htt)
+{
+	int ret = 0;
+
+	spin_lock_bh(&htt->tx_lock);
+
+	if (htt->num_pending_tx >= htt->max_num_pending_tx) {
+		ret = -EBUSY;
+		goto exit;
+	}
+
+	htt->num_pending_tx++;
+	if (htt->num_pending_tx == htt->max_num_pending_tx)
+		ieee80211_stop_queues(htt->ar->hw);
+
+exit:
+	spin_unlock_bh(&htt->tx_lock);
+	return ret;
+}
+
+int ath10k_htt_tx_alloc_msdu_id(struct ath10k_htt *htt)
+{
+	int msdu_id;
+
+	lockdep_assert_held(&htt->tx_lock);
+
+	msdu_id = find_first_zero_bit(htt->used_msdu_ids,
+				      htt->max_num_pending_tx);
+	if (msdu_id == htt->max_num_pending_tx)
+		return -ENOBUFS;
+
+	ath10k_dbg(ATH10K_DBG_HTT, "htt tx alloc msdu_id %d\n", msdu_id);
+	__set_bit(msdu_id, htt->used_msdu_ids);
+	return msdu_id;
+}
+
+void ath10k_htt_tx_free_msdu_id(struct ath10k_htt *htt, u16 msdu_id)
+{
+	lockdep_assert_held(&htt->tx_lock);
+
+	if (!test_bit(msdu_id, htt->used_msdu_ids))
+		ath10k_warn("trying to free unallocated msdu_id %d\n", msdu_id);
+
+	ath10k_dbg(ATH10K_DBG_HTT, "htt tx free msdu_id %hu\n", msdu_id);
+	__clear_bit(msdu_id, htt->used_msdu_ids);
+}
+
+int ath10k_htt_tx_attach(struct ath10k_htt *htt)
+{
+	u8 pipe;
+
+	spin_lock_init(&htt->tx_lock);
+	init_waitqueue_head(&htt->empty_tx_wq);
+
+	/* At the beginning free queue number should hint us the maximum
+	 * queue length */
+	pipe = htt->ar->htc->endpoint[htt->eid].ul_pipe_id;
+	htt->max_num_pending_tx = ath10k_hif_get_free_queue_number(htt->ar,
+								   pipe);
+
+	ath10k_dbg(ATH10K_DBG_HTT, "htt tx max num pending tx %d\n",
+		   htt->max_num_pending_tx);
+
+	htt->pending_tx = kzalloc(sizeof(*htt->pending_tx) *
+				  htt->max_num_pending_tx, GFP_KERNEL);
+	if (!htt->pending_tx)
+		return -ENOMEM;
+
+	htt->used_msdu_ids = kzalloc(sizeof(unsigned long) *
+				     BITS_TO_LONGS(htt->max_num_pending_tx),
+				     GFP_KERNEL);
+	if (!htt->used_msdu_ids) {
+		kfree(htt->pending_tx);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void ath10k_htt_tx_cleanup_pending(struct ath10k_htt *htt)
+{
+	struct sk_buff *txdesc;
+	int msdu_id;
+
+	/* No locks needed. Called after communication with the device has
+	 * been stopped. */
+
+	for (msdu_id = 0; msdu_id < htt->max_num_pending_tx; msdu_id++) {
+		if (!test_bit(msdu_id, htt->used_msdu_ids))
+			continue;
+
+		txdesc = htt->pending_tx[msdu_id];
+		if (!txdesc)
+			continue;
+
+		ath10k_dbg(ATH10K_DBG_HTT, "force cleanup msdu_id %hu\n",
+			   msdu_id);
+
+		if (ATH10K_SKB_CB(txdesc)->htt.refcount > 0)
+			ATH10K_SKB_CB(txdesc)->htt.refcount = 1;
+
+		ATH10K_SKB_CB(txdesc)->htt.discard = true;
+		ath10k_txrx_tx_unref(htt, txdesc);
+	}
+}
+
+void ath10k_htt_tx_detach(struct ath10k_htt *htt)
+{
+	ath10k_htt_tx_cleanup_pending(htt);
+	kfree(htt->pending_tx);
+	kfree(htt->used_msdu_ids);
+	return;
+}
+
+void ath10k_htt_htc_tx_complete(struct ath10k *ar, struct sk_buff *skb)
+{
+	struct ath10k_skb_cb *skb_cb = ATH10K_SKB_CB(skb);
+	struct ath10k_htt *htt = ar->htt;
+
+	if (skb_cb->htt.is_conf) {
+		dev_kfree_skb_any(skb);
+		return;
+	}
+
+	if (skb_cb->is_aborted) {
+		skb_cb->htt.discard = true;
+
+		/* if the skbuff is aborted we need to make sure we'll free up
+		 * the tx resources, we can't simply run tx_unref() 2 times
+		 * because if htt tx completion came in earlier we'd access
+		 * unallocated memory */
+		if (skb_cb->htt.refcount > 1)
+			skb_cb->htt.refcount = 1;
+	}
+
+	ath10k_txrx_tx_unref(htt, skb);
+}
+
+int ath10k_htt_h2t_ver_req_msg(struct ath10k_htt *htt)
+{
+	struct sk_buff *skb;
+	struct htt_cmd *cmd;
+	int len = 0;
+	int ret;
+
+	len += sizeof(cmd->hdr);
+	len += sizeof(cmd->ver_req);
+
+	skb = ath10k_htc_alloc_skb(len);
+	if (!skb)
+		return -ENOMEM;
+
+	skb_put(skb, len);
+	cmd = (struct htt_cmd *)skb->data;
+	cmd->hdr.msg_type = HTT_H2T_MSG_TYPE_VERSION_REQ;
+
+	ATH10K_SKB_CB(skb)->htt.is_conf = true;
+
+	ret = ath10k_htc_send(htt->ar->htc, htt->eid, skb);
+	if (ret) {
+		dev_kfree_skb_any(skb);
+		return ret;
+	}
+
+	return 0;
+}
+
+int ath10k_htt_send_rx_ring_cfg_ll(struct ath10k_htt *htt)
+{
+	struct sk_buff *skb;
+	struct htt_cmd *cmd;
+	struct htt_rx_ring_setup_ring *ring;
+	const int num_rx_ring = 1;
+	u16 flags;
+	u32 fw_idx;
+	int len;
+	int ret;
+
+	/*
+	 * the HW expects the buffer to be an integral number of 4-byte
+	 * "words"
+	 */
+	BUILD_BUG_ON(!IS_ALIGNED(HTT_RX_BUF_SIZE, 4));
+	BUILD_BUG_ON((HTT_RX_BUF_SIZE & HTT_MAX_CACHE_LINE_SIZE_MASK) != 0);
+
+	len = sizeof(cmd->hdr) + sizeof(cmd->rx_setup.hdr)
+	    + (sizeof(*ring) * num_rx_ring);
+	skb = ath10k_htc_alloc_skb(len);
+	if (!skb)
+		return -ENOMEM;
+
+	skb_put(skb, len);
+
+	cmd = (struct htt_cmd *)skb->data;
+	ring = &cmd->rx_setup.rings[0];
+
+	cmd->hdr.msg_type = HTT_H2T_MSG_TYPE_RX_RING_CFG;
+	cmd->rx_setup.hdr.num_rings = 1;
+
+	/* FIXME: do we need all of this? */
+	flags = 0;
+	flags |= HTT_RX_RING_FLAGS_MAC80211_HDR;
+	flags |= HTT_RX_RING_FLAGS_MSDU_PAYLOAD;
+	flags |= HTT_RX_RING_FLAGS_PPDU_START;
+	flags |= HTT_RX_RING_FLAGS_PPDU_END;
+	flags |= HTT_RX_RING_FLAGS_MPDU_START;
+	flags |= HTT_RX_RING_FLAGS_MPDU_END;
+	flags |= HTT_RX_RING_FLAGS_MSDU_START;
+	flags |= HTT_RX_RING_FLAGS_MSDU_END;
+	flags |= HTT_RX_RING_FLAGS_RX_ATTENTION;
+	flags |= HTT_RX_RING_FLAGS_FRAG_INFO;
+	flags |= HTT_RX_RING_FLAGS_UNICAST_RX;
+	flags |= HTT_RX_RING_FLAGS_MULTICAST_RX;
+	flags |= HTT_RX_RING_FLAGS_CTRL_RX;
+	flags |= HTT_RX_RING_FLAGS_MGMT_RX;
+	flags |= HTT_RX_RING_FLAGS_NULL_RX;
+	flags |= HTT_RX_RING_FLAGS_PHY_DATA_RX;
+
+	fw_idx = __le32_to_cpu(*htt->rx_ring.alloc_idx.vaddr);
+
+	ring->fw_idx_shadow_reg_paddr =
+		__cpu_to_le32(htt->rx_ring.alloc_idx.paddr);
+	ring->rx_ring_base_paddr = __cpu_to_le32(htt->rx_ring.base_paddr);
+	ring->rx_ring_len = __cpu_to_le16(htt->rx_ring.size);
+	ring->rx_ring_bufsize = __cpu_to_le16(HTT_RX_BUF_SIZE);
+	ring->flags = __cpu_to_le16(flags);
+	ring->fw_idx_init_val = __cpu_to_le16(fw_idx);
+
+#define desc_offset(x) (offsetof(struct htt_rx_desc, x) / 4)
+
+	ring->mac80211_hdr_offset = __cpu_to_le16(desc_offset(rx_hdr_status));
+	ring->msdu_payload_offset = __cpu_to_le16(desc_offset(msdu_payload));
+	ring->ppdu_start_offset = __cpu_to_le16(desc_offset(ppdu_start));
+	ring->ppdu_end_offset = __cpu_to_le16(desc_offset(ppdu_end));
+	ring->mpdu_start_offset = __cpu_to_le16(desc_offset(mpdu_start));
+	ring->mpdu_end_offset = __cpu_to_le16(desc_offset(mpdu_end));
+	ring->msdu_start_offset = __cpu_to_le16(desc_offset(msdu_start));
+	ring->msdu_end_offset = __cpu_to_le16(desc_offset(msdu_end));
+	ring->rx_attention_offset = __cpu_to_le16(desc_offset(attention));
+	ring->frag_info_offset = __cpu_to_le16(desc_offset(frag_info));
+
+#undef desc_offset
+
+	ATH10K_SKB_CB(skb)->htt.is_conf = true;
+
+	ret = ath10k_htc_send(htt->ar->htc, htt->eid, skb);
+	if (ret) {
+		dev_kfree_skb_any(skb);
+		return ret;
+	}
+
+	return 0;
+}
+
+int ath10k_htt_mgmt_tx(struct ath10k_htt *htt, struct sk_buff *msdu)
+{
+	struct device *dev = htt->ar->dev;
+	struct ath10k_skb_cb *skb_cb;
+	struct sk_buff *txdesc = NULL;
+	struct htt_cmd *cmd;
+	u8 vdev_id = ATH10K_SKB_CB(msdu)->htt.vdev_id;
+	int len = 0;
+	int msdu_id = -1;
+	int res;
+
+
+	res = ath10k_htt_tx_inc_pending(htt);
+	if (res)
+		return res;
+
+	len += sizeof(cmd->hdr);
+	len += sizeof(cmd->mgmt_tx);
+
+	txdesc = ath10k_htc_alloc_skb(len);
+	if (!txdesc) {
+		res = -ENOMEM;
+		goto err;
+	}
+
+	spin_lock_bh(&htt->tx_lock);
+	msdu_id = ath10k_htt_tx_alloc_msdu_id(htt);
+	if (msdu_id < 0) {
+		spin_unlock_bh(&htt->tx_lock);
+		res = msdu_id;
+		goto err;
+	}
+	htt->pending_tx[msdu_id] = txdesc;
+	spin_unlock_bh(&htt->tx_lock);
+
+	res = ath10k_skb_map(dev, msdu);
+	if (res)
+		goto err;
+
+	skb_put(txdesc, len);
+	cmd = (struct htt_cmd *)txdesc->data;
+	cmd->hdr.msg_type         = HTT_H2T_MSG_TYPE_MGMT_TX;
+	cmd->mgmt_tx.msdu_paddr = __cpu_to_le32(ATH10K_SKB_CB(msdu)->paddr);
+	cmd->mgmt_tx.len        = __cpu_to_le32(msdu->len);
+	cmd->mgmt_tx.desc_id    = __cpu_to_le32(msdu_id);
+	cmd->mgmt_tx.vdev_id    = __cpu_to_le32(vdev_id);
+	memcpy(cmd->mgmt_tx.hdr, msdu->data,
+	       min_t(int, msdu->len, HTT_MGMT_FRM_HDR_DOWNLOAD_LEN));
+
+	/* refcount is decremented by HTC and HTT completions until it reaches
+	 * zero and is freed */
+	skb_cb = ATH10K_SKB_CB(txdesc);
+	skb_cb->htt.msdu_id = msdu_id;
+	skb_cb->htt.refcount = 2;
+	skb_cb->htt.msdu = msdu;
+
+	res = ath10k_htc_send(htt->ar->htc, htt->eid, txdesc);
+	if (res)
+		goto err;
+
+	return 0;
+
+err:
+	ath10k_skb_unmap(dev, msdu);
+
+	if (txdesc)
+		dev_kfree_skb_any(txdesc);
+	if (msdu_id >= 0) {
+		spin_lock_bh(&htt->tx_lock);
+		htt->pending_tx[msdu_id] = NULL;
+		ath10k_htt_tx_free_msdu_id(htt, msdu_id);
+		spin_unlock_bh(&htt->tx_lock);
+	}
+	ath10k_htt_tx_dec_pending(htt);
+	return res;
+}
+
+int ath10k_htt_tx(struct ath10k_htt *htt, struct sk_buff *msdu)
+{
+	struct device *dev = htt->ar->dev;
+	struct htt_cmd *cmd;
+	struct htt_data_tx_desc_frag *tx_frags;
+	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)msdu->data;
+	struct ath10k_skb_cb *skb_cb;
+	struct sk_buff *txdesc = NULL;
+	struct sk_buff *txfrag = NULL;
+	u8 vdev_id = ATH10K_SKB_CB(msdu)->htt.vdev_id;
+	u8 tid;
+	int prefetch_len, desc_len, frag_len;
+	dma_addr_t frags_paddr;
+	int msdu_id = -1;
+	int res;
+	u8 flags0;
+	u16 flags1;
+
+	res = ath10k_htt_tx_inc_pending(htt);
+	if (res)
+		return res;
+
+	prefetch_len = min(htt->prefetch_len, msdu->len);
+	prefetch_len = roundup(prefetch_len, 4);
+
+	desc_len = sizeof(cmd->hdr) + sizeof(cmd->data_tx) + prefetch_len;
+	frag_len = sizeof(*tx_frags) * 2;
+
+	txdesc = ath10k_htc_alloc_skb(desc_len);
+	if (!txdesc) {
+		res = -ENOMEM;
+		goto err;
+	}
+
+	txfrag = dev_alloc_skb(frag_len);
+	if (!txfrag) {
+		res = -ENOMEM;
+		goto err;
+	}
+
+	if (!IS_ALIGNED((unsigned long)txdesc->data, 4)) {
+		ath10k_warn("htt alignment check failed. dropping packet.\n");
+		res = -EIO;
+		goto err;
+	}
+
+	spin_lock_bh(&htt->tx_lock);
+	msdu_id = ath10k_htt_tx_alloc_msdu_id(htt);
+	if (msdu_id < 0) {
+		spin_unlock_bh(&htt->tx_lock);
+		res = msdu_id;
+		goto err;
+	}
+	htt->pending_tx[msdu_id] = txdesc;
+	spin_unlock_bh(&htt->tx_lock);
+
+	res = ath10k_skb_map(dev, msdu);
+	if (res)
+		goto err;
+
+	/* tx fragment list must be terminated with zero-entry */
+	skb_put(txfrag, frag_len);
+	tx_frags = (struct htt_data_tx_desc_frag *)txfrag->data;
+	tx_frags[0].paddr = __cpu_to_le32(ATH10K_SKB_CB(msdu)->paddr);
+	tx_frags[0].len   = __cpu_to_le32(msdu->len);
+	tx_frags[1].paddr = __cpu_to_le32(0);
+	tx_frags[1].len   = __cpu_to_le32(0);
+
+	res = ath10k_skb_map(dev, txfrag);
+	if (res)
+		goto err;
+
+	ath10k_dbg(ATH10K_DBG_HTT, "txfrag 0x%llx msdu 0x%llx\n",
+		   (unsigned long long) ATH10K_SKB_CB(txfrag)->paddr,
+		   (unsigned long long) ATH10K_SKB_CB(msdu)->paddr);
+	ath10k_dbg_dump(ATH10K_DBG_HTT_DUMP, NULL, "txfrag: ",
+			txfrag->data, frag_len);
+	ath10k_dbg_dump(ATH10K_DBG_HTT_DUMP, NULL, "msdu: ",
+			msdu->data, msdu->len);
+
+	skb_put(txdesc, desc_len);
+	cmd = (struct htt_cmd *)txdesc->data;
+	memset(cmd, 0, desc_len);
+
+	tid = ATH10K_SKB_CB(msdu)->htt.tid;
+
+	ath10k_dbg(ATH10K_DBG_HTT, "htt data tx using tid %hhu\n", tid);
+
+	flags0  = 0;
+	if (!ieee80211_has_protected(hdr->frame_control))
+		flags0 |= HTT_DATA_TX_DESC_FLAGS0_NO_ENCRYPT;
+	flags0 |= HTT_DATA_TX_DESC_FLAGS0_MAC_HDR_PRESENT;
+	flags0 |= SM(ATH10K_HW_TXRX_NATIVE_WIFI,
+		     HTT_DATA_TX_DESC_FLAGS0_PKT_TYPE);
+
+	flags1  = 0;
+	flags1 |= SM((u16)vdev_id, HTT_DATA_TX_DESC_FLAGS1_VDEV_ID);
+	flags1 |= SM((u16)tid, HTT_DATA_TX_DESC_FLAGS1_EXT_TID);
+
+	frags_paddr = ATH10K_SKB_CB(txfrag)->paddr;
+
+	cmd->hdr.msg_type        = HTT_H2T_MSG_TYPE_TX_FRM;
+	cmd->data_tx.flags0      = flags0;
+	cmd->data_tx.flags1      = __cpu_to_le16(flags1);
+	cmd->data_tx.len         = __cpu_to_le16(msdu->len);
+	cmd->data_tx.id          = __cpu_to_le16(msdu_id);
+	cmd->data_tx.frags_paddr = __cpu_to_le32(frags_paddr);
+	cmd->data_tx.peerid      = __cpu_to_le32(HTT_INVALID_PEERID);
+
+	memcpy(cmd->data_tx.prefetch, msdu->data, prefetch_len);
+
+	/* refcount is decremented by HTC and HTT completions until it reaches
+	 * zero and is freed */
+	skb_cb = ATH10K_SKB_CB(txdesc);
+	skb_cb->htt.msdu_id = msdu_id;
+	skb_cb->htt.refcount = 2;
+	skb_cb->htt.txfrag = txfrag;
+	skb_cb->htt.msdu = msdu;
+
+	res = ath10k_htc_send(htt->ar->htc, htt->eid, txdesc);
+	if (res)
+		goto err;
+
+	return 0;
+err:
+	if (txfrag)
+		ath10k_skb_unmap(dev, txfrag);
+	if (txdesc)
+		dev_kfree_skb_any(txdesc);
+	if (txfrag)
+		dev_kfree_skb_any(txfrag);
+	if (msdu_id >= 0) {
+		spin_lock_bh(&htt->tx_lock);
+		htt->pending_tx[msdu_id] = NULL;
+		ath10k_htt_tx_free_msdu_id(htt, msdu_id);
+		spin_unlock_bh(&htt->tx_lock);
+	}
+	ath10k_htt_tx_dec_pending(htt);
+	ath10k_skb_unmap(dev, msdu);
+	return res;
+}