ath10k: use msdu headroom to store txfrag

Instead of allocating sk_buff for a mere 16-byte
tx fragment list buffer use headroom of the
original msdu sk_buff.

This decreases CPU cache pressure and improves
performance.

Measured improvement on AP135 is 560mbps ->
590mbps of UDP TX briding traffic.

Signed-off-by: Michal Kazior <michal.kazior@tieto.com>
Signed-off-by: Kalle Valo <kvalo@qca.qualcomm.com>

diff --git a/drivers/net/wireless/ath/ath10k/core.h b/drivers/net/wireless/ath/ath10k/core.h
index 4563f800a2911be53bb03f12c85055d7eb2c5058..292ad4577c986aa3efc9c4c377307005fcdddecf 100644 (file)
--- a/drivers/net/wireless/ath/ath10k/core.h
+++ b/drivers/net/wireless/ath/ath10k/core.h
@@ -54,7 +54,9 @@ struct ath10k_skb_cb {
                u8 vdev_id;
                u8 tid;
                bool is_offchan;
-               struct sk_buff *txfrag;
+
+               u8 frag_len;
+               u8 pad_len;
        } __packed htt;
 } __packed;
 

diff --git a/drivers/net/wireless/ath/ath10k/htt_tx.c b/drivers/net/wireless/ath/ath10k/htt_tx.c
index 5e738d80138fa3898d8b793a68e257df505ab3bd..3b93c6a01c6c618a7e2ae4a194a226be769984aa 100644 (file)
--- a/drivers/net/wireless/ath/ath10k/htt_tx.c
+++ b/drivers/net/wireless/ath/ath10k/htt_tx.c
@@ -307,7 +307,8 @@ int ath10k_htt_mgmt_tx(struct ath10k_htt *htt, struct sk_buff *msdu)
        struct device *dev = htt->ar->dev;
        struct sk_buff *txdesc = NULL;
        struct htt_cmd *cmd;
-       u8 vdev_id = ATH10K_SKB_CB(msdu)->htt.vdev_id;
+       struct ath10k_skb_cb *skb_cb = ATH10K_SKB_CB(msdu);
+       u8 vdev_id = skb_cb->htt.vdev_id;
        int len = 0;
        int msdu_id = -1;
        int res;
@@ -350,6 +351,9 @@ int ath10k_htt_mgmt_tx(struct ath10k_htt *htt, struct sk_buff *msdu)
        memcpy(cmd->mgmt_tx.hdr, msdu->data,
               min_t(int, msdu->len, HTT_MGMT_FRM_HDR_DOWNLOAD_LEN));
 
+       skb_cb->htt.frag_len = 0;
+       skb_cb->htt.pad_len = 0;
+
        res = ath10k_htc_send(&htt->ar->htc, htt->eid, txdesc);
        if (res)
                goto err_unmap_msdu;
@@ -377,13 +381,12 @@ int ath10k_htt_tx(struct ath10k_htt *htt, struct sk_buff *msdu)
        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 = ATH10K_SKB_CB(msdu);
        struct sk_buff *txdesc = NULL;
-       struct sk_buff *txfrag = NULL;
        bool use_frags;
        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 prefetch_len, desc_len;
        int msdu_id = -1;
        int res;
        u8 flags0;
@@ -407,7 +410,6 @@ int ath10k_htt_tx(struct ath10k_htt *htt, struct sk_buff *msdu)
        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) {
@@ -421,41 +423,44 @@ int ath10k_htt_tx(struct ath10k_htt *htt, struct sk_buff *msdu)
        use_frags = htt->target_version_major < 3 ||
                    !ieee80211_is_mgmt(hdr->frame_control);
 
-       if (use_frags) {
-               txfrag = dev_alloc_skb(frag_len);
-               if (!txfrag) {
-                       res = -ENOMEM;
-                       goto err_free_txdesc;
-               }
-       }
-
        if (!IS_ALIGNED((unsigned long)txdesc->data, 4)) {
                ath10k_warn("htt alignment check failed. dropping packet.\n");
                res = -EIO;
-               goto err_free_txfrag;
+               goto err_free_txdesc;
+       }
+
+       if (use_frags) {
+               skb_cb->htt.frag_len = sizeof(*tx_frags) * 2;
+               skb_cb->htt.pad_len = (unsigned long)msdu->data -
+                                     round_down((unsigned long)msdu->data, 4);
+
+               skb_push(msdu, skb_cb->htt.frag_len + skb_cb->htt.pad_len);
+       } else {
+               skb_cb->htt.frag_len = 0;
+               skb_cb->htt.pad_len = 0;
        }
 
        res = ath10k_skb_map(dev, msdu);
        if (res)
-               goto err_free_txfrag;
+               goto err_pull_txfrag;
 
        if (use_frags) {
+               dma_sync_single_for_cpu(dev, skb_cb->paddr, msdu->len,
+                                       DMA_TO_DEVICE);
+
                /* 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 = (struct htt_data_tx_desc_frag *)msdu->data;
+               tx_frags[0].paddr = __cpu_to_le32(skb_cb->paddr +
+                                                 skb_cb->htt.frag_len +
+                                                 skb_cb->htt.pad_len);
+               tx_frags[0].len   = __cpu_to_le32(msdu->len -
+                                                 skb_cb->htt.frag_len -
+                                                 skb_cb->htt.pad_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_unmap_msdu;
-
-               ath10k_dbg(ATH10K_DBG_HTT, "txfrag 0x%llx\n",
-                          (unsigned long long) ATH10K_SKB_CB(txfrag)->paddr);
-               ath10k_dbg_dump(ATH10K_DBG_HTT_DUMP, NULL, "txfrag: ",
-                               txfrag->data, frag_len);
+               dma_sync_single_for_device(dev, skb_cb->paddr, msdu->len,
+                                          DMA_TO_DEVICE);
        }
 
        ath10k_dbg(ATH10K_DBG_HTT, "msdu 0x%llx\n",
@@ -488,35 +493,28 @@ int ath10k_htt_tx(struct ath10k_htt *htt, struct sk_buff *msdu)
        flags1 |= HTT_DATA_TX_DESC_FLAGS1_CKSUM_L3_OFFLOAD;
        flags1 |= HTT_DATA_TX_DESC_FLAGS1_CKSUM_L4_OFFLOAD;
 
-       if (use_frags)
-               frags_paddr = ATH10K_SKB_CB(txfrag)->paddr;
-       else
-               frags_paddr = ATH10K_SKB_CB(msdu)->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.len         = __cpu_to_le16(msdu->len -
+                                                skb_cb->htt.frag_len -
+                                                skb_cb->htt.pad_len);
        cmd->data_tx.id          = __cpu_to_le16(msdu_id);
-       cmd->data_tx.frags_paddr = __cpu_to_le32(frags_paddr);
+       cmd->data_tx.frags_paddr = __cpu_to_le32(skb_cb->paddr);
        cmd->data_tx.peerid      = __cpu_to_le32(HTT_INVALID_PEERID);
 
-       memcpy(cmd->data_tx.prefetch, msdu->data, prefetch_len);
+       memcpy(cmd->data_tx.prefetch, hdr, prefetch_len);
 
        res = ath10k_htc_send(&htt->ar->htc, htt->eid, txdesc);
        if (res)
-               goto err_restore;
+               goto err_unmap_msdu;
 
        return 0;
 
-err_restore:
-       if (use_frags)
-               ath10k_skb_unmap(dev, txfrag);
 err_unmap_msdu:
        ath10k_skb_unmap(dev, msdu);
-err_free_txfrag:
-       if (use_frags)
-               dev_kfree_skb_any(txfrag);
+err_pull_txfrag:
+       skb_pull(msdu, skb_cb->htt.frag_len + skb_cb->htt.pad_len);
 err_free_txdesc:
        dev_kfree_skb_any(txdesc);
 err_free_msdu_id:

diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index 9112e6d6f75c338d5a18e3d3b6363a5996be663f..99a9bad3f398cc87238b1d1c37868b7585a795b3 100644 (file)
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -3342,6 +3342,10 @@ int ath10k_mac_register(struct ath10k *ar)
                        IEEE80211_HW_WANT_MONITOR_VIF |
                        IEEE80211_HW_AP_LINK_PS;
 
+       /* MSDU can have HTT TX fragment pushed in front. The additional 4
+        * bytes is used for padding/alignment if necessary. */
+       ar->hw->extra_tx_headroom += sizeof(struct htt_data_tx_desc_frag)*2 + 4;
+
        if (ar->ht_cap_info & WMI_HT_CAP_DYNAMIC_SMPS)
                ar->hw->flags |= IEEE80211_HW_SUPPORTS_DYNAMIC_SMPS;
 

diff --git a/drivers/net/wireless/ath/ath10k/txrx.c b/drivers/net/wireless/ath/ath10k/txrx.c
index 15395afae95770c0aa312f126883c39d73b2c45a..57931d0fae4b0c1e26167ea378118b16e177f173 100644 (file)
--- a/drivers/net/wireless/ath/ath10k/txrx.c
+++ b/drivers/net/wireless/ath/ath10k/txrx.c
@@ -49,7 +49,8 @@ void ath10k_txrx_tx_unref(struct ath10k_htt *htt,
 {
        struct device *dev = htt->ar->dev;
        struct ieee80211_tx_info *info;
-       struct sk_buff *msdu, *txfrag;
+       struct ath10k_skb_cb *skb_cb;
+       struct sk_buff *msdu;
        int ret;
 
        ath10k_dbg(ATH10K_DBG_HTT, "htt tx completion msdu_id %u discard %d no_ack %d\n",
@@ -62,20 +63,15 @@ void ath10k_txrx_tx_unref(struct ath10k_htt *htt,
        }
 
        msdu = htt->pending_tx[tx_done->msdu_id];
-       txfrag = ATH10K_SKB_CB(msdu)->htt.txfrag;
-
-       if (txfrag) {
-               ret = ath10k_skb_unmap(dev, txfrag);
-               if (ret)
-                       ath10k_warn("txfrag unmap failed (%d)\n", ret);
-
-               dev_kfree_skb_any(txfrag);
-       }
+       skb_cb = ATH10K_SKB_CB(msdu);
 
        ret = ath10k_skb_unmap(dev, msdu);
        if (ret)
                ath10k_warn("data skb unmap failed (%d)\n", ret);
 
+       if (skb_cb->htt.frag_len)
+               skb_pull(msdu, skb_cb->htt.frag_len + skb_cb->htt.pad_len);
+
        ath10k_report_offchan_tx(htt->ar, msdu);
 
        info = IEEE80211_SKB_CB(msdu);