[PATCH 2/2] mac80211: add NEED_ALIGNED4_SKBS hw flag

[Janusz Dziedzic <janusz.dziedzic@tieto.com>]

HW/driver should set NEED_ALIGNED4_SKBS flag in case
require aligned skbs to four-byte boundaries.
This affect only TX direction.

Padding is added after ieee80211_hdr, before IV/LLC.

Before we have to do memmove(hdrlen) twice in the
dirver. Once before we pass this to HW and next
in tx completion (to be sure monitor will report
this tx frame correctly).

With this patch we can skip this memmove() and save CPU.

Currently this was tested with ath9k, both hw/sw crypt for
wep/tkip/ccmp.

Signed-off-by: Janusz Dziedzic <janusz.dziedzic@tieto.com>
---
 include/net/mac80211.h     |  3 +++
 net/mac80211/debugfs.c     |  1 +
 net/mac80211/ieee80211_i.h | 23 +++++++++++++++++++++++
 net/mac80211/sta_info.h    |  2 +-
 net/mac80211/status.c      | 13 +++++++++++++
 net/mac80211/tkip.c        |  4 +++-
 net/mac80211/tx.c          | 21 +++++++++++++++------
 net/mac80211/util.c        |  3 ++-
 8 files changed, 61 insertions(+), 9 deletions(-)

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 31337f8..561605c 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -1961,6 +1961,8 @@ struct ieee80211_txq {
  *	reordering buffer internally, guaranteeing mac80211 receives frames in
  *	order and does not need to manage its own reorder buffer or BA session
  *	timeout.
+ * @IEEE80211_HW_NEEDS_ALIGNED4_SKBS: Driver need aligned skbs to four-byte.
+ *	Padding will be added after ieee80211_hdr, before IV/LLC.
  *
  * @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays
  */
@@ -1999,6 +2001,7 @@ enum ieee80211_hw_flags {
 	IEEE80211_HW_BEACON_TX_STATUS,
 	IEEE80211_HW_NEEDS_UNIQUE_STA_ADDR,
 	IEEE80211_HW_SUPPORTS_REORDERING_BUFFER,
+	IEEE80211_HW_NEEDS_ALIGNED4_SKBS,
 
 	/* keep last, obviously */
 	NUM_IEEE80211_HW_FLAGS
diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c
index 4ab5c52..c48905e 100644
--- a/net/mac80211/debugfs.c
+++ b/net/mac80211/debugfs.c
@@ -127,6 +127,7 @@ static const char *hw_flag_names[] = {
 	FLAG(BEACON_TX_STATUS),
 	FLAG(NEEDS_UNIQUE_STA_ADDR),
 	FLAG(SUPPORTS_REORDERING_BUFFER),
+	FLAG(NEEDS_ALIGNED4_SKBS),
 #undef FLAG
 };
 
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 81a476a..0687f94 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -1476,6 +1476,29 @@ ieee80211_have_rx_timestamp(struct ieee80211_rx_status *status)
 	return false;
 }
 
+static inline unsigned int
+ieee80211_hdr_padsize(struct ieee80211_hw *hw, unsigned int hdrlen)
+{
+	/*
+	 * While hdrlen is already aligned to two-byte boundaries,
+	 * simple check with & 2 will return correct padsize.
+	 */
+	if (ieee80211_hw_check(hw, NEEDS_ALIGNED4_SKBS))
+		return hdrlen & 2;
+	return 0;
+}
+
+static inline unsigned int
+ieee80211_padded_hdrlen(struct ieee80211_hw *hw, __le16 fc)
+{
+	unsigned int hdrlen;
+
+	hdrlen = ieee80211_hdrlen(fc);
+	hdrlen += ieee80211_hdr_padsize(hw, hdrlen);
+
+	return hdrlen;
+}
+
 u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local,
 				     struct ieee80211_rx_status *status,
 				     unsigned int mpdu_len,
diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h
index f4d3899..c432f4a 100644
--- a/net/mac80211/sta_info.h
+++ b/net/mac80211/sta_info.h
@@ -271,7 +271,7 @@ struct ieee80211_fast_tx {
 	u8 hdr_len;
 	u8 sa_offs, da_offs, pn_offs;
 	u8 band;
-	u8 hdr[30 + 2 + IEEE80211_FAST_XMIT_MAX_IV +
+	u8 hdr[30 + 2 + 2 + IEEE80211_FAST_XMIT_MAX_IV +
 	       sizeof(rfc1042_header)];
 
 	struct rcu_head rcu_head;
diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index 6101deb..d2b0273 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -683,9 +683,22 @@ void ieee80211_tx_monitor(struct ieee80211_local *local, struct sk_buff *skb,
 	struct sk_buff *skb2;
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
 	struct ieee80211_sub_if_data *sdata;
+	struct ieee80211_hdr *hdr = (void *)skb->data;
 	struct net_device *prev_dev = NULL;
+	unsigned int hdrlen, padsize;
 	int rtap_len;
 
+	/* Remove padding if was added */
+	if (ieee80211_hw_check(&local->hw, NEEDS_ALIGNED4_SKBS)) {
+		hdrlen = ieee80211_hdrlen(hdr->frame_control);
+		padsize = ieee80211_hdr_padsize(&local->hw, hdrlen);
+
+		if (padsize && skb->len > hdrlen + padsize) {
+			memmove(skb->data + padsize, skb->data, hdrlen);
+			skb_pull(skb, padsize);
+		}
+	}
+
 	/* send frame to monitor interfaces now */
 	rtap_len = ieee80211_tx_radiotap_len(info);
 	if (WARN_ON_ONCE(skb_headroom(skb) < rtap_len)) {
diff --git a/net/mac80211/tkip.c b/net/mac80211/tkip.c
index 0ae2077..b3ab779 100644
--- a/net/mac80211/tkip.c
+++ b/net/mac80211/tkip.c
@@ -201,10 +201,12 @@ void ieee80211_get_tkip_p2k(struct ieee80211_key_conf *keyconf,
 {
 	struct ieee80211_key *key = (struct ieee80211_key *)
 			container_of(keyconf, struct ieee80211_key, conf);
+	struct ieee80211_hw *hw = &key->local->hw;
 	const u8 *tk = &key->conf.key[NL80211_TKIP_DATA_OFFSET_ENCR_KEY];
 	struct tkip_ctx *ctx = &key->u.tkip.tx;
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
-	const u8 *data = (u8 *)hdr + ieee80211_hdrlen(hdr->frame_control);
+	const u8 *data = (u8 *)hdr + ieee80211_padded_hdrlen(hw,
+							hdr->frame_control);
 	u32 iv32 = get_unaligned_le32(&data[4]);
 	u16 iv16 = data[2] | (data[0] << 8);
 
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index cd4c361..3c2fad3 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -1162,8 +1162,7 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata,
 	info->flags &= ~IEEE80211_TX_INTFL_NEED_TXPROCESSING;
 
 	hdr = (struct ieee80211_hdr *) skb->data;
-
-	tx->hdrlen = ieee80211_hdrlen(hdr->frame_control);
+	tx->hdrlen = ieee80211_padded_hdrlen(&local->hw, hdr->frame_control);
 
 	if (likely(sta)) {
 		if (!IS_ERR(sta))
@@ -1795,7 +1794,7 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb,
 		goto fail;
 
 	hdr = (struct ieee80211_hdr *)(skb->data + len_rthdr);
-	hdrlen = ieee80211_hdrlen(hdr->frame_control);
+	hdrlen = ieee80211_padded_hdrlen(&local->hw, hdr->frame_control);
 
 	if (skb->len < len_rthdr + hdrlen)
 		goto fail;
@@ -2020,7 +2019,7 @@ static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata,
 	struct ieee80211_chanctx_conf *chanctx_conf;
 	struct ieee80211_sub_if_data *ap_sdata;
 	enum ieee80211_band band;
-	int ret;
+	int padsize, ret;
 
 	if (IS_ERR(sta))
 		sta = NULL;
@@ -2237,6 +2236,9 @@ static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata,
 		hdrlen += 2;
 	}
 
+	/* Check aligned4 skb required */
+	padsize = ieee80211_hdr_padsize(&sdata->local->hw, hdrlen);
+
 	/*
 	 * Drop unicast frames to unauthorised stations unless they are
 	 * EAPOL frames from the local station.
@@ -2323,6 +2325,7 @@ static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata,
 	h_pos -= skip_header_bytes;
 
 	head_need = hdrlen + encaps_len + meshhdrlen - skb_headroom(skb);
+	head_need += padsize;
 
 	/*
 	 * So we need to modify the skb header and hence need a copy of
@@ -2361,6 +2364,9 @@ static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata,
 	}
 #endif
 
+	if (padsize)
+		memset(skb_push(skb, padsize), 0, padsize);
+
 	if (ieee80211_is_data_qos(fc)) {
 		__le16 *qos_control;
 
@@ -2374,8 +2380,8 @@ static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata,
 	} else
 		memcpy(skb_push(skb, hdrlen), &hdr, hdrlen);
 
-	nh_pos += hdrlen;
-	h_pos += hdrlen;
+	nh_pos += hdrlen + padsize;
+	h_pos += hdrlen + padsize;
 
 	/* Update skb pointers to various headers since this modified frame
 	 * is going to go through Linux networking code that may potentially
@@ -2544,6 +2550,9 @@ void ieee80211_check_fast_xmit(struct sta_info *sta)
 		fc |= cpu_to_le16(IEEE80211_STYPE_QOS_DATA);
 	}
 
+	/* Check aligned4 skb required */
+	build.hdr_len += ieee80211_hdr_padsize(&local->hw, build.hdr_len);
+
 	/* We store the key here so there's no point in using rcu_dereference()
 	 * but that's fine because the code that changes the pointers will call
 	 * this function after doing so. For a single CPU that would be enough,
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index b3c6515..6e39835 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -1223,6 +1223,7 @@ void ieee80211_send_auth(struct ieee80211_sub_if_data *sdata,
 			 u32 tx_flags)
 {
 	struct ieee80211_local *local = sdata->local;
+	struct ieee80211_hw *hw = &local->hw;
 	struct sk_buff *skb;
 	struct ieee80211_mgmt *mgmt;
 	unsigned int hdrlen;
@@ -1250,7 +1251,7 @@ void ieee80211_send_auth(struct ieee80211_sub_if_data *sdata,
 		memcpy(skb_put(skb, extra_len), extra, extra_len);
 
 	if (auth_alg == WLAN_AUTH_SHARED_KEY && transaction == 3) {
-		hdrlen = ieee80211_hdrlen(mgmt->frame_control);
+		hdrlen = ieee80211_padded_hdrlen(hw, mgmt->frame_control);
 		mgmt->frame_control |= cpu_to_le16(IEEE80211_FCTL_PROTECTED);
 		err = ieee80211_wep_encrypt(local, skb, hdrlen, key,
 					    key_len, key_idx);
-- 
1.9.1