stmmac: optimize tx desc management

This patch is to optimize the way to manage the TDES inside the
xmit function. When prepare the frame, some settings (e.g. OWN
bit) can be merged. This has been reworked to improve the tx
performances.
Signed-off-by: Fabrice Gasnier <fabrice.gasnier@st.com>
Signed-off-by: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Signed-off-by: Alexandre TORGUE <alexandre.torgue@st.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/stmicro/stmmac/chain_mode.c

@@ -50,7 +50,9 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum)
 		return -1;
 	priv->tx_skbuff_dma[entry].buf = desc->des2;
 	priv->tx_skbuff_dma[entry].len = bmax;
-	priv->hw->desc->prepare_tx_desc(desc, 1, bmax, csum, STMMAC_CHAIN_MODE);
+	/* do not close the descriptor and do not set own bit */
+	priv->hw->desc->prepare_tx_desc(desc, 1, bmax, csum, STMMAC_CHAIN_MODE,
+					0, false);
 
 	while (len != 0) {
 		priv->tx_skbuff[entry] = NULL;
@@ -66,8 +68,8 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum)
 			priv->tx_skbuff_dma[entry].buf = desc->des2;
 			priv->tx_skbuff_dma[entry].len = bmax;
 			priv->hw->desc->prepare_tx_desc(desc, 0, bmax, csum,
-							STMMAC_CHAIN_MODE);
-			priv->hw->desc->set_tx_owner(desc);
+							STMMAC_CHAIN_MODE, 1,
+							false);
 			len -= bmax;
 			i++;
 		} else {
@@ -78,9 +80,10 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum)
 				return -1;
 			priv->tx_skbuff_dma[entry].buf = desc->des2;
 			priv->tx_skbuff_dma[entry].len = len;
+			/* last descriptor can be set now */
 			priv->hw->desc->prepare_tx_desc(desc, 0, len, csum,
-							STMMAC_CHAIN_MODE);
-			priv->hw->desc->set_tx_owner(desc);
+							STMMAC_CHAIN_MODE, 1,
+							true);
 			len = 0;
 		}
 	}

drivers/net/ethernet/stmicro/stmmac/common.h

@@ -338,12 +338,11 @@ struct stmmac_desc_ops {
 
 	/* Invoked by the xmit function to prepare the tx descriptor */
 	void (*prepare_tx_desc) (struct dma_desc *p, int is_fs, int len,
-				 int csum_flag, int mode);
+				 bool csum_flag, int mode, bool tx_own,
+				 bool ls_ic);
 	/* Set/get the owner of the descriptor */
 	void (*set_tx_owner) (struct dma_desc *p);
 	int (*get_tx_owner) (struct dma_desc *p);
-	/* Invoked by the xmit function to close the tx descriptor */
-	void (*close_tx_desc) (struct dma_desc *p);
 	/* Clean the tx descriptor as soon as the tx irq is received */
 	void (*release_tx_desc) (struct dma_desc *p, int mode);
 	/* Clear interrupt on tx frame completion. When this bit is

drivers/net/ethernet/stmicro/stmmac/enh_desc.c

@@ -302,7 +302,8 @@ static void enh_desc_release_tx_desc(struct dma_desc *p, int mode)
 }
 
 static void enh_desc_prepare_tx_desc(struct dma_desc *p, int is_fs, int len,
-				     int csum_flag, int mode)
+				     bool csum_flag, int mode, bool tx_own,
+				     bool ls_ic)
 {
 	unsigned int tdes0 = p->des0;
 
@@ -316,6 +317,19 @@ static void enh_desc_prepare_tx_desc(struct dma_desc *p, int is_fs, int len,
 	else
 		tdes0 &= ~(TX_CIC_FULL << ETDES0_CHECKSUM_INSERTION_SHIFT);
 
+	if (tx_own)
+		tdes0 |= ETDES0_OWN;
+
+	if (is_fs & tx_own)
+		/* When the own bit, for the first frame, has to be set, all
+		 * descriptors for the same frame has to be set before, to
+		 * avoid race condition.
+		 */
+		wmb();
+
+	if (ls_ic)
+		tdes0 |= ETDES0_LAST_SEGMENT | ETDES0_INTERRUPT;
+
 	p->des0 = tdes0;
 
 	if (mode == STMMAC_CHAIN_MODE)
@@ -329,11 +343,6 @@ static void enh_desc_clear_tx_ic(struct dma_desc *p)
 	p->des0 &= ~ETDES0_INTERRUPT;
 }
 
-static void enh_desc_close_tx_desc(struct dma_desc *p)
-{
-	p->des0 |= ETDES0_LAST_SEGMENT | ETDES0_INTERRUPT;
-}
-
 static int enh_desc_get_rx_frame_len(struct dma_desc *p, int rx_coe_type)
 {
 	unsigned int csum = 0;
@@ -403,7 +412,6 @@ const struct stmmac_desc_ops enh_desc_ops = {
 	.release_tx_desc = enh_desc_release_tx_desc,
 	.prepare_tx_desc = enh_desc_prepare_tx_desc,
 	.clear_tx_ic = enh_desc_clear_tx_ic,
-	.close_tx_desc = enh_desc_close_tx_desc,
 	.get_tx_ls = enh_desc_get_tx_ls,
 	.set_tx_owner = enh_desc_set_tx_owner,
 	.set_rx_owner = enh_desc_set_rx_owner,

drivers/net/ethernet/stmicro/stmmac/norm_desc.c

@@ -185,7 +185,8 @@ static void ndesc_release_tx_desc(struct dma_desc *p, int mode)
 }
 
 static void ndesc_prepare_tx_desc(struct dma_desc *p, int is_fs, int len,
-				  int csum_flag, int mode)
+				  bool csum_flag, int mode, bool tx_own,
+				  bool ls_ic)
 {
 	unsigned int tdes1 = p->des1;
 
@@ -199,6 +200,12 @@ static void ndesc_prepare_tx_desc(struct dma_desc *p, int is_fs, int len,
 	else
 		tdes1 &= ~(TX_CIC_FULL << TDES1_CHECKSUM_INSERTION_SHIFT);
 
+	if (tx_own)
+		tdes1 |= TDES0_OWN;
+
+	if (ls_ic)
+		tdes1 |= TDES1_LAST_SEGMENT | TDES1_INTERRUPT;
+
 	p->des1 = tdes1;
 
 	if (mode == STMMAC_CHAIN_MODE)
@@ -212,11 +219,6 @@ static void ndesc_clear_tx_ic(struct dma_desc *p)
 	p->des1 &= ~TDES1_INTERRUPT;
 }
 
-static void ndesc_close_tx_desc(struct dma_desc *p)
-{
-	p->des1 |= TDES1_LAST_SEGMENT | TDES1_INTERRUPT;
-}
-
 static int ndesc_get_rx_frame_len(struct dma_desc *p, int rx_coe_type)
 {
 	unsigned int csum = 0;
@@ -278,7 +280,6 @@ const struct stmmac_desc_ops ndesc_ops = {
 	.release_tx_desc = ndesc_release_tx_desc,
 	.prepare_tx_desc = ndesc_prepare_tx_desc,
 	.clear_tx_ic = ndesc_clear_tx_ic,
-	.close_tx_desc = ndesc_close_tx_desc,
 	.get_tx_ls = ndesc_get_tx_ls,
 	.set_tx_owner = ndesc_set_tx_owner,
 	.set_rx_owner = ndesc_set_rx_owner,

drivers/net/ethernet/stmicro/stmmac/ring_mode.c

@@ -61,7 +61,7 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum)
 
 		desc->des3 = desc->des2 + BUF_SIZE_4KiB;
 		priv->hw->desc->prepare_tx_desc(desc, 1, bmax, csum,
-						STMMAC_RING_MODE);
+						STMMAC_RING_MODE, 0, false);
 		wmb();
 		priv->tx_skbuff[entry] = NULL;
 		entry = STMMAC_GET_ENTRY(entry, DMA_TX_SIZE);
@@ -81,9 +81,8 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum)
 
 		desc->des3 = desc->des2 + BUF_SIZE_4KiB;
 		priv->hw->desc->prepare_tx_desc(desc, 0, len, csum,
-						STMMAC_RING_MODE);
+						STMMAC_RING_MODE, 1, true);
 		wmb();
-		priv->hw->desc->set_tx_owner(desc);
 	} else {
 		desc->des2 = dma_map_single(priv->device, skb->data,
 					    nopaged_len, DMA_TO_DEVICE);
@@ -94,7 +93,7 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum)
 		priv->tx_skbuff_dma[entry].is_jumbo = true;
 		desc->des3 = desc->des2 + BUF_SIZE_4KiB;
 		priv->hw->desc->prepare_tx_desc(desc, 1, nopaged_len, csum,
-						STMMAC_RING_MODE);
+						STMMAC_RING_MODE, 0, true);
 	}
 
 	priv->cur_tx = entry;

drivers/net/ethernet/stmicro/stmmac/stmmac_main.c

@@ -1991,8 +1991,10 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 			goto dma_map_err;
 		priv->tx_skbuff_dma[entry].buf = desc->des2;
 		priv->tx_skbuff_dma[entry].len = nopaged_len;
+		/* do not set the own at this stage */
 		priv->hw->desc->prepare_tx_desc(desc, 1, nopaged_len,
-						csum_insertion, priv->mode);
+						csum_insertion, priv->mode, 0,
+						nfrags == 0);
 	} else {
 		desc = first;
 		entry = priv->hw->mode->jumbo_frm(priv, skb, csum_insertion);
@@ -2003,6 +2005,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 	for (i = 0; i < nfrags; i++) {
 		const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
 		int len = skb_frag_size(frag);
+		bool last_segment = (i == (nfrags - 1));
 
 		priv->tx_skbuff[entry] = NULL;
 		entry = STMMAC_GET_ENTRY(entry, DMA_TX_SIZE);
@@ -2021,19 +2024,12 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 		priv->tx_skbuff_dma[entry].map_as_page = true;
 		priv->tx_skbuff_dma[entry].len = len;
 		priv->hw->desc->prepare_tx_desc(desc, 0, len, csum_insertion,
-						priv->mode);
-		wmb();
-		priv->hw->desc->set_tx_owner(desc);
-		wmb();
+						priv->mode, 1, last_segment);
+		priv->tx_skbuff_dma[entry].last_segment = last_segment;
 	}
 
 	priv->tx_skbuff[entry] = skb;
 
-	/* Finalize the latest segment. */
-	priv->hw->desc->close_tx_desc(desc);
-	priv->tx_skbuff_dma[entry].last_segment = true;
-
-	wmb();
 	/* According to the coalesce parameter the IC bit for the latest
 	 * segment could be reset and the timer re-started to invoke the
 	 * stmmac_tx function. This approach takes care about the fragments.