i40e/i40evf: fix TSO accounting

The TSO logic in the transmit path had some assumptions that
have been broken now that the kernel can send as much as 32kB
in a single skb->frag[.] entry, even on a system with 4kB pages.

This fixes the assumptions and allows the kernel to operate
as efficiently as possible with both SENDFILE and SEND.

In addition, the hardware limit of data contained in a descriptor is
changed to the next power of two below where it currently is in
order to align to a power of two value, preventing a single byte
of data in a descriptor.

Change-ID: I6af1f0b87c1458e10644dbd47541591075a52651
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>

drivers/net/ethernet/intel/i40e/i40e_txrx.c

@@ -2170,9 +2170,7 @@ static int i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size)
 static int i40e_xmit_descriptor_count(struct sk_buff *skb,
 				      struct i40e_ring *tx_ring)
 {
-#if PAGE_SIZE > I40E_MAX_DATA_PER_TXD
 	unsigned int f;
-#endif
 	int count = 0;
 
 	/* need: 1 descriptor per page * PAGE_SIZE/I40E_MAX_DATA_PER_TXD,
@@ -2181,12 +2179,9 @@ static int i40e_xmit_descriptor_count(struct sk_buff *skb,
 	 *       + 1 desc for context descriptor,
 	 * otherwise try next time
 	 */
-#if PAGE_SIZE > I40E_MAX_DATA_PER_TXD
 	for (f = 0; f < skb_shinfo(skb)->nr_frags; f++)
 		count += TXD_USE_COUNT(skb_shinfo(skb)->frags[f].size);
-#else
-	count += skb_shinfo(skb)->nr_frags;
-#endif
+
 	count += TXD_USE_COUNT(skb_headlen(skb));
 	if (i40e_maybe_stop_tx(tx_ring, count + 4 + 1)) {
 		tx_ring->tx_stats.tx_busy++;

drivers/net/ethernet/intel/i40e/i40e_txrx.h

@@ -117,11 +117,11 @@ enum i40e_dyn_idx_t {
 #define i40e_rx_desc i40e_32byte_rx_desc
 
 #define I40E_MIN_TX_LEN		17
-#define I40E_MAX_DATA_PER_TXD	16383	/* aka 16kB - 1 */
+#define I40E_MAX_DATA_PER_TXD	8192
 
 /* Tx Descriptors needed, worst case */
 #define TXD_USE_COUNT(S) DIV_ROUND_UP((S), I40E_MAX_DATA_PER_TXD)
-#define DESC_NEEDED ((MAX_SKB_FRAGS * TXD_USE_COUNT(PAGE_SIZE)) + 4)
+#define DESC_NEEDED (MAX_SKB_FRAGS + 4)
 
 #define I40E_TX_FLAGS_CSUM		(u32)(1)
 #define I40E_TX_FLAGS_HW_VLAN		(u32)(1 << 1)

drivers/net/ethernet/intel/i40evf/i40e_txrx.c

@@ -1511,9 +1511,7 @@ static int i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size)
 static int i40e_xmit_descriptor_count(struct sk_buff *skb,
 				      struct i40e_ring *tx_ring)
 {
-#if PAGE_SIZE > I40E_MAX_DATA_PER_TXD
 	unsigned int f;
-#endif
 	int count = 0;
 
 	/* need: 1 descriptor per page * PAGE_SIZE/I40E_MAX_DATA_PER_TXD,
@@ -1522,12 +1520,9 @@ static int i40e_xmit_descriptor_count(struct sk_buff *skb,
 	 *       + 1 desc for context descriptor,
 	 * otherwise try next time
 	 */
-#if PAGE_SIZE > I40E_MAX_DATA_PER_TXD
 	for (f = 0; f < skb_shinfo(skb)->nr_frags; f++)
 		count += TXD_USE_COUNT(skb_shinfo(skb)->frags[f].size);
-#else
-	count += skb_shinfo(skb)->nr_frags;
-#endif
+
 	count += TXD_USE_COUNT(skb_headlen(skb));
 	if (i40e_maybe_stop_tx(tx_ring, count + 4 + 1)) {
 		tx_ring->tx_stats.tx_busy++;

drivers/net/ethernet/intel/i40evf/i40e_txrx.h

@@ -117,11 +117,11 @@ enum i40e_dyn_idx_t {
 #define i40e_rx_desc i40e_32byte_rx_desc
 
 #define I40E_MIN_TX_LEN		17
-#define I40E_MAX_DATA_PER_TXD	16383	/* aka 16kB - 1 */
+#define I40E_MAX_DATA_PER_TXD	8192
 
 /* Tx Descriptors needed, worst case */
 #define TXD_USE_COUNT(S) DIV_ROUND_UP((S), I40E_MAX_DATA_PER_TXD)
-#define DESC_NEEDED ((MAX_SKB_FRAGS * TXD_USE_COUNT(PAGE_SIZE)) + 4)
+#define DESC_NEEDED (MAX_SKB_FRAGS + 4)
 
 #define I40E_TX_FLAGS_CSUM		(u32)(1)
 #define I40E_TX_FLAGS_HW_VLAN		(u32)(1 << 1)