ioat1: trim ioat_dma_desc_sw

Save 4 bytes per software descriptor by transmitting tx_cnt in an unused
portion of the hardware descriptor.

Signed-off-by: Maciej Sosnowski <[e-mail]>
Signed-off-by: Dan Williams <[e-mail]>

drivers/dma/ioat/dma.c

···
 	dump_desc_dbg(ioat, chain_tail);
 	dump_desc_dbg(ioat, first);
 
-	ioat->pending += desc->tx_cnt;
+	ioat->pending += desc->hw->tx_cnt;
 	if (ioat->pending >= ioat_pending_level)
 		__ioat1_dma_memcpy_issue_pending(ioat);
 	spin_unlock_bh(&ioat->desc_lock);
···
 	spin_unlock_bh(&ioat->desc_lock);
 
 	desc->txd.flags = flags;
-	desc->tx_cnt = tx_cnt;
 	desc->len = total_len;
 	list_splice(&chain, &desc->txd.tx_list);
 	hw->ctl_f.int_en = !!(flags & DMA_PREP_INTERRUPT);
 	hw->ctl_f.compl_write = 1;
+	hw->tx_cnt = tx_cnt;
 	dump_desc_dbg(ioat, desc);
 
 	return &desc->txd;

drivers/dma/ioat/dma.h

···
  * @hw: hardware DMA descriptor
  * @node: this descriptor will either be on the free list,
  *     or attached to a transaction list (async_tx.tx_list)
- * @tx_cnt: number of descriptors required to complete the transaction
  * @txd: the generic software descriptor for all engines
  * @id: identifier for debug
  */
 struct ioat_desc_sw {
 	struct ioat_dma_descriptor *hw;
 	struct list_head node;
-	int tx_cnt;
 	size_t len;
 	struct dma_async_tx_descriptor txd;
 	#ifdef DEBUG

drivers/dma/ioat/hw.h

···
 	uint64_t	next;
 	uint64_t	rsv1;
 	uint64_t	rsv2;
-	uint64_t	user1;
+	/* store some driver data in an unused portion of the descriptor */
+	union {
+		uint64_t	user1;
+		uint64_t	tx_cnt;
+	};
 	uint64_t	user2;
 };
 #endif