ath10k: use local memory instead of shadow descriptor in ce_send

Currently to avoid uncached memory access while filling up copy engine
descriptors, shadow descriptors are used. This can be optimized further
by removing shadow descriptors. To achieve that first shadow ring
dependency in ce_send is removed by creating local copy of the
descriptor on stack and make a one-shot copy into the "uncached"
descriptor.

Signed-off-by: Rajkumar Manoharan <rmanohar@qti.qualcomm.com>
Signed-off-by: Kalle Valo <kvalo@qca.qualcomm.com>
diff --git a/drivers/net/wireless/ath/ath10k/ce.c b/drivers/net/wireless/ath/ath10k/ce.c
index 84220c3..f63376b 100644
--- a/drivers/net/wireless/ath/ath10k/ce.c
+++ b/drivers/net/wireless/ath/ath10k/ce.c
@@ -274,7 +274,7 @@
 {
 	struct ath10k *ar = ce_state->ar;
 	struct ath10k_ce_ring *src_ring = ce_state->src_ring;
-	struct ce_desc *desc, *sdesc;
+	struct ce_desc *desc, sdesc;
 	unsigned int nentries_mask = src_ring->nentries_mask;
 	unsigned int sw_index = src_ring->sw_index;
 	unsigned int write_index = src_ring->write_index;
@@ -294,7 +294,6 @@
 
 	desc = CE_SRC_RING_TO_DESC(src_ring->base_addr_owner_space,
 				   write_index);
-	sdesc = CE_SRC_RING_TO_DESC(src_ring->shadow_base, write_index);
 
 	desc_flags |= SM(transfer_id, CE_DESC_FLAGS_META_DATA);
 
@@ -303,11 +302,11 @@
 	if (flags & CE_SEND_FLAG_BYTE_SWAP)
 		desc_flags |= CE_DESC_FLAGS_BYTE_SWAP;
 
-	sdesc->addr   = __cpu_to_le32(buffer);
-	sdesc->nbytes = __cpu_to_le16(nbytes);
-	sdesc->flags  = __cpu_to_le16(desc_flags);
+	sdesc.addr   = __cpu_to_le32(buffer);
+	sdesc.nbytes = __cpu_to_le16(nbytes);
+	sdesc.flags  = __cpu_to_le16(desc_flags);
 
-	*desc = *sdesc;
+	*desc = sdesc;
 
 	src_ring->per_transfer_context[write_index] = per_transfer_context;
 
@@ -614,7 +613,7 @@
 	if (read_index == sw_index)
 		return -EIO;
 
-	sbase = src_ring->shadow_base;
+	sbase = src_ring->base_addr_owner_space;
 	sdesc = CE_SRC_RING_TO_DESC(sbase, sw_index);
 
 	/* Return data from completed source descriptor */