i40e: introduce next_to_process to i40e_ring

Add a new field called next_to_process in the i40e_ring that is
advanced for every buffer and change the semantics of next_to_clean to
point to the first buffer of a packet. Driver will use next_to_process
in the same way next_to_clean was used previously.

For the non multi-buffer case, next_to_process and next_to_clean will
always be the same since each packet consists of a single buffer.
Signed-off-by: Tirthendu Sarkar <tirthendu.sarkar@intel.com>
Tested-by: Chandan Kumar Rout <chandanx.rout@intel.com> (A Contingent Worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>

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

@@ -1524,6 +1524,7 @@ void i40e_clean_rx_ring(struct i40e_ring *rx_ring)
 
 	rx_ring->next_to_alloc = 0;
 	rx_ring->next_to_clean = 0;
+	rx_ring->next_to_process = 0;
 	rx_ring->next_to_use = 0;
 }
 
@@ -1576,6 +1577,7 @@ int i40e_setup_rx_descriptors(struct i40e_ring *rx_ring)
 
 	rx_ring->next_to_alloc = 0;
 	rx_ring->next_to_clean = 0;
+	rx_ring->next_to_process = 0;
 	rx_ring->next_to_use = 0;
 
 	/* XDP RX-queue info only needed for RX rings exposed to XDP */
@@ -2076,7 +2078,7 @@ static struct i40e_rx_buffer *i40e_get_rx_buffer(struct i40e_ring *rx_ring,
 {
 	struct i40e_rx_buffer *rx_buffer;
 
-	rx_buffer = i40e_rx_bi(rx_ring, rx_ring->next_to_clean);
+	rx_buffer = i40e_rx_bi(rx_ring, rx_ring->next_to_process);
 	rx_buffer->page_count =
 #if (PAGE_SIZE < 8192)
 		page_count(rx_buffer->page);
@@ -2375,16 +2377,16 @@ void i40e_finalize_xdp_rx(struct i40e_ring *rx_ring, unsigned int xdp_res)
 }
 
 /**
- * i40e_inc_ntc: Advance the next_to_clean index
+ * i40e_inc_ntp: Advance the next_to_process index
  * @rx_ring: Rx ring
  **/
-static void i40e_inc_ntc(struct i40e_ring *rx_ring)
+static void i40e_inc_ntp(struct i40e_ring *rx_ring)
 {
-	u32 ntc = rx_ring->next_to_clean + 1;
+	u32 ntp = rx_ring->next_to_process + 1;
 
-	ntc = (ntc < rx_ring->count) ? ntc : 0;
-	rx_ring->next_to_clean = ntc;
-	prefetch(I40E_RX_DESC(rx_ring, ntc));
+	ntp = (ntp < rx_ring->count) ? ntp : 0;
+	rx_ring->next_to_process = ntp;
+	prefetch(I40E_RX_DESC(rx_ring, ntp));
 }
 
 /**
@@ -2421,6 +2423,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget,
 	xdp_prog = READ_ONCE(rx_ring->xdp_prog);
 
 	while (likely(total_rx_packets < (unsigned int)budget)) {
+		u16 ntp = rx_ring->next_to_process;
 		struct i40e_rx_buffer *rx_buffer;
 		union i40e_rx_desc *rx_desc;
 		unsigned int size;
@@ -2433,7 +2436,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget,
 			cleaned_count = 0;
 		}
 
-		rx_desc = I40E_RX_DESC(rx_ring, rx_ring->next_to_clean);
+		rx_desc = I40E_RX_DESC(rx_ring, ntp);
 
 		/* status_error_len will always be zero for unused descriptors
 		 * because it's cleared in cleanup, and overlaps with hdr_addr
@@ -2452,8 +2455,8 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget,
 			i40e_clean_programming_status(rx_ring,
 						      rx_desc->raw.qword[0],
 						      qword);
-			rx_buffer = i40e_rx_bi(rx_ring, rx_ring->next_to_clean);
-			i40e_inc_ntc(rx_ring);
+			rx_buffer = i40e_rx_bi(rx_ring, ntp);
+			i40e_inc_ntp(rx_ring);
 			i40e_reuse_rx_page(rx_ring, rx_buffer);
 			cleaned_count++;
 			continue;
@@ -2509,7 +2512,8 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget,
 		i40e_put_rx_buffer(rx_ring, rx_buffer);
 		cleaned_count++;
 
-		i40e_inc_ntc(rx_ring);
+		i40e_inc_ntp(rx_ring);
+		rx_ring->next_to_clean = rx_ring->next_to_process;
 		if (i40e_is_non_eop(rx_ring, rx_desc))
 			continue;
 

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

@@ -337,6 +337,10 @@ struct i40e_ring {
 	u8 dcb_tc;			/* Traffic class of ring */
 	u8 __iomem *tail;
 
+	/* Next descriptor to be processed; next_to_clean is updated only on
+	 * processing EOP descriptor
+	 */
+	u16 next_to_process;
 	/* high bit set means dynamic, use accessor routines to read/write.
 	 * hardware only supports 2us resolution for the ITR registers.
 	 * these values always store the USER setting, and must be converted