[PATCH 3.16 367/410] net: systemport: Rewrite __bcm_sysport_tx_reclaim()

[Ben Hutchings]

3.16.57-rc1 review patch.  If anyone has any objections, please let me know.

------------------

From: Florian Fainelli <f.fainelli@xxxxxxxxx>

commit 484d802d0f2f29c335563fcac2a8facf174a1bbc upstream.

There is no need for complex checking between the last consumed index
and current consumed index, a simple subtraction will do.

This also eliminates the possibility of a permanent transmit queue stall
under the following conditions:

- one CPU bursts ring->size worth of traffic (up to 256 buffers), to the
  point where we run out of free descriptors, so we stop the transmit
  queue at the end of bcm_sysport_xmit()

- because of our locking, we have the transmit process disable
  interrupts which means we can be blocking the TX reclamation process

- when TX reclamation finally runs, we will be computing the difference
  between ring->c_index (last consumed index by SW) and what the HW
  reports through its register

- this register is masked with (ring->size - 1) = 0xff, which will lead
  to stripping the upper bits of the index (register is 16-bits wide)

- we will be computing last_tx_cn as 0, which means there is no work to
  be done, and we never wake-up the transmit queue, leaving it
  permanently disabled

A practical example is e.g: ring->c_index aka last_c_index = 12, we
pushed 256 entries, HW consumer index = 268, we mask it with 0xff = 12,
so last_tx_cn == 0, nothing happens.

Fixes: 80105befdb4b ("net: systemport: add Broadcom SYSTEMPORT Ethernet MAC driver")
Signed-off-by: Florian Fainelli <f.fainelli@xxxxxxxxx>
Signed-off-by: David S. Miller <davem@xxxxxxxxxxxxx>
[bwh: Backported to 3.16: adjust context]
Signed-off-by: Ben Hutchings <ben@xxxxxxxxxxxxxxx>
---
 drivers/net/ethernet/broadcom/bcmsysport.c | 33 ++++++++++------------
 drivers/net/ethernet/broadcom/bcmsysport.h |  2 +-
 2 files changed, 16 insertions(+), 19 deletions(-)

--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -584,37 +584,33 @@ static unsigned int __bcm_sysport_tx_rec
 					     struct bcm_sysport_tx_ring *ring)
 {
 	struct net_device *ndev = priv->netdev;
-	unsigned int c_index, last_c_index, last_tx_cn, num_tx_cbs;
 	unsigned int pkts_compl = 0, bytes_compl = 0;
+	unsigned int txbds_processed = 0;
 	struct bcm_sysport_cb *cb;
+	unsigned int txbds_ready;
+	unsigned int c_index;
 	u32 hw_ind;
 
 	/* Compute how many descriptors have been processed since last call */
 	hw_ind = tdma_readl(priv, TDMA_DESC_RING_PROD_CONS_INDEX(ring->index));
 	c_index = (hw_ind >> RING_CONS_INDEX_SHIFT) & RING_CONS_INDEX_MASK;
-	ring->p_index = (hw_ind & RING_PROD_INDEX_MASK);
-
-	last_c_index = ring->c_index;
-	num_tx_cbs = ring->size;
-
-	c_index &= (num_tx_cbs - 1);
-
-	if (c_index >= last_c_index)
-		last_tx_cn = c_index - last_c_index;
-	else
-		last_tx_cn = num_tx_cbs - last_c_index + c_index;
+	txbds_ready = (c_index - ring->c_index) & RING_CONS_INDEX_MASK;
 
 	netif_dbg(priv, tx_done, ndev,
-			"ring=%d c_index=%d last_tx_cn=%d last_c_index=%d\n",
-			ring->index, c_index, last_tx_cn, last_c_index);
+		  "ring=%d old_c_index=%u c_index=%u txbds_ready=%u\n",
+		  ring->index, ring->c_index, c_index, txbds_ready);
 
-	while (last_tx_cn-- > 0) {
-		cb = ring->cbs + last_c_index;
+	while (txbds_processed < txbds_ready) {
+		cb = &ring->cbs[ring->clean_index];
 		bcm_sysport_tx_reclaim_one(priv, cb, &bytes_compl, &pkts_compl);
 
 		ring->desc_count++;
-		last_c_index++;
-		last_c_index &= (num_tx_cbs - 1);
+		txbds_processed++;
+
+		if (likely(ring->clean_index < ring->size - 1))
+			ring->clean_index++;
+		else
+			ring->clean_index = 0;
 	}
 
 	ring->c_index = c_index;
@@ -1036,6 +1032,7 @@ static int bcm_sysport_init_tx_ring(stru
 	netif_napi_add(priv->netdev, &ring->napi, bcm_sysport_tx_poll, 64);
 	ring->index = index;
 	ring->size = size;
+	ring->clean_index = 0;
 	ring->alloc_size = ring->size;
 	ring->desc_cpu = p;
 	ring->desc_count = ring->size;
--- a/drivers/net/ethernet/broadcom/bcmsysport.h
+++ b/drivers/net/ethernet/broadcom/bcmsysport.h
@@ -624,7 +624,7 @@ struct bcm_sysport_tx_ring {
 	unsigned int	desc_count;	/* Number of descriptors */
 	unsigned int	curr_desc;	/* Current descriptor */
 	unsigned int	c_index;	/* Last consumer index */
-	unsigned int	p_index;	/* Current producer index */
+	unsigned int	clean_index;	/* Current clean index */
 	struct bcm_sysport_cb *cbs;	/* Transmit control blocks */
 	struct dma_desc	*desc_cpu;	/* CPU view of the descriptor */
 	struct bcm_sysport_priv *priv;	/* private context backpointer */