1 files changed, 211 insertions, 57 deletions

diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index d2871757ec94..73f08d02f9c7 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -144,6 +144,56 @@ static struct netdev_queue *txring_txq(const struct ice_tx_ring *ring)
 }
 
 /**
+ * ice_clean_tstamp_ring - clean time stamp ring
+ * @tx_ring: Tx ring to clean the Time Stamp ring for
+ */
+static void ice_clean_tstamp_ring(struct ice_tx_ring *tx_ring)
+{
+	struct ice_tstamp_ring *tstamp_ring = tx_ring->tstamp_ring;
+	u32 size;
+
+	if (!tstamp_ring->desc)
+		return;
+
+	size = ALIGN(tstamp_ring->count * sizeof(struct ice_ts_desc),
+		     PAGE_SIZE);
+	memset(tstamp_ring->desc, 0, size);
+	tstamp_ring->next_to_use = 0;
+}
+
+/**
+ * ice_free_tstamp_ring - free time stamp resources per queue
+ * @tx_ring: Tx ring to free the Time Stamp ring for
+ */
+void ice_free_tstamp_ring(struct ice_tx_ring *tx_ring)
+{
+	struct ice_tstamp_ring *tstamp_ring = tx_ring->tstamp_ring;
+	u32 size;
+
+	if (!tstamp_ring->desc)
+		return;
+
+	ice_clean_tstamp_ring(tx_ring);
+	size = ALIGN(tstamp_ring->count * sizeof(struct ice_ts_desc),
+		     PAGE_SIZE);
+	dmam_free_coherent(tx_ring->dev, size, tstamp_ring->desc,
+			   tstamp_ring->dma);
+	tstamp_ring->desc = NULL;
+}
+
+/**
+ * ice_free_tx_tstamp_ring - free time stamp resources per Tx ring
+ * @tx_ring: Tx ring to free the Time Stamp ring for
+ */
+void ice_free_tx_tstamp_ring(struct ice_tx_ring *tx_ring)
+{
+	ice_free_tstamp_ring(tx_ring);
+	kfree_rcu(tx_ring->tstamp_ring, rcu);
+	tx_ring->tstamp_ring = NULL;
+	tx_ring->flags &= ~ICE_TX_FLAGS_TXTIME;
+}
+
+/**
  * ice_clean_tx_ring - Free any empty Tx buffers
  * @tx_ring: ring to be cleaned
  */
@@ -181,6 +231,9 @@ tx_skip_free:
 
 	/* cleanup Tx queue statistics */
 	netdev_tx_reset_queue(txring_txq(tx_ring));
+
+	if (ice_is_txtime_cfg(tx_ring))
+		ice_free_tx_tstamp_ring(tx_ring);
 }
 
 /**
@@ -332,6 +385,84 @@ static bool ice_clean_tx_irq(struct ice_tx_ring *tx_ring, int napi_budget)
 }
 
 /**
+ * ice_alloc_tstamp_ring - allocate the Time Stamp ring
+ * @tx_ring: Tx ring to allocate the Time Stamp ring for
+ *
+ * Return: 0 on success, negative on error
+ */
+static int ice_alloc_tstamp_ring(struct ice_tx_ring *tx_ring)
+{
+	struct ice_tstamp_ring *tstamp_ring;
+
+	/* allocate with kzalloc(), free with kfree_rcu() */
+	tstamp_ring = kzalloc(sizeof(*tstamp_ring), GFP_KERNEL);
+	if (!tstamp_ring)
+		return -ENOMEM;
+
+	tstamp_ring->tx_ring = tx_ring;
+	tx_ring->tstamp_ring = tstamp_ring;
+	tstamp_ring->desc = NULL;
+	tstamp_ring->count = ice_calc_ts_ring_count(tx_ring);
+	tx_ring->flags |= ICE_TX_FLAGS_TXTIME;
+	return 0;
+}
+
+/**
+ * ice_setup_tstamp_ring - allocate the Time Stamp ring
+ * @tx_ring: Tx ring to set up the Time Stamp ring for
+ *
+ * Return: 0 on success, negative on error
+ */
+static int ice_setup_tstamp_ring(struct ice_tx_ring *tx_ring)
+{
+	struct ice_tstamp_ring *tstamp_ring = tx_ring->tstamp_ring;
+	struct device *dev = tx_ring->dev;
+	u32 size;
+
+	/* round up to nearest page */
+	size = ALIGN(tstamp_ring->count * sizeof(struct ice_ts_desc),
+		     PAGE_SIZE);
+	tstamp_ring->desc = dmam_alloc_coherent(dev, size, &tstamp_ring->dma,
+						GFP_KERNEL);
+	if (!tstamp_ring->desc) {
+		dev_err(dev, "Unable to allocate memory for Time stamp Ring, size=%d\n",
+			size);
+		return -ENOMEM;
+	}
+
+	tstamp_ring->next_to_use = 0;
+	return 0;
+}
+
+/**
+ * ice_alloc_setup_tstamp_ring - Allocate and setup the Time Stamp ring
+ * @tx_ring: Tx ring to allocate and setup the Time Stamp ring for
+ *
+ * Return: 0 on success, negative on error
+ */
+int ice_alloc_setup_tstamp_ring(struct ice_tx_ring *tx_ring)
+{
+	struct device *dev = tx_ring->dev;
+	int err;
+
+	err = ice_alloc_tstamp_ring(tx_ring);
+	if (err) {
+		dev_err(dev, "Unable to allocate Time stamp ring for Tx ring %d\n",
+			tx_ring->q_index);
+		return err;
+	}
+
+	err = ice_setup_tstamp_ring(tx_ring);
+	if (err) {
+		dev_err(dev, "Unable to setup Time stamp ring for Tx ring %d\n",
+			tx_ring->q_index);
+		ice_free_tx_tstamp_ring(tx_ring);
+		return err;
+	}
+	return 0;
+}
+
+/**
  * ice_setup_tx_ring - Allocate the Tx descriptors
  * @tx_ring: the Tx ring to set up
  *
@@ -894,10 +1025,6 @@ ice_add_xdp_frag(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
 	__skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++, rx_buf->page,
 				   rx_buf->page_offset, size);
 	sinfo->xdp_frags_size += size;
-	/* remember frag count before XDP prog execution; bpf_xdp_adjust_tail()
-	 * can pop off frags but driver has to handle it on its own
-	 */
-	rx_ring->nr_frags = sinfo->nr_frags;
 
 	if (page_is_pfmemalloc(rx_buf->page))
 		xdp_buff_set_frag_pfmemalloc(xdp);
@@ -968,20 +1095,20 @@ ice_get_rx_buf(struct ice_rx_ring *rx_ring, const unsigned int size,
 /**
  * ice_get_pgcnts - grab page_count() for gathered fragments
  * @rx_ring: Rx descriptor ring to store the page counts on
+ * @ntc: the next to clean element (not included in this frame!)
  *
  * This function is intended to be called right before running XDP
  * program so that the page recycling mechanism will be able to take
  * a correct decision regarding underlying pages; this is done in such
  * way as XDP program can change the refcount of page
  */
-static void ice_get_pgcnts(struct ice_rx_ring *rx_ring)
+static void ice_get_pgcnts(struct ice_rx_ring *rx_ring, unsigned int ntc)
 {
-	u32 nr_frags = rx_ring->nr_frags + 1;
 	u32 idx = rx_ring->first_desc;
 	struct ice_rx_buf *rx_buf;
 	u32 cnt = rx_ring->count;
 
-	for (int i = 0; i < nr_frags; i++) {
+	while (idx != ntc) {
 		rx_buf = &rx_ring->rx_buf[idx];
 		rx_buf->pgcnt = page_count(rx_buf->page);
 
@@ -1035,10 +1162,9 @@ ice_build_skb(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp)
 		skb_metadata_set(skb, metasize);
 
 	if (unlikely(xdp_buff_has_frags(xdp)))
-		xdp_update_skb_shared_info(skb, nr_frags,
-					   sinfo->xdp_frags_size,
-					   nr_frags * xdp->frame_sz,
-					   xdp_buff_is_frag_pfmemalloc(xdp));
+		xdp_update_skb_frags_info(skb, nr_frags, sinfo->xdp_frags_size,
+					  nr_frags * xdp->frame_sz,
+					  xdp_buff_get_skb_flags(xdp));
 
 	return skb;
 }
@@ -1115,10 +1241,10 @@ ice_construct_skb(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp)
 		memcpy(&skinfo->frags[skinfo->nr_frags], &sinfo->frags[0],
 		       sizeof(skb_frag_t) * nr_frags);
 
-		xdp_update_skb_shared_info(skb, skinfo->nr_frags + nr_frags,
-					   sinfo->xdp_frags_size,
-					   nr_frags * xdp->frame_sz,
-					   xdp_buff_is_frag_pfmemalloc(xdp));
+		xdp_update_skb_frags_info(skb, skinfo->nr_frags + nr_frags,
+					  sinfo->xdp_frags_size,
+					  nr_frags * xdp->frame_sz,
+					  xdp_buff_get_skb_flags(xdp));
 	}
 
 	return skb;
@@ -1154,62 +1280,51 @@ ice_put_rx_buf(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf)
 }
 
 /**
- * ice_put_rx_mbuf - ice_put_rx_buf() caller, for all frame frags
+ * ice_put_rx_mbuf - ice_put_rx_buf() caller, for all buffers in frame
  * @rx_ring: Rx ring with all the auxiliary data
  * @xdp: XDP buffer carrying linear + frags part
- * @xdp_xmit: XDP_TX/XDP_REDIRECT verdict storage
- * @ntc: a current next_to_clean value to be stored at rx_ring
+ * @ntc: the next to clean element (not included in this frame!)
  * @verdict: return code from XDP program execution
  *
- * Walk through gathered fragments and satisfy internal page
- * recycle mechanism; we take here an action related to verdict
- * returned by XDP program;
+ * Called after XDP program is completed, or on error with verdict set to
+ * ICE_XDP_CONSUMED.
+ *
+ * Walk through buffers from first_desc to the end of the frame, releasing
+ * buffers and satisfying internal page recycle mechanism. The action depends
+ * on verdict from XDP program.
  */
 static void ice_put_rx_mbuf(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
-			    u32 *xdp_xmit, u32 ntc, u32 verdict)
+			    u32 ntc, u32 verdict)
 {
-	u32 nr_frags = rx_ring->nr_frags + 1;
 	u32 idx = rx_ring->first_desc;
 	u32 cnt = rx_ring->count;
-	u32 post_xdp_frags = 1;
 	struct ice_rx_buf *buf;
-	int i;
+	u32 xdp_frags = 0;
+	int i = 0;
 
 	if (unlikely(xdp_buff_has_frags(xdp)))
-		post_xdp_frags += xdp_get_shared_info_from_buff(xdp)->nr_frags;
+		xdp_frags = xdp_get_shared_info_from_buff(xdp)->nr_frags;
 
-	for (i = 0; i < post_xdp_frags; i++) {
+	while (idx != ntc) {
 		buf = &rx_ring->rx_buf[idx];
+		if (++idx == cnt)
+			idx = 0;
 
-		if (verdict & (ICE_XDP_TX | ICE_XDP_REDIR)) {
+		/* An XDP program could release fragments from the end of the
+		 * buffer. For these, we need to keep the pagecnt_bias as-is.
+		 * To do this, only adjust pagecnt_bias for fragments up to
+		 * the total remaining after the XDP program has run.
+		 */
+		if (verdict != ICE_XDP_CONSUMED)
 			ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz);
-			*xdp_xmit |= verdict;
-		} else if (verdict & ICE_XDP_CONSUMED) {
+		else if (i++ <= xdp_frags)
 			buf->pagecnt_bias++;
-		} else if (verdict == ICE_XDP_PASS) {
-			ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz);
-		}
 
 		ice_put_rx_buf(rx_ring, buf);
-
-		if (++idx == cnt)
-			idx = 0;
-	}
-	/* handle buffers that represented frags released by XDP prog;
-	 * for these we keep pagecnt_bias as-is; refcount from struct page
-	 * has been decremented within XDP prog and we do not have to increase
-	 * the biased refcnt
-	 */
-	for (; i < nr_frags; i++) {
-		buf = &rx_ring->rx_buf[idx];
-		ice_put_rx_buf(rx_ring, buf);
-		if (++idx == cnt)
-			idx = 0;
 	}
 
 	xdp->data = NULL;
 	rx_ring->first_desc = ntc;
-	rx_ring->nr_frags = 0;
 }
 
 /**
@@ -1317,6 +1432,10 @@ static int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
 		/* retrieve a buffer from the ring */
 		rx_buf = ice_get_rx_buf(rx_ring, size, ntc);
 
+		/* Increment ntc before calls to ice_put_rx_mbuf() */
+		if (++ntc == cnt)
+			ntc = 0;
+
 		if (!xdp->data) {
 			void *hard_start;
 
@@ -1325,24 +1444,23 @@ static int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
 			xdp_prepare_buff(xdp, hard_start, offset, size, !!offset);
 			xdp_buff_clear_frags_flag(xdp);
 		} else if (ice_add_xdp_frag(rx_ring, xdp, rx_buf, size)) {
-			ice_put_rx_mbuf(rx_ring, xdp, NULL, ntc, ICE_XDP_CONSUMED);
+			ice_put_rx_mbuf(rx_ring, xdp, ntc, ICE_XDP_CONSUMED);
 			break;
 		}
-		if (++ntc == cnt)
-			ntc = 0;
 
 		/* skip if it is NOP desc */
 		if (ice_is_non_eop(rx_ring, rx_desc))
 			continue;
 
-		ice_get_pgcnts(rx_ring);
+		ice_get_pgcnts(rx_ring, ntc);
 		xdp_verdict = ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_desc);
 		if (xdp_verdict == ICE_XDP_PASS)
 			goto construct_skb;
 		total_rx_bytes += xdp_get_buff_len(xdp);
 		total_rx_pkts++;
 
-		ice_put_rx_mbuf(rx_ring, xdp, &xdp_xmit, ntc, xdp_verdict);
+		ice_put_rx_mbuf(rx_ring, xdp, ntc, xdp_verdict);
+		xdp_xmit |= xdp_verdict & (ICE_XDP_TX | ICE_XDP_REDIR);
 
 		continue;
 construct_skb:
@@ -1355,7 +1473,7 @@ construct_skb:
 			rx_ring->ring_stats->rx_stats.alloc_buf_failed++;
 			xdp_verdict = ICE_XDP_CONSUMED;
 		}
-		ice_put_rx_mbuf(rx_ring, xdp, &xdp_xmit, ntc, xdp_verdict);
+		ice_put_rx_mbuf(rx_ring, xdp, ntc, xdp_verdict);
 
 		if (!skb)
 			break;
@@ -1835,10 +1953,46 @@ ice_tx_map(struct ice_tx_ring *tx_ring, struct ice_tx_buf *first,
 	/* notify HW of packet */
 	kick = __netdev_tx_sent_queue(txring_txq(tx_ring), first->bytecount,
 				      netdev_xmit_more());
-	if (kick)
-		/* notify HW of packet */
-		writel(i, tx_ring->tail);
+	if (!kick)
+		return;
 
+	if (ice_is_txtime_cfg(tx_ring)) {
+		struct ice_tstamp_ring *tstamp_ring = tx_ring->tstamp_ring;
+		u32 tstamp_count = tstamp_ring->count;
+		u32 j = tstamp_ring->next_to_use;
+		struct ice_ts_desc *ts_desc;
+		struct timespec64 ts;
+		u32 tstamp;
+
+		ts = ktime_to_timespec64(first->skb->tstamp);
+		tstamp = ts.tv_nsec >> ICE_TXTIME_CTX_RESOLUTION_128NS;
+
+		ts_desc = ICE_TS_DESC(tstamp_ring, j);
+		ts_desc->tx_desc_idx_tstamp = ice_build_tstamp_desc(i, tstamp);
+
+		j++;
+		if (j == tstamp_count) {
+			u32 fetch = tstamp_count - tx_ring->count;
+
+			j = 0;
+
+			/* To prevent an MDD, when wrapping the tstamp ring
+			 * create additional TS descriptors equal to the number
+			 * of the fetch TS descriptors value. HW will merge the
+			 * TS descriptors with the same timestamp value into a
+			 * single descriptor.
+			 */
+			for (; j < fetch; j++) {
+				ts_desc = ICE_TS_DESC(tstamp_ring, j);
+				ts_desc->tx_desc_idx_tstamp =
+				       ice_build_tstamp_desc(i, tstamp);
+			}
+		}
+		tstamp_ring->next_to_use = j;
+		writel_relaxed(j, tstamp_ring->tail);
+	} else {
+		writel_relaxed(i, tx_ring->tail);
+	}
 	return;
 
 dma_error: