Merge: ice: fix Rx page leak on multi-buffer frames

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-10/-/merge_requests/1478

JIRA: https://issues.redhat.com/browse/RHEL-104682

ice: fix Rx page leak on multi-buffer frames

Signed-off-by: Petr Oros <poros@redhat.com>

Closes RHEL-104682

Approved-by: Kamal Heib <kheib@redhat.com>
Approved-by: Michal Schmidt <mschmidt@redhat.com>
Approved-by: CKI KWF Bot <cki-ci-bot+kwf-gitlab-com@redhat.com>

Merged-by: CKI GitLab Kmaint Pipeline Bot <26919896-cki-kmaint-pipeline-bot@users.noreply.gitlab.com>

Author: CKI KWF Bot

drivers/net/ethernet/intel/ice/ice_txrx.c

@@ -865,10 +865,6 @@ 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);
@@ -939,20 +935,20 @@ 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);
 
@@ -1125,62 +1121,51 @@ 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;
 }
 
 /**
@@ -1260,6 +1245,10 @@ 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;
 
@@ -1268,24 +1257,23 @@ 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:
@@ -1298,7 +1286,7 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
 			rx_ring->ring_stats->rx_stats.alloc_page_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;

drivers/net/ethernet/intel/ice/ice_txrx.h

@@ -358,7 +358,6 @@ struct ice_rx_ring {
 	struct ice_tx_ring *xdp_ring;
 	struct ice_rx_ring *next;	/* pointer to next ring in q_vector */
 	struct xsk_buff_pool *xsk_pool;
-	u32 nr_frags;
 	u16 max_frame;
 	u16 rx_buf_len;
 	dma_addr_t dma;			/* physical address of ring */