[PATCH net] qede: Fix NULL pointer dereference in TPA fragment processing

[PATCH net] qede: Fix NULL pointer dereference in TPA fragment processing

[Vaibhav Nagare]

  Under memory pressure, the qede driver encounters NULL pointer
  dereferences when processing TPA continuation fragments because:
  1. qede_fill_frag_skb() does not validate the page pointer before use
  2. qede_tpa_end() checks error state AFTER calling qede_fill_frag_skb()

  The crash occurs when:
  1. System experiences memory pressure (GFP_ATOMIC allocations fail)
  2. qede_alloc_rx_buffer() returns -ENOMEM, leaving sw_rx_data->data NULL
  3. qede_tpa_start() sets QEDE_AGG_STATE_ERROR on SKB allocation failure
  4. Hardware delivers TPA_CONT and TPA_END events for this aggregation
  5. qede_tpa_end() calls qede_fill_frag_skb() before checking error state
  6. qede_fill_frag_skb() accesses NULL pointer in skb_fill_page_desc()
  7. Kernel panics with NULL pointer dereference

Example crash from production system:
  BUG: unable to handle kernel NULL pointer dereference at 0x8
  RIP: qede_fill_frag_skb+0x96/0x430 [qede]
  Call Trace:
    qede_rx_int+0xb06/0x1de0
    qede_poll+0x2f4/0x6c0
    __napi_poll+0x2d/0x130

Observed on HPE Synergy 480 Gen11 running RHEL 8.10
(4.18.0-553.134.1.el8_10.x86_64), but the vulnerable code path
exists in mainline.

Fix by:
1. Adding NULL page validation in qede_fill_frag_skb() before dereferencing
2. Checking error state EARLY in qede_tpa_end() before processing fragments
3. Checking error state in qede_tpa_cont() to skip fragment processing

This allows the system to survive memory pressure by dropping packets
instead of crashing.

Fixes: 55482edc25f0 ("qede: Add slowpath/fastpath support and enable hardware GRO")
Cc: stable@vger.kernel.org

Signed-off-by: Vaibhav Nagare <vnagare@redhat.com>
---
 drivers/net/ethernet/qlogic/qede/qede_fp.c | 25 ++++++++++++++++++++--
 1 file changed, 23 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c
index 33e18bb69774..95b5cfcc43c2 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_fp.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c
@@ -670,13 +670,22 @@ static int qede_fill_frag_skb(struct qede_dev *edev,
 							 NUM_RX_BDS_MAX];
 	struct qede_agg_info *tpa_info = &rxq->tpa_info[tpa_agg_index];
 	struct sk_buff *skb = tpa_info->skb;
+	struct page *page = current_bd->data;
 
 	if (unlikely(tpa_info->state != QEDE_AGG_STATE_START))
 		goto out;
 
+	/* Avoid NULL pointer dereference when under severe memory pressure */
+	if (unlikely(!page)) {
+		DP_NOTICE(edev,
+			  "Failed to allocate RX buffer for TPA agg %u\n",
+			  tpa_agg_index);
+		goto out;
+	}
+
 	/* Add one frag and update the appropriate fields in the skb */
 	skb_fill_page_desc(skb, tpa_info->frag_id++,
-			   current_bd->data,
+			   page,
 			   current_bd->page_offset + rxq->rx_headroom,
 			   len_on_bd);
 
@@ -684,7 +693,7 @@ static int qede_fill_frag_skb(struct qede_dev *edev,
 		/* Incr page ref count to reuse on allocation failure
 		 * so that it doesn't get freed while freeing SKB.
 		 */
-		page_ref_inc(current_bd->data);
+		page_ref_inc(page);
 		goto out;
 	}
 
@@ -959,8 +968,16 @@ static inline void qede_tpa_cont(struct qede_dev *edev,
 				 struct qede_rx_queue *rxq,
 				 struct eth_fast_path_rx_tpa_cont_cqe *cqe)
 {
+	struct qede_agg_info *tpa_info = &rxq->tpa_info[cqe->tpa_agg_index];
 	int i;
 
+	/* Don't process fragments if TPA start failed */
+	if (unlikely(tpa_info->state != QEDE_AGG_STATE_START)) {
+		for (i = 0; i < ARRAY_SIZE(cqe->len_list) && cqe->len_list[i]; i++)
+			qede_recycle_rx_bd_ring(rxq, 1);
+		return;
+	}
+
 	for (i = 0; i < ARRAY_SIZE(cqe->len_list) && cqe->len_list[i]; i++)
 		qede_fill_frag_skb(edev, rxq, cqe->tpa_agg_index,
 				   le16_to_cpu(cqe->len_list[i]));
@@ -982,6 +999,10 @@ static int qede_tpa_end(struct qede_dev *edev,
 	tpa_info = &rxq->tpa_info[cqe->tpa_agg_index];
 	skb = tpa_info->skb;
 
+	/* Drop the packet if TPA start failed */
+	if (unlikely(tpa_info->state != QEDE_AGG_STATE_START || !skb))
+		goto err;
+
 	if (tpa_info->buffer.page_offset == PAGE_SIZE)
 		dma_unmap_page(rxq->dev, tpa_info->buffer.mapping,
 			       PAGE_SIZE, rxq->data_direction);
-- 
2.54.0