bnxt_en: Fix potential data corruption with HW GRO/LRO

Fix the max number of bits passed to find_first_zero_bit() in
bnxt_alloc_agg_idx().  We were incorrectly passing the number of
long words.  find_first_zero_bit() may fail to find a zero bit and
cause a wrong ID to be used.  If the wrong ID is already in use, this
can cause data corruption.  Sometimes an error like this can also be
seen:

bnxt_en 0000:83:00.0 enp131s0np0: TPA end agg_buf 2 != expected agg_bufs 1

Fix it by passing the correct number of bits MAX_TPA_P5.  Use
DECLARE_BITMAP() to more cleanly define the bitmap.  Add a sanity
check to warn if a bit cannot be found and reset the ring [MChan].

Fixes: ec4d8e7cf024 ("bnxt_en: Add TPA ID mapping logic for 57500 chips.")
Reviewed-by: Ray Jui <ray.jui@broadcom.com>
Signed-off-by: Srijit Bose <srijit.bose@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Reviewed-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Link: https://patch.msgid.link/20251231083625.3911652-1-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

2 files changed, 13 insertions, 6 deletions

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index d17d0ea89c36..d160e54ac121 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -1482,9 +1482,11 @@ static u16 bnxt_alloc_agg_idx(struct bnxt_rx_ring_info *rxr, u16 agg_id)
 	struct bnxt_tpa_idx_map *map = rxr->rx_tpa_idx_map;
 	u16 idx = agg_id & MAX_TPA_P5_MASK;
 
-	if (test_bit(idx, map->agg_idx_bmap))
-		idx = find_first_zero_bit(map->agg_idx_bmap,
-					  BNXT_AGG_IDX_BMAP_SIZE);
+	if (test_bit(idx, map->agg_idx_bmap)) {
+		idx = find_first_zero_bit(map->agg_idx_bmap, MAX_TPA_P5);
+		if (idx >= MAX_TPA_P5)
+			return INVALID_HW_RING_ID;
+	}
 	__set_bit(idx, map->agg_idx_bmap);
 	map->agg_id_tbl[agg_id] = idx;
 	return idx;
@@ -1548,6 +1550,13 @@ static void bnxt_tpa_start(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
 	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
 		agg_id = TPA_START_AGG_ID_P5(tpa_start);
 		agg_id = bnxt_alloc_agg_idx(rxr, agg_id);
+		if (unlikely(agg_id == INVALID_HW_RING_ID)) {
+			netdev_warn(bp->dev, "Unable to allocate agg ID for ring %d, agg 0x%x\n",
+				    rxr->bnapi->index,
+				    TPA_START_AGG_ID_P5(tpa_start));
+			bnxt_sched_reset_rxr(bp, rxr);
+			return;
+		}
 	} else {
 		agg_id = TPA_START_AGG_ID(tpa_start);
 	}
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index f5f07a7e6b29..f88e7769a838 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1080,11 +1080,9 @@ struct bnxt_tpa_info {
 	struct rx_agg_cmp	*agg_arr;
 };
 
-#define BNXT_AGG_IDX_BMAP_SIZE	(MAX_TPA_P5 / BITS_PER_LONG)
-
 struct bnxt_tpa_idx_map {
 	u16		agg_id_tbl[1024];
-	unsigned long	agg_idx_bmap[BNXT_AGG_IDX_BMAP_SIZE];
+	DECLARE_BITMAP(agg_idx_bmap, MAX_TPA_P5);
 };
 
 struct bnxt_rx_ring_info {