bnxt_en: Bound SW TPA IDs to prevent crashes

FW supports up to 1024 concurrent TPAs, so the FW TPA ID is in the range
0..1023 (see commit ec4d8e7cf024 ("bnxt_en: Add TPA ID mapping logic for
57500 chips.")). bnxt_alloc_agg_idx is intended to wrap the FW ID down to a
software ID which is used to index rxr->rx_tpa, and to generate a mapping
between FW IDs and the wrapped software ID.

On a 57608 with firmware version 233, the firmware advertises 32
concurrent TPAs. As of the commit under fixes, bp->max_tpa on this NIC
is set to 32.

If the software ID from bnxt_alloc_agg_idx is above 31, this results in
an invalid address being loaded on this line:

  tpa_info = &rxr->rx_tpa[agg_id];

because rx_tpa is allocated with only bp->max_tpa (32) entries. Writes
to tpa_info later in the code are out of bounds.

This bug results in a crash at boot:

Oops: general protection fault, kernel NULL pointer dereference 0x8: 0000 [#1] SMP NOPTI
RIP: 0010:bnxt_rx_pkt+0xc0/0x1560
RSP: 0018:ffffc900009b8c78 EFLAGS: 00010246
RAX: 0000000000000000 RBX: 0000000000000048 RCX: 0000000206682516
RDX: ffffc900009b8db4 RSI: 0000000000000000 RDI: 01ffffff038fe1c0
RBP: ffffc9006e687480 R08: ffffc9006e687000 R09: 0000000000003048
R10: 0000000000000480 R11: ffff8881c6083900 R12: 0000000006682516
R13: ffff8881c6095400 R14: 0000000000000016 R15: ffff8881c6b66680
FS:  0000000000000000(0000) GS:ffff88fef3c77000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007fc8bda40584 CR3: 000000807c812001 CR4: 0000000008772ef0
PKRU: 55555554
Call Trace:
 <IRQ>
 ? __netif_receive_skb_list_core+0x1ca/0x250
 __bnxt_poll_work+0x152/0x280
 bnxt_poll_p5+0x1cd/0x480
 __napi_poll+0x30/0x180
 net_rx_action+0x20b/0x3b0
 ? note_gp_changes+0x53/0xe0
 ? tick_setup_sched_timer+0x180/0x180
 ? __napi_schedule+0x9a/0xb0
 ? bnxt_msix+0x24/0x30
 handle_softirqs+0xdd/0x2c0
 __irq_exit_rcu.llvm.3171231171502365008+0x47/0xf0
 common_interrupt+0x85/0x90
 </IRQ>
 <TASK>
 asm_common_interrupt+0x22/0x40

This stack trace is from a crash triggered when an out of bounds rx_tpa
is dereferenced. The invalid write mentioned above is silent in this
particular crash.

Fix this by allocating rx_tpa with bp->max_tpa rounded up to the next
power of 2 (bp->max_tpa_roundup_size) entries and masking the FW TPA ID
with that size, so the wrapped ID can never index past the end of the
array.

Fixes: 54c28fab2fa5 ("bnxt_en: Set bp->max_tpa according to what the FW supports")
Reported-by: Raphael Cardoso Fernandes <raphaelcf@meta.com>
Suggested-by: Michael Chan <michael.chan@broadcom.com>
Cc: stable@vger.kernel.org
Signed-off-by: Joe Damato <joe@dama.to>
Link: https://patch.msgid.link/20260902015652.2421609-7-joe@dama.to
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

2 files changed, 18 insertions, 11 deletions

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 32c59b3d1cbc..d7728d0c5b6e 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -1534,14 +1534,16 @@ static int bnxt_discard_rx(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	return 0;
 }
 
-static u16 bnxt_alloc_agg_idx(struct bnxt_rx_ring_info *rxr, u16 agg_id)
+static u16 bnxt_alloc_agg_idx(struct bnxt *bp, 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;
+	u16 idx = agg_id & (bp->max_tpa_roundup_size - 1);
 
 	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)
+		idx = find_first_zero_bit(map->agg_idx_bmap,
+					  bp->max_tpa_roundup_size);
+		if (idx >= bp->max_tpa_roundup_size)
 			return INVALID_HW_RING_ID;
 	}
 	__set_bit(idx, map->agg_idx_bmap);
@@ -1606,7 +1608,7 @@ 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);
+		agg_id = bnxt_alloc_agg_idx(bp, 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,
@@ -3604,7 +3606,7 @@ static void bnxt_free_one_tpa_info_data(struct bnxt *bp,
 {
 	int i;
 
-	for (i = 0; i < bp->max_tpa; i++) {
+	for (i = 0; i < bp->max_tpa_roundup_size; i++) {
 		struct bnxt_tpa_info *tpa_info = &rxr->rx_tpa[i];
 		u8 *data = tpa_info->data;
 
@@ -3801,7 +3803,7 @@ static void bnxt_free_one_tpa_info(struct bnxt *bp,
 	kfree(rxr->rx_tpa_idx_map);
 	rxr->rx_tpa_idx_map = NULL;
 	if (rxr->rx_tpa) {
-		for (i = 0; i < bp->max_tpa; i++) {
+		for (i = 0; i < bp->max_tpa_roundup_size; i++) {
 			kfree(rxr->rx_tpa[i].agg_arr);
 			rxr->rx_tpa[i].agg_arr = NULL;
 		}
@@ -3827,13 +3829,14 @@ static int bnxt_alloc_one_tpa_info(struct bnxt *bp,
 	struct rx_agg_cmp *agg;
 	int i;
 
-	rxr->rx_tpa = kzalloc_objs(struct bnxt_tpa_info, bp->max_tpa);
+	rxr->rx_tpa = kzalloc_objs(struct bnxt_tpa_info,
+				   bp->max_tpa_roundup_size);
 	if (!rxr->rx_tpa)
 		return -ENOMEM;
 
 	if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS))
 		return 0;
-	for (i = 0; i < bp->max_tpa; i++) {
+	for (i = 0; i < bp->max_tpa_roundup_size; i++) {
 		agg = kzalloc_objs(*agg, MAX_SKB_FRAGS);
 		if (!agg)
 			return -ENOMEM;
@@ -3852,6 +3855,9 @@ static int bnxt_alloc_tpa_info(struct bnxt *bp)
 
 	bp->max_tpa = MAX_TPA;
 	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
+		/* TPA is not supported at all, so there is nothing to
+		 * allocate.
+		 */
 		if (!bp->max_tpa_v2)
 			return 0;
 		bp->max_tpa = min_t(u16, bp->max_tpa_v2, MAX_TPA_P5);
@@ -3859,6 +3865,7 @@ static int bnxt_alloc_tpa_info(struct bnxt *bp)
 		if (bp->max_tpa <= 32 && BNXT_CHIP_P5(bp) && !BNXT_NPAR(bp))
 			bp->max_tpa = MAX_TPA_P5;
 	}
+	bp->max_tpa_roundup_size = roundup_pow_of_two(bp->max_tpa);
 
 	for (i = 0; i < bp->rx_nr_rings; i++) {
 		struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i];
@@ -4571,7 +4578,7 @@ static int bnxt_alloc_one_tpa_info_data(struct bnxt *bp,
 	u8 *data;
 	int i;
 
-	for (i = 0; i < bp->max_tpa; i++) {
+	for (i = 0; i < bp->max_tpa_roundup_size; i++) {
 		data = __bnxt_alloc_rx_frag(bp, &mapping, rxr,
 					    GFP_KERNEL);
 		if (!data)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index dc5a16ec5943..c673b2ce4a0d 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -789,7 +789,6 @@ struct nqe_cn {
 
 #define MAX_TPA		64
 #define MAX_TPA_P5	256
-#define MAX_TPA_P5_MASK	(MAX_TPA_P5 - 1)
 #define MAX_TPA_SEGS_P5	0x3f
 
 #if (BNXT_PAGE_SHIFT == 16)
@@ -2381,6 +2380,7 @@ struct bnxt {
 
 	u16			max_tpa_v2;
 	u16			max_tpa;
+	u16			max_tpa_roundup_size;
 	u32			rx_buf_size;
 	u32			rx_buf_use_size;	/* useable size */
 	u16			rx_offset;