-----Original Message-----
From: Zaremba, Larysa <redacted>
Sent: Tuesday, February 17, 2026 2:25 PM
To: bpf@vger.kernel.org
Cc: Zaremba, Larysa <redacted>; Claudiu Manoil
[off-list ref]; Vladimir Oltean [off-list ref];
Wei Fang [off-list ref]; Clark Wang [off-list ref];
Andrew Lunn [off-list ref]; David S. Miller
[off-list ref]; Eric Dumazet [off-list ref]; Jakub
Kicinski [off-list ref]; Paolo Abeni [off-list ref]; Nguyen,
Anthony L [off-list ref]; Kitszel, Przemyslaw
[off-list ref]; Alexei Starovoitov [off-list ref];
Daniel Borkmann [off-list ref]; Jesper Dangaard Brouer
[off-list ref]; John Fastabend [off-list ref];
Stanislav Fomichev [off-list ref]; Andrii Nakryiko
[off-list ref]; Martin KaFai Lau [off-list ref]; Eduard
Zingerman [off-list ref]; Song Liu [off-list ref]; Yonghong
Song [off-list ref]; KP Singh [off-list ref]; Hao Luo
[off-list ref]; Jiri Olsa [off-list ref]; Simon Horman
[off-list ref]; Shuah Khan [off-list ref]; Lobakin, Aleksander
[off-list ref]; Fijalkowski, Maciej
[off-list ref]; Bastien Curutchet (eBPF Foundation)
[off-list ref]; Vyavahare, Tushar
[off-list ref]; Jason Xing [off-list ref];
Ricardo B. Marlière [off-list ref]; Eelco Chaudron
[off-list ref]; Lorenzo Bianconi [off-list ref]; Toke
Hoiland-Jorgensen [off-list ref]; imx@lists.linux.dev;
netdev@vger.kernel.org; linux-kernel@vger.kernel.org; intel-wired-
lan@lists.osuosl.org; linux-kselftest@vger.kernel.org; Loktionov,
Aleksandr [off-list ref]; Dragos Tatulea
[off-list ref]
Subject: [PATCH bpf v3 6/9] i40e: use xdp.frame_sz as XDP RxQ info
frag_size

The only user of frag_size field in XDP RxQ info is
bpf_xdp_frags_increase_tail(). It clearly expects whole buffer size
instead of DMA write size. Different assumptions in i40e driver
configuration lead to negative tailroom.

Set frag_size to the same value as frame_sz in shared pages mode, use
new helper to set frag_size when AF_XDP ZC is active.

Fixes: a045d2f2d03d ("i40e: set xdp_rxq_info::frag_size")
Signed-off-by: Larysa Zaremba <redacted>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c

b/drivers/net/ethernet/intel/i40e/i40e_main.c
index eaa5b65e6daf..e012a50a0448 100644

--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c

@@ -3561,6 +3561,7 @@ static int i40e_configure_rx_ring(struct

i40e_ring *ring)
 	struct i40e_vsi *vsi = ring->vsi;
 	u32 chain_len = vsi->back->hw.func_caps.rx_buf_chain_len;
 	u16 pf_q = vsi->base_queue + ring->queue_index;
+	u32 xdp_frame_sz = i40e_rx_pg_size(ring) / 2;
 	struct i40e_hw *hw = &vsi->back->hw;
 	struct i40e_hmc_obj_rxq rx_ctx;
 	int err = 0;

@@ -3579,11 +3580,12 @@ static int i40e_configure_rx_ring(struct

i40e_ring *ring)

 	ring->xsk_pool = i40e_xsk_pool(ring);
 	if (ring->xsk_pool) {
+		xdp_frame_sz = xsk_pool_get_rx_frag_step(ring-

quoted

xsk_pool);

 		ring->rx_buf_len = xsk_pool_get_rx_frame_size(ring-

quoted

xsk_pool);

 		err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
 					 ring->queue_index,
 					 ring->q_vector->napi.napi_id,
-					 ring->rx_buf_len);
+					 xdp_frame_sz);
 		if (err)
 			return err;
 		err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,

@@ -3599,7 +3601,7 @@ static int i40e_configure_rx_ring(struct

i40e_ring *ring)
 		err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
 					 ring->queue_index,
 					 ring->q_vector->napi.napi_id,
-					 ring->rx_buf_len);
+					 xdp_frame_sz);
 		if (err)
 			return err;
 		err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,

@@ -3610,7 +3612,7 @@ static int i40e_configure_rx_ring(struct

i40e_ring *ring)
 	}

 skip:
-	xdp_init_buff(&ring->xdp, i40e_rx_pg_size(ring) / 2, &ring-

quoted

xdp_rxq);

+	xdp_init_buff(&ring->xdp, xdp_frame_sz, &ring->xdp_rxq);

 	rx_ctx.dbuff = DIV_ROUND_UP(ring->rx_buf_len,
 				    BIT_ULL(I40E_RXQ_CTX_DBUFF_SHIFT));
--
2.52.0