From 73670ddb91a4d22e1deb3efd962242de1ec48e90 Mon Sep 17 00:00:00 2001 From: Joshua Washington Date: Wed, 30 Sep 2026 14:47:33 -0700 Subject: [PATCH 1/3] gve: fix XSK buffer leak when rings are stopped GVE does not free XSK buffers when resetting ring state as a part of stopping queues. This causes all XSK buffers which are posted to the NIC to be leaked. Free XSK buffers attached to an allocated buf_state when stopping rings. This issue was hit in production. Fixes: c1fffc5d66a7 ("gve: implement DQO RX datapath and control path for AF_XDP zero-copy") Cc: stable@vger.kernel.org Reviewed-by: Tim Hostetler Reviewed-by: Jordan Rhee Signed-off-by: Joshua Washington Link: https://patch.msgid.link/20260930214735.3288780-2-joshwash@google.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/google/gve/gve_rx_dqo.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/net/ethernet/google/gve/gve_rx_dqo.c b/drivers/net/ethernet/google/gve/gve_rx_dqo.c index 5cf242b28557..a2c4a08ce68d 100644 --- a/drivers/net/ethernet/google/gve/gve_rx_dqo.c +++ b/drivers/net/ethernet/google/gve/gve_rx_dqo.c @@ -113,6 +113,12 @@ static void gve_rx_reset_ring_dqo(struct gve_priv *priv, int idx) gve_free_to_page_pool(rx, bs, false); else gve_free_qpl_page_dqo(bs); + + if (gve_buf_state_is_allocated(rx, bs) && + bs->xsk_buff) { + xsk_buff_free(bs->xsk_buff); + bs->xsk_buff = NULL; + } } } From 9fed6a8ab8a5bacba2c709cb19d2dd6d2fa9112e Mon Sep 17 00:00:00 2001 From: Joshua Washington Date: Wed, 30 Sep 2026 14:47:34 -0700 Subject: [PATCH 2/3] gve: fix XSK buffer leak on error descriptor When the error bit is set in the RX completion descriptor, the buf_state and its attached buffer should be freed. In the case of AF_XDP ZC, the XSK buffer was not freed, leading to a leak. This issue was caught by LLM. Fixes: c1fffc5d66a7 ("gve: implement DQO RX datapath and control path for AF_XDP zero-copy") Cc: stable@vger.kernel.org Reviewed-by: Jordan Rhee Reviewed-by: Tim Hostetler Signed-off-by: Joshua Washington Link: https://patch.msgid.link/20260930214735.3288780-3-joshwash@google.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/google/gve/gve_rx_dqo.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/google/gve/gve_rx_dqo.c b/drivers/net/ethernet/google/gve/gve_rx_dqo.c index a2c4a08ce68d..82ed5e48b00a 100644 --- a/drivers/net/ethernet/google/gve/gve_rx_dqo.c +++ b/drivers/net/ethernet/google/gve/gve_rx_dqo.c @@ -842,7 +842,12 @@ static int gve_rx_dqo(struct napi_struct *napi, struct gve_rx_ring *rx, } if (unlikely(compl_desc->rx_error)) { - gve_free_buffer(rx, buf_state); + if (buf_state->xsk_buff) { + xsk_buff_free(buf_state->xsk_buff); + gve_free_buf_state(rx, buf_state); + } else { + gve_free_buffer(rx, buf_state); + } return -EINVAL; } From 0cb6939a4dfefa822007b7a71986e06bc4f61f54 Mon Sep 17 00:00:00 2001 From: Joshua Washington Date: Wed, 30 Sep 2026 14:47:35 -0700 Subject: [PATCH 3/3] gve: fix napi_disable deadlock when attempting to disable XSK pools When disabling XSK pools, GVE calls the unlocked versions of napi_disable and napi_enable. However, the netdev lock has already been acquired before ndo_bpf is called because GVE supports queue management ops. Calling the unlocked versions of napi_disable/enable results in a deadlock when attempting to disable XSK pools, as the thread attempts to re-acquire a lock it already holds. Update the NAPI calls to use the locked versions. This issue was found in production. Fixes: 606048cbd834 ("net: designate XSK pool pointers in queues as "ops protected"") Cc: stable@vger.kernel.org Reviewed-by: Harshitha Ramamurthy Reviewed-by: Jordan Rhee Signed-off-by: Joshua Washington Link: https://patch.msgid.link/20260930214735.3288780-4-joshwash@google.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/google/gve/gve_main.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index 9cc343a16271..a6c18e2431cc 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -1708,17 +1708,17 @@ static int gve_xsk_pool_disable(struct net_device *dev, } napi_rx = &priv->ntfy_blocks[priv->rx[qid].ntfy_id].napi; - napi_disable(napi_rx); /* make sure current rx poll is done */ + napi_disable_locked(napi_rx); /* make sure current rx poll is done */ tx_qid = gve_xdp_tx_queue_id(priv, qid); napi_tx = &priv->ntfy_blocks[priv->tx[tx_qid].ntfy_id].napi; - napi_disable(napi_tx); /* make sure current tx poll is done */ + napi_disable_locked(napi_tx); /* make sure current tx poll is done */ gve_unreg_xsk_pool(priv, qid); smp_mb(); /* Make sure it is visible to the workers on datapath */ - napi_enable(napi_rx); - napi_enable(napi_tx); + napi_enable_locked(napi_rx); + napi_enable_locked(napi_tx); if (gve_is_gqi(priv)) { if (gve_rx_work_pending(&priv->rx[qid])) napi_schedule(napi_rx);