The per-CPU variables used during bpf_prog_run_xdp() invocation and later during xdp_do_redirect() rely on disabled BH for their protection. Without locking in local_bh_disable() on PREEMPT_RT these data structure require explicit locking.
This is a follow-up on the previous change which introduced bpf_run_lock.redirect_lock and uses it now within drivers. The simple way is to acquire the lock before bpf_prog_run_xdp() is invoked and hold it until the end of function. This does not always work because some drivers (cpsw, atlantic) invoke xdp_do_flush() in the same context. Acquiring the lock in bpf_prog_run_xdp() and dropping in xdp_do_redirect() (without touching drivers) does not work because not all driver, which use bpf_prog_run_xdp(), do support XDP_REDIRECT (and invoke xdp_do_redirect()). Ideally the minimal locking scope would be bpf_prog_run_xdp() + xdp_do_redirect() and everything else (error recovery, DMA unmapping, free/ alloc of memory, …) would happen outside of the locked section. Cc: "K. Y. Srinivasan" <[email protected]> Cc: Alexei Starovoitov <[email protected]> Cc: AngeloGioacchino Del Regno <[email protected]> Cc: Dexuan Cui <[email protected]> Cc: Dimitris Michailidis <[email protected]> Cc: Felix Fietkau <[email protected]> Cc: Haiyang Zhang <[email protected]> Cc: Horatiu Vultur <[email protected]> Cc: Jeroen de Borst <[email protected]> Cc: Jesper Dangaard Brouer <[email protected]> Cc: John Crispin <[email protected]> Cc: John Fastabend <[email protected]> Cc: Lorenzo Bianconi <[email protected]> Cc: Mark Lee <[email protected]> Cc: Matthias Brugger <[email protected]> Cc: Praveen Kaligineedi <[email protected]> Cc: Sean Wang <[email protected]> Cc: Shailend Chand <[email protected]> Cc: [email protected] Cc: Wei Liu <[email protected]> Cc: [email protected] Cc: [email protected] Cc: [email protected] Signed-off-by: Sebastian Andrzej Siewior <[email protected]> --- drivers/net/ethernet/fungible/funeth/funeth_rx.c | 1 + drivers/net/ethernet/google/gve/gve_rx.c | 12 +++++++----- drivers/net/ethernet/mediatek/mtk_eth_soc.c | 1 + drivers/net/ethernet/microchip/lan966x/lan966x_xdp.c | 1 + drivers/net/ethernet/microsoft/mana/mana_bpf.c | 1 + 5 files changed, 11 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/fungible/funeth/funeth_rx.c b/drivers/net/ethernet/fungible/funeth/funeth_rx.c index 7e2584895de39..e7b1382545908 100644 --- a/drivers/net/ethernet/fungible/funeth/funeth_rx.c +++ b/drivers/net/ethernet/fungible/funeth/funeth_rx.c @@ -152,6 +152,7 @@ static void *fun_run_xdp(struct funeth_rxq *q, skb_frag_t *frags, void *buf_va, xdp_prepare_buff(&xdp, buf_va, FUN_XDP_HEADROOM, skb_frag_size(frags) - (FUN_RX_TAILROOM + FUN_XDP_HEADROOM), false); + guard(local_lock_nested_bh)(&bpf_run_lock.redirect_lock); xdp_prog = READ_ONCE(q->xdp_prog); act = bpf_prog_run_xdp(xdp_prog, &xdp); diff --git a/drivers/net/ethernet/google/gve/gve_rx.c b/drivers/net/ethernet/google/gve/gve_rx.c index 73655347902d2..504c8ef761a33 100644 --- a/drivers/net/ethernet/google/gve/gve_rx.c +++ b/drivers/net/ethernet/google/gve/gve_rx.c @@ -779,11 +779,13 @@ static void gve_rx(struct gve_rx_ring *rx, netdev_features_t feat, page_info->page_offset, GVE_RX_PAD, len, false); old_data = xdp.data; - xdp_act = bpf_prog_run_xdp(xprog, &xdp); - if (xdp_act != XDP_PASS) { - gve_xdp_done(priv, rx, &xdp, xprog, xdp_act); - ctx->total_size += frag_size; - goto finish_ok_pkt; + scoped_guard(local_lock_nested_bh, &bpf_run_lock.redirect_lock) { + xdp_act = bpf_prog_run_xdp(xprog, &xdp); + if (xdp_act != XDP_PASS) { + gve_xdp_done(priv, rx, &xdp, xprog, xdp_act); + ctx->total_size += frag_size; + goto finish_ok_pkt; + } } page_info->pad += xdp.data - old_data; diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 3cf6589cfdacf..477a74ee18c0a 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -1946,6 +1946,7 @@ static u32 mtk_xdp_run(struct mtk_eth *eth, struct mtk_rx_ring *ring, if (!prog) goto out; + guard(local_lock_nested_bh)(&bpf_run_lock.redirect_lock); act = bpf_prog_run_xdp(prog, xdp); switch (act) { case XDP_PASS: diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_xdp.c b/drivers/net/ethernet/microchip/lan966x/lan966x_xdp.c index 9ee61db8690b4..026311af07f9e 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_xdp.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_xdp.c @@ -84,6 +84,7 @@ int lan966x_xdp_run(struct lan966x_port *port, struct page *page, u32 data_len) xdp_prepare_buff(&xdp, page_address(page), IFH_LEN_BYTES + XDP_PACKET_HEADROOM, data_len - IFH_LEN_BYTES, false); + guard(local_lock_nested_bh)(&bpf_run_lock.redirect_lock); act = bpf_prog_run_xdp(xdp_prog, &xdp); switch (act) { case XDP_PASS: diff --git a/drivers/net/ethernet/microsoft/mana/mana_bpf.c b/drivers/net/ethernet/microsoft/mana/mana_bpf.c index 23b1521c0df96..d465b1dd9fca0 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_bpf.c +++ b/drivers/net/ethernet/microsoft/mana/mana_bpf.c @@ -93,6 +93,7 @@ u32 mana_run_xdp(struct net_device *ndev, struct mana_rxq *rxq, xdp_init_buff(xdp, PAGE_SIZE, &rxq->xdp_rxq); xdp_prepare_buff(xdp, buf_va, XDP_PACKET_HEADROOM, pkt_len, false); + guard(local_lock_nested_bh)(&bpf_run_lock.redirect_lock); act = bpf_prog_run_xdp(prog, xdp); rx_stats = &rxq->stats; -- 2.43.0
