diff options
91 files changed, 1011 insertions, 521 deletions
diff --git a/Documentation/process/maintainer-netdev.rst b/Documentation/process/maintainer-netdev.rst index 2397b31c0198..2ab843cde830 100644 --- a/Documentation/process/maintainer-netdev.rst +++ b/Documentation/process/maintainer-netdev.rst @@ -98,7 +98,7 @@ If you aren't subscribed to netdev and/or are simply unsure if repository link above for any new networking-related commits. You may also check the following website for the current status: - http://vger.kernel.org/~davem/net-next.html + https://patchwork.hopto.org/net-next.html The ``net`` tree continues to collect fixes for the vX.Y content, and is fed back to Linus at regular (~weekly) intervals. Meaning that the diff --git a/MAINTAINERS b/MAINTAINERS index 3be1bdfe8ecc..dfbb271f1667 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -17543,6 +17543,7 @@ QUALCOMM ETHQOS ETHERNET DRIVER M: Vinod Koul <vkoul@kernel.org> R: Bhupesh Sharma <bhupesh.sharma@linaro.org> L: netdev@vger.kernel.org +L: linux-arm-msm@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/net/qcom,ethqos.yaml F: drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c diff --git a/arch/riscv/net/bpf_jit.h b/arch/riscv/net/bpf_jit.h index bf9802a63061..2717f5490428 100644 --- a/arch/riscv/net/bpf_jit.h +++ b/arch/riscv/net/bpf_jit.h @@ -69,7 +69,7 @@ struct rv_jit_context { struct bpf_prog *prog; u16 *insns; /* RV insns */ int ninsns; - int body_len; + int prologue_len; int epilogue_offset; int *offset; /* BPF to RV */ int nexentries; @@ -216,8 +216,8 @@ static inline int rv_offset(int insn, int off, struct rv_jit_context *ctx) int from, to; off++; /* BPF branch is from PC+1, RV is from PC */ - from = (insn > 0) ? ctx->offset[insn - 1] : 0; - to = (insn + off > 0) ? ctx->offset[insn + off - 1] : 0; + from = (insn > 0) ? ctx->offset[insn - 1] : ctx->prologue_len; + to = (insn + off > 0) ? ctx->offset[insn + off - 1] : ctx->prologue_len; return ninsns_rvoff(to - from); } diff --git a/arch/riscv/net/bpf_jit_core.c b/arch/riscv/net/bpf_jit_core.c index 737baf8715da..7a26a3e1c73c 100644 --- a/arch/riscv/net/bpf_jit_core.c +++ b/arch/riscv/net/bpf_jit_core.c @@ -44,7 +44,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) unsigned int prog_size = 0, extable_size = 0; bool tmp_blinded = false, extra_pass = false; struct bpf_prog *tmp, *orig_prog = prog; - int pass = 0, prev_ninsns = 0, prologue_len, i; + int pass = 0, prev_ninsns = 0, i; struct rv_jit_data *jit_data; struct rv_jit_context *ctx; @@ -83,6 +83,12 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) prog = orig_prog; goto out_offset; } + + if (build_body(ctx, extra_pass, NULL)) { + prog = orig_prog; + goto out_offset; + } + for (i = 0; i < prog->len; i++) { prev_ninsns += 32; ctx->offset[i] = prev_ninsns; @@ -91,12 +97,15 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) for (i = 0; i < NR_JIT_ITERATIONS; i++) { pass++; ctx->ninsns = 0; + + bpf_jit_build_prologue(ctx); + ctx->prologue_len = ctx->ninsns; + if (build_body(ctx, extra_pass, ctx->offset)) { prog = orig_prog; goto out_offset; } - ctx->body_len = ctx->ninsns; - bpf_jit_build_prologue(ctx); + ctx->epilogue_offset = ctx->ninsns; bpf_jit_build_epilogue(ctx); @@ -162,10 +171,8 @@ skip_init_ctx: if (!prog->is_func || extra_pass) { bpf_jit_binary_lock_ro(jit_data->header); - prologue_len = ctx->epilogue_offset - ctx->body_len; for (i = 0; i < prog->len; i++) - ctx->offset[i] = ninsns_rvoff(prologue_len + - ctx->offset[i]); + ctx->offset[i] = ninsns_rvoff(ctx->offset[i]); bpf_prog_fill_jited_linfo(prog, ctx->offset); out_offset: kfree(ctx->offset); diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index 70c0e2b1936b..8da46d284e35 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -1286,7 +1286,6 @@ static int felix_parse_ports_node(struct felix *felix, if (err < 0) { dev_info(dev, "Unsupported PHY mode %s on port %d\n", phy_modes(phy_mode), port); - of_node_put(child); /* Leave port_phy_modes[port] = 0, which is also * PHY_INTERFACE_MODE_NA. This will perform a @@ -1786,16 +1785,15 @@ static int felix_change_mtu(struct dsa_switch *ds, int port, int new_mtu) { struct ocelot *ocelot = ds->priv; struct ocelot_port *ocelot_port = ocelot->ports[port]; - struct felix *felix = ocelot_to_felix(ocelot); ocelot_port_set_maxlen(ocelot, port, new_mtu); - mutex_lock(&ocelot->tas_lock); + mutex_lock(&ocelot->fwd_domain_lock); - if (ocelot_port->taprio && felix->info->tas_guard_bands_update) - felix->info->tas_guard_bands_update(ocelot, port); + if (ocelot_port->taprio && ocelot->ops->tas_guard_bands_update) + ocelot->ops->tas_guard_bands_update(ocelot, port); - mutex_unlock(&ocelot->tas_lock); + mutex_unlock(&ocelot->fwd_domain_lock); return 0; } diff --git a/drivers/net/dsa/ocelot/felix.h b/drivers/net/dsa/ocelot/felix.h index 96008c046da5..1d4befe7cfe8 100644 --- a/drivers/net/dsa/ocelot/felix.h +++ b/drivers/net/dsa/ocelot/felix.h @@ -57,7 +57,6 @@ struct felix_info { void (*mdio_bus_free)(struct ocelot *ocelot); int (*port_setup_tc)(struct dsa_switch *ds, int port, enum tc_setup_type type, void *type_data); - void (*tas_guard_bands_update)(struct ocelot *ocelot, int port); void (*port_sched_speed_set)(struct ocelot *ocelot, int port, u32 speed); void (*phylink_mac_config)(struct ocelot *ocelot, int port, diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c index bb39fedd46c7..1c113957fcf4 100644 --- a/drivers/net/dsa/ocelot/felix_vsc9959.c +++ b/drivers/net/dsa/ocelot/felix_vsc9959.c @@ -1209,15 +1209,17 @@ static u32 vsc9959_tas_tc_max_sdu(struct tc_taprio_qopt_offload *taprio, int tc) static void vsc9959_tas_guard_bands_update(struct ocelot *ocelot, int port) { struct ocelot_port *ocelot_port = ocelot->ports[port]; + struct ocelot_mm_state *mm = &ocelot->mm[port]; struct tc_taprio_qopt_offload *taprio; u64 min_gate_len[OCELOT_NUM_TC]; + u32 val, maxlen, add_frag_size; + u64 needed_min_frag_time_ps; int speed, picos_per_byte; u64 needed_bit_time_ps; - u32 val, maxlen; u8 tas_speed; int tc; - lockdep_assert_held(&ocelot->tas_lock); + lockdep_assert_held(&ocelot->fwd_domain_lock); taprio = ocelot_port->taprio; @@ -1253,14 +1255,21 @@ static void vsc9959_tas_guard_bands_update(struct ocelot *ocelot, int port) */ needed_bit_time_ps = (u64)(maxlen + 24) * picos_per_byte; + /* Preemptible TCs don't need to pass a full MTU, the port will + * automatically emit a HOLD request when a preemptible TC gate closes + */ + val = ocelot_read_rix(ocelot, QSYS_PREEMPTION_CFG, port); + add_frag_size = QSYS_PREEMPTION_CFG_MM_ADD_FRAG_SIZE_X(val); + needed_min_frag_time_ps = picos_per_byte * + (u64)(24 + 2 * ethtool_mm_frag_size_add_to_min(add_frag_size)); + dev_dbg(ocelot->dev, - "port %d: max frame size %d needs %llu ps at speed %d\n", - port, maxlen, needed_bit_time_ps, speed); + "port %d: max frame size %d needs %llu ps, %llu ps for mPackets at speed %d\n", + port, maxlen, needed_bit_time_ps, needed_min_frag_time_ps, + speed); vsc9959_tas_min_gate_lengths(taprio, min_gate_len); - mutex_lock(&ocelot->fwd_domain_lock); - for (tc = 0; tc < OCELOT_NUM_TC; tc++) { u32 requested_max_sdu = vsc9959_tas_tc_max_sdu(taprio, tc); u64 remaining_gate_len_ps; @@ -1269,7 +1278,9 @@ static void vsc9959_tas_guard_bands_update(struct ocelot *ocelot, int port) remaining_gate_len_ps = vsc9959_tas_remaining_gate_len_ps(min_gate_len[tc]); - if (remaining_gate_len_ps > needed_bit_time_ps) { + if ((mm->active_preemptible_tcs & BIT(tc)) ? + remaining_gate_len_ps > needed_min_frag_time_ps : + remaining_gate_len_ps > needed_bit_time_ps) { /* Setting QMAXSDU_CFG to 0 disables oversized frame * dropping. */ @@ -1323,8 +1334,6 @@ static void vsc9959_tas_guard_bands_update(struct ocelot *ocelot, int port) ocelot_write_rix(ocelot, maxlen, QSYS_PORT_MAX_SDU, port); ocelot->ops->cut_through_fwd(ocelot); - - mutex_unlock(&ocelot->fwd_domain_lock); } static void vsc9959_sched_speed_set(struct ocelot *ocelot, int port, @@ -1351,7 +1360,7 @@ static void vsc9959_sched_speed_set(struct ocelot *ocelot, int port, break; } - mutex_lock(&ocelot->tas_lock); + mutex_lock(&ocelot->fwd_domain_lock); ocelot_rmw_rix(ocelot, QSYS_TAG_CONFIG_LINK_SPEED(tas_speed), @@ -1361,7 +1370,7 @@ static void vsc9959_sched_speed_set(struct ocelot *ocelot, int port, if (ocelot_port->taprio) vsc9959_tas_guard_bands_update(ocelot, port); - mutex_unlock(&ocelot->tas_lock); + mutex_unlock(&ocelot->fwd_domain_lock); } static void vsc9959_new_base_time(struct ocelot *ocelot, ktime_t base_time, @@ -1409,7 +1418,7 @@ static int vsc9959_qos_port_tas_set(struct ocelot *ocelot, int port, int ret, i; u32 val; - mutex_lock(&ocelot->tas_lock); + mutex_lock(&ocelot->fwd_domain_lock); if (taprio->cmd == TAPRIO_CMD_DESTROY) { ocelot_port_mqprio(ocelot, port, &taprio->mqprio); @@ -1421,7 +1430,7 @@ static int vsc9959_qos_port_tas_set(struct ocelot *ocelot, int port, vsc9959_tas_guard_bands_update(ocelot, port); - mutex_unlock(&ocelot->tas_lock); + mutex_unlock(&ocelot->fwd_domain_lock); return 0; } else if (taprio->cmd != TAPRIO_CMD_REPLACE) { ret = -EOPNOTSUPP; @@ -1504,7 +1513,7 @@ static int vsc9959_qos_port_tas_set(struct ocelot *ocelot, int port, ocelot_port->taprio = taprio_offload_get(taprio); vsc9959_tas_guard_bands_update(ocelot, port); - mutex_unlock(&ocelot->tas_lock); + mutex_unlock(&ocelot->fwd_domain_lock); return 0; @@ -1512,7 +1521,7 @@ err_reset_tc: taprio->mqprio.qopt.num_tc = 0; ocelot_port_mqprio(ocelot, port, &taprio->mqprio); err_unlock: - mutex_unlock(&ocelot->tas_lock); + mutex_unlock(&ocelot->fwd_domain_lock); return ret; } @@ -1525,7 +1534,7 @@ static void vsc9959_tas_clock_adjust(struct ocelot *ocelot) int port; u32 val; - mutex_lock(&ocelot->tas_lock); + mutex_lock(&ocelot->fwd_domain_lock); for (port = 0; port < ocelot->num_phys_ports; port++) { ocelot_port = ocelot->ports[port]; @@ -1563,7 +1572,7 @@ static void vsc9959_tas_clock_adjust(struct ocelot *ocelot) QSYS_TAG_CONFIG_ENABLE, QSYS_TAG_CONFIG, port); } - mutex_unlock(&ocelot->tas_lock); + mutex_unlock(&ocelot->fwd_domain_lock); } static int vsc9959_qos_port_cbs_set(struct dsa_switch *ds, int port, @@ -1634,6 +1643,18 @@ static int vsc9959_qos_query_caps(struct tc_query_caps_base *base) } } +static int vsc9959_qos_port_mqprio(struct ocelot *ocelot, int port, + struct tc_mqprio_qopt_offload *mqprio) +{ + int ret; + + mutex_lock(&ocelot->fwd_domain_lock); + ret = ocelot_port_mqprio(ocelot, port, mqprio); + mutex_unlock(&ocelot->fwd_domain_lock); + + return ret; +} + static int vsc9959_port_setup_tc(struct dsa_switch *ds, int port, enum tc_setup_type type, void *type_data) @@ -1646,7 +1667,7 @@ static int vsc9959_port_setup_tc(struct dsa_switch *ds, int port, case TC_SETUP_QDISC_TAPRIO: return vsc9959_qos_port_tas_set(ocelot, port, type_data); case TC_SETUP_QDISC_MQPRIO: - return ocelot_port_mqprio(ocelot, port, type_data); + return vsc9959_qos_port_mqprio(ocelot, port, type_data); case TC_SETUP_QDISC_CBS: return vsc9959_qos_port_cbs_set(ds, port, type_data); default: @@ -2591,6 +2612,7 @@ static const struct ocelot_ops vsc9959_ops = { .cut_through_fwd = vsc9959_cut_through_fwd, .tas_clock_adjust = vsc9959_tas_clock_adjust, .update_stats = vsc9959_update_stats, + .tas_guard_bands_update = vsc9959_tas_guard_bands_update, }; static const struct felix_info felix_info_vsc9959 = { @@ -2616,7 +2638,6 @@ static const struct felix_info felix_info_vsc9959 = { .port_modes = vsc9959_port_modes, .port_setup_tc = vsc9959_port_setup_tc, .port_sched_speed_set = vsc9959_sched_speed_set, - .tas_guard_bands_update = vsc9959_tas_guard_bands_update, }; /* The INTB interrupt is shared between for PTP TX timestamp availability diff --git a/drivers/net/dsa/qca/qca8k-8xxx.c b/drivers/net/dsa/qca/qca8k-8xxx.c index f7d7cfb2fd86..09b80644c11b 100644 --- a/drivers/net/dsa/qca/qca8k-8xxx.c +++ b/drivers/net/dsa/qca/qca8k-8xxx.c @@ -588,6 +588,9 @@ qca8k_phy_eth_busy_wait(struct qca8k_mgmt_eth_data *mgmt_eth_data, bool ack; int ret; + if (!skb) + return -ENOMEM; + reinit_completion(&mgmt_eth_data->rw_done); /* Increment seq_num and set it in the copy pkt */ diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c index 451c3a1b6255..633b321d7fdd 100644 --- a/drivers/net/ethernet/amazon/ena/ena_com.c +++ b/drivers/net/ethernet/amazon/ena/ena_com.c @@ -35,6 +35,8 @@ #define ENA_REGS_ADMIN_INTR_MASK 1 +#define ENA_MAX_BACKOFF_DELAY_EXP 16U + #define ENA_MIN_ADMIN_POLL_US 100 #define ENA_MAX_ADMIN_POLL_US 5000 @@ -536,6 +538,7 @@ static int ena_com_comp_status_to_errno(struct ena_com_admin_queue *admin_queue, static void ena_delay_exponential_backoff_us(u32 exp, u32 delay_us) { + exp = min_t(u32, exp, ENA_MAX_BACKOFF_DELAY_EXP); delay_us = max_t(u32, ENA_MIN_ADMIN_POLL_US, delay_us); delay_us = min_t(u32, delay_us * (1U << exp), ENA_MAX_ADMIN_POLL_US); usleep_range(delay_us, 2 * delay_us); diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c index 1761df8fb7f9..10c7c232cc4e 100644 --- a/drivers/net/ethernet/broadcom/bgmac.c +++ b/drivers/net/ethernet/broadcom/bgmac.c @@ -1492,8 +1492,6 @@ int bgmac_enet_probe(struct bgmac *bgmac) bgmac->in_init = true; - bgmac_chip_intrs_off(bgmac); - net_dev->irq = bgmac->irq; SET_NETDEV_DEV(net_dev, bgmac->dev); dev_set_drvdata(bgmac->dev, bgmac); @@ -1511,6 +1509,8 @@ int bgmac_enet_probe(struct bgmac *bgmac) */ bgmac_clk_enable(bgmac, 0); + bgmac_chip_intrs_off(bgmac); + /* This seems to be fixing IRQ by assigning OOB #6 to the core */ if (!(bgmac->feature_flags & BGMAC_FEAT_IDM_MASK)) { if (bgmac->feature_flags & BGMAC_FEAT_IRQ_ID_OOB_6) diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h index 9939ccafb556..63a053dea819 100644 --- a/drivers/net/ethernet/freescale/fec.h +++ b/drivers/net/ethernet/freescale/fec.h @@ -355,7 +355,7 @@ struct bufdesc_ex { #define RX_RING_SIZE (FEC_ENET_RX_FRPPG * FEC_ENET_RX_PAGES) #define FEC_ENET_TX_FRSIZE 2048 #define FEC_ENET_TX_FRPPG (PAGE_SIZE / FEC_ENET_TX_FRSIZE) -#define TX_RING_SIZE 512 /* Must be power of two */ +#define TX_RING_SIZE 1024 /* Must be power of two */ #define TX_RING_MOD_MASK 511 /* for this to work */ #define BD_ENET_RX_INT 0x00800000 @@ -544,10 +544,23 @@ enum { XDP_STATS_TOTAL, }; +enum fec_txbuf_type { + FEC_TXBUF_T_SKB, + FEC_TXBUF_T_XDP_NDO, +}; + +struct fec_tx_buffer { + union { + struct sk_buff *skb; + struct xdp_frame *xdp; + }; + enum fec_txbuf_type type; +}; + struct fec_enet_priv_tx_q { struct bufdesc_prop bd; unsigned char *tx_bounce[TX_RING_SIZE]; - struct sk_buff *tx_skbuff[TX_RING_SIZE]; + struct fec_tx_buffer tx_buf[TX_RING_SIZE]; unsigned short tx_stop_threshold; unsigned short tx_wake_threshold; diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 8fbe47703d47..ec9e4bdb0c06 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -397,7 +397,7 @@ static void fec_dump(struct net_device *ndev) fec16_to_cpu(bdp->cbd_sc), fec32_to_cpu(bdp->cbd_bufaddr), fec16_to_cpu(bdp->cbd_datlen), - txq->tx_skbuff[index]); + txq->tx_buf[index].skb); bdp = fec_enet_get_nextdesc(bdp, &txq->bd); index++; } while (bdp != txq->bd.base); @@ -654,7 +654,7 @@ static int fec_enet_txq_submit_skb(struct fec_enet_priv_tx_q *txq, index = fec_enet_get_bd_index(last_bdp, &txq->bd); /* Save skb pointer */ - txq->tx_skbuff[index] = skb; + txq->tx_buf[index].skb = skb; /* Make sure the updates to rest of the descriptor are performed before * transferring ownership. @@ -672,9 +672,7 @@ static int fec_enet_txq_submit_skb(struct fec_enet_priv_tx_q *txq, skb_tx_timestamp(skb); - /* Make sure the update to bdp and tx_skbuff are performed before - * txq->bd.cur. - */ + /* Make sure the update to bdp is performed before txq->bd.cur. */ wmb(); txq->bd.cur = bdp; @@ -862,7 +860,7 @@ static int fec_enet_txq_submit_tso(struct fec_enet_priv_tx_q *txq, } /* Save skb pointer */ - txq->tx_skbuff[index] = skb; + txq->tx_buf[index].skb = skb; skb_tx_timestamp(skb); txq->bd.cur = bdp; @@ -952,16 +950,33 @@ static void fec_enet_bd_init(struct net_device *dev) for (i = 0; i < txq->bd.ring_size; i++) { /* Initialize the BD for every fragment in the page. */ bdp->cbd_sc = cpu_to_fec16(0); - if (bdp->cbd_bufaddr && - !IS_TSO_HEADER(txq, fec32_to_cpu(bdp->cbd_bufaddr))) - dma_unmap_single(&fep->pdev->dev, - fec32_to_cpu(bdp->cbd_bufaddr), - fec16_to_cpu(bdp->cbd_datlen), - DMA_TO_DEVICE); - if (txq->tx_skbuff[i]) { - dev_kfree_skb_any(txq->tx_skbuff[i]); - txq->tx_skbuff[i] = NULL; + if (txq->tx_buf[i].type == FEC_TXBUF_T_SKB) { + if (bdp->cbd_bufaddr && + !IS_TSO_HEADER(txq, fec32_to_cpu(bdp->cbd_bufaddr))) + dma_unmap_single(&fep->pdev->dev, + fec32_to_cpu(bdp->cbd_bufaddr), + fec16_to_cpu(bdp->cbd_datlen), + DMA_TO_DEVICE); + if (txq->tx_buf[i].skb) { + dev_kfree_skb_any(txq->tx_buf[i].skb); + txq->tx_buf[i].skb = NULL; + } + } else { + if (bdp->cbd_bufaddr) + dma_unmap_single(&fep->pdev->dev, + fec32_to_cpu(bdp->cbd_bufaddr), + fec16_to_cpu(bdp->cbd_datlen), + DMA_TO_DEVICE); + + if (txq->tx_buf[i].xdp) { + xdp_return_frame(txq->tx_buf[i].xdp); + txq->tx_buf[i].xdp = NULL; + } + + /* restore default tx buffer type: FEC_TXBUF_T_SKB */ + txq->tx_buf[i].type = FEC_TXBUF_T_SKB; } + bdp->cbd_bufaddr = cpu_to_fec32(0); bdp = fec_enet_get_nextdesc(bdp, &txq->bd); } @@ -1360,6 +1375,7 @@ static void fec_enet_tx_queue(struct net_device *ndev, u16 queue_id) { struct fec_enet_private *fep; + struct xdp_frame *xdpf; struct bufdesc *bdp; unsigned short status; struct sk_buff *skb; @@ -1387,16 +1403,31 @@ fec_enet_tx_queue(struct net_device *ndev, u16 queue_id) index = fec_enet_get_bd_index(bdp, &txq->bd); - skb = txq->tx_skbuff[index]; - txq->tx_skbuff[index] = NULL; - if (!IS_TSO_HEADER(txq, fec32_to_cpu(bdp->cbd_bufaddr))) - dma_unmap_single(&fep->pdev->dev, - fec32_to_cpu(bdp->cbd_bufaddr), - fec16_to_cpu(bdp->cbd_datlen), - DMA_TO_DEVICE); - bdp->cbd_bufaddr = cpu_to_fec32(0); - if (!skb) - goto skb_done; + if (txq->tx_buf[index].type == FEC_TXBUF_T_SKB) { + skb = txq->tx_buf[index].skb; + txq->tx_buf[index].skb = NULL; + if (bdp->cbd_bufaddr && + !IS_TSO_HEADER(txq, fec32_to_cpu(bdp->cbd_bufaddr))) + dma_unmap_single(&fep->pdev->dev, + fec32_to_cpu(bdp->cbd_bufaddr), + fec16_to_cpu(bdp->cbd_datlen), + DMA_TO_DEVICE); + bdp->cbd_bufaddr = cpu_to_fec32(0); + if (!skb) + goto tx_buf_done; + } else { + xdpf = txq->tx_buf[index].xdp; + if (bdp->cbd_bufaddr) + dma_unmap_single(&fep->pdev->dev, + fec32_to_cpu(bdp->cbd_bufaddr), + fec16_to_cpu(bdp->cbd_datlen), + DMA_TO_DEVICE); + bdp->cbd_bufaddr = cpu_to_fec32(0); + if (!xdpf) { + txq->tx_buf[index].type = FEC_TXBUF_T_SKB; + goto tx_buf_done; + } + } /* Check for errors. */ if (status & (BD_ENET_TX_HB | BD_ENET_TX_LC | @@ -1415,21 +1446,11 @@ fec_enet_tx_queue(struct net_device *ndev, u16 queue_id) ndev->stats.tx_carrier_errors++; } else { ndev->stats.tx_packets++; - ndev->stats.tx_bytes += skb->len; - } - - /* NOTE: SKBTX_IN_PROGRESS being set does not imply it's we who - * are to time stamp the packet, so we still need to check time - * stamping enabled flag. - */ - if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS && - fep->hwts_tx_en) && - fep->bufdesc_ex) { - struct skb_shared_hwtstamps shhwtstamps; - struct bufdesc_ex *ebdp = (struct bufdesc_ex *)bdp; - fec_enet_hwtstamp(fep, fec32_to_cpu(ebdp->ts), &shhwtstamps); - skb_tstamp_tx(skb, &shhwtstamps); + if (txq->tx_buf[index].type == FEC_TXBUF_T_SKB) + ndev->stats.tx_bytes += skb->len; + else + ndev->stats.tx_bytes += xdpf->len; } /* Deferred means some collisions occurred during transmit, @@ -1438,10 +1459,32 @@ fec_enet_tx_queue(struct net_device *ndev, u16 queue_id) if (status & BD_ENET_TX_DEF) ndev->stats.collisions++; - /* Free the sk buffer associated with this last transmit */ - dev_kfree_skb_any(skb); -skb_done: - /* Make sure the update to bdp and tx_skbuff are performed + if (txq->tx_buf[index].type == FEC_TXBUF_T_SKB) { + /* NOTE: SKBTX_IN_PROGRESS being set does not imply it's we who + * are to time stamp the packet, so we still need to check time + * stamping enabled flag. + */ + if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS && + fep->hwts_tx_en) && fep->bufdesc_ex) { + struct skb_shared_hwtstamps shhwtstamps; + struct bufdesc_ex *ebdp = (struct bufdesc_ex *)bdp; + + fec_enet_hwtstamp(fep, fec32_to_cpu(ebdp->ts), &shhwtstamps); + skb_tstamp_tx(skb, &shhwtstamps); + } + + /* Free the sk buffer associated with this last transmit */ + dev_kfree_skb_any(skb); + } else { + xdp_return_frame(xdpf); + + txq->tx_buf[index].xdp = NULL; + /* restore default tx buffer type: FEC_TXBUF_T_SKB */ + txq->tx_buf[index].type = FEC_TXBUF_T_SKB; + } + +tx_buf_done: + /* Make sure the update to bdp and tx_buf are performed * before dirty_tx */ wmb(); @@ -3249,9 +3292,19 @@ static void fec_enet_free_buffers(struct net_device *ndev) for (i = 0; i < txq->bd.ring_size; i++) { kfree(txq->tx_bounce[i]); txq->tx_bounce[i] = NULL; - skb = txq->tx_skbuff[i]; - txq->tx_skbuff[i] = NULL; - dev_kfree_skb(skb); + + if (txq->tx_buf[i].type == FEC_TXBUF_T_SKB) { + skb = txq->tx_buf[i].skb; + txq->tx_buf[i].skb = NULL; + dev_kfree_skb(skb); + } else { + if (txq->tx_buf[i].xdp) { + xdp_return_frame(txq->tx_buf[i].xdp); + txq->tx_buf[i].xdp = NULL; + } + + txq->tx_buf[i].type = FEC_TXBUF_T_SKB; + } } } } @@ -3296,8 +3349,7 @@ static int fec_enet_alloc_queue(struct net_device *ndev) fep->total_tx_ring_size += fep->tx_queue[i]->bd.ring_size; txq->tx_stop_threshold = FEC_MAX_SKB_DESCS; - txq->tx_wake_threshold = - (txq->bd.ring_size - txq->tx_stop_threshold) / 2; + txq->tx_wake_threshold = FEC_MAX_SKB_DESCS + 2 * MAX_SKB_FRAGS; txq->tso_hdrs = dma_alloc_coherent(&fep->pdev->dev, txq->bd.ring_size * TSO_HEADER_SIZE, @@ -3732,12 +3784,18 @@ static int fec_enet_bpf(struct net_device *dev, struct netdev_bpf *bpf) if (fep->quirks & FEC_QUIRK_SWAP_FRAME) return -EOPNOTSUPP; + if (!bpf->prog) + xdp_features_clear_redirect_target(dev); + if (is_run) { napi_disable(&fep->napi); netif_tx_disable(dev); } old_prog = xchg(&fep->xdp_prog, bpf->prog); + if (old_prog) + bpf_prog_put(old_prog); + fec_restart(dev); if (is_run) { @@ -3745,8 +3803,8 @@ static int fec_enet_bpf(struct net_device *dev, struct netdev_bpf *bpf) netif_tx_start_all_queues(dev); } - if (old_prog) - bpf_prog_put(old_prog); + if (bpf->prog) + xdp_features_set_redirect_target(dev, false); return 0; @@ -3778,7 +3836,7 @@ static int fec_enet_txq_xmit_frame(struct fec_enet_private *fep, entries_free = fec_enet_get_free_txdesc_num(txq); if (entries_free < MAX_SKB_FRAGS + 1) { - netdev_err(fep->netdev, "NOT enough BD for SG!\n"); + netdev_err_once(fep->netdev, "NOT enough BD for SG!\n"); return -EBUSY; } @@ -3811,7 +3869,8 @@ static int fec_enet_txq_xmit_frame(struct fec_enet_private *fep, ebdp->cbd_esc = cpu_to_fec32(estatus); } - txq->tx_skbuff[index] = NULL; + txq->tx_buf[index].type = FEC_TXBUF_T_XDP_NDO; + txq->tx_buf[index].xdp = frame; /* Make sure the updates to rest of the descriptor are performed before * transferring ownership. @@ -4016,8 +4075,7 @@ static int fec_enet_init(struct net_device *ndev) if (!(fep->quirks & FEC_QUIRK_SWAP_FRAME)) ndev->xdp_features = NETDEV_XDP_ACT_BASIC | - NETDEV_XDP_ACT_REDIRECT | - NETDEV_XDP_ACT_NDO_XMIT; + NETDEV_XDP_ACT_REDIRECT; fec_restart(ndev); diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h index 98eb78d98e9f..4b425bf71ede 100644 --- a/drivers/net/ethernet/google/gve/gve.h +++ b/drivers/net/ethernet/google/gve/gve.h @@ -964,5 +964,6 @@ void gve_handle_report_stats(struct gve_priv *priv); /* exported by ethtool.c */ extern const struct ethtool_ops gve_ethtool_ops; /* needed by ethtool */ +extern char gve_driver_name[]; extern const char gve_version_str[]; #endif /* _GVE_H_ */ diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c index cfd4b8d284d1..233e5946905e 100644 --- a/drivers/net/ethernet/google/gve/gve_ethtool.c +++ b/drivers/net/ethernet/google/gve/gve_ethtool.c @@ -15,7 +15,7 @@ static void gve_get_drvinfo(struct net_device *netdev, { struct gve_priv *priv = netdev_priv(netdev); - strscpy(info->driver, "gve", sizeof(info->driver)); + strscpy(info->driver, gve_driver_name, sizeof(info->driver)); strscpy(info->version, gve_version_str, sizeof(info->version)); strscpy(info->bus_info, pci_name(priv->pdev), sizeof(info->bus_info)); } @@ -590,6 +590,9 @@ static int gve_get_link_ksettings(struct net_device *netdev, err = gve_adminq_report_link_speed(priv); cmd->base.speed = priv->link_speed; + + cmd->base.duplex = DUPLEX_FULL; + return err; } diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index 8fb70db63b8b..e6f1711d9be0 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -33,6 +33,7 @@ #define MIN_TX_TIMEOUT_GAP (1000 * 10) #define DQO_TX_MAX 0x3FFFF +char gve_driver_name[] = "gve"; const char gve_version_str[] = GVE_VERSION; static const char gve_version_prefix[] = GVE_VERSION_PREFIX; @@ -2200,7 +2201,7 @@ static int gve_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) return err; - err = pci_request_regions(pdev, "gvnic-cfg"); + err = pci_request_regions(pdev, gve_driver_name); if (err) goto abort_with_enabled; @@ -2393,8 +2394,8 @@ static const struct pci_device_id gve_id_table[] = { { } }; -static struct pci_driver gvnic_driver = { - .name = "gvnic", +static struct pci_driver gve_driver = { + .name = gve_driver_name, .id_table = gve_id_table, .probe = gve_probe, .remove = gve_remove, @@ -2405,10 +2406,10 @@ static struct pci_driver gvnic_driver = { #endif }; -module_pci_driver(gvnic_driver); +module_pci_driver(gve_driver); MODULE_DEVICE_TABLE(pci, gve_id_table); MODULE_AUTHOR("Google, Inc."); -MODULE_DESCRIPTION("gVNIC Driver"); +MODULE_DESCRIPTION("Google Virtual NIC Driver"); MODULE_LICENSE("Dual MIT/GPL"); MODULE_VERSION(GVE_VERSION); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 93979ab18bc1..19a5e7f3a075 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -5739,6 +5739,13 @@ ice_set_tx_maxrate(struct net_device *netdev, int queue_index, u32 maxrate) q_handle = vsi->tx_rings[queue_index]->q_handle; tc = ice_dcb_get_tc(vsi, queue_index); + vsi = ice_locate_vsi_using_queue(vsi, queue_index); + if (!vsi) { + netdev_err(netdev, "Invalid VSI for given queue %d\n", + queue_index); + return -EINVAL; + } + /* Set BW back to default, when user set maxrate to 0 */ if (!maxrate) status = ice_cfg_q_bw_dflt_lmt(vsi->port_info, vsi->idx, tc, @@ -7872,10 +7879,10 @@ static int ice_validate_mqprio_qopt(struct ice_vsi *vsi, struct tc_mqprio_qopt_offload *mqprio_qopt) { - u64 sum_max_rate = 0, sum_min_rate = 0; int non_power_of_2_qcount = 0; struct ice_pf *pf = vsi->back; int max_rss_q_cnt = 0; + u64 sum_min_rate = 0; struct device *dev; int i, speed; u8 num_tc; @@ -7891,6 +7898,7 @@ ice_validate_mqprio_qopt(struct ice_vsi *vsi, dev = ice_pf_to_dev(pf); vsi->ch_rss_size = 0; num_tc = mqprio_qopt->qopt.num_tc; + speed = ice_get_link_speed_kbps(vsi); for (i = 0; num_tc; i++) { int qcount = mqprio_qopt->qopt.count[i]; @@ -7931,7 +7939,6 @@ ice_validate_mqprio_qopt(struct ice_vsi *vsi, */ max_rate = mqprio_qopt->max_rate[i]; max_rate = div_u64(max_rate, ICE_BW_KBPS_DIVISOR); - sum_max_rate += max_rate; /* min_rate is minimum guaranteed rate and it can't be zero */ min_rate = mqprio_qopt->min_rate[i]; @@ -7944,6 +7951,12 @@ ice_validate_mqprio_qopt(struct ice_vsi *vsi, return -EINVAL; } + if (max_rate && max_rate > speed) { + dev_err(dev, "TC%d: max_rate(%llu Kbps) > link speed of %u Kbps\n", + i, max_rate, speed); + return -EINVAL; + } + iter_div_u64_rem(min_rate, ICE_MIN_BW_LIMIT, &rem); if (rem) { dev_err(dev, "TC%d: Min Rate not multiple of %u Kbps", @@ -7981,12 +7994,6 @@ ice_validate_mqprio_qopt(struct ice_vsi *vsi, (mqprio_qopt->qopt.offset[i] + mqprio_qopt->qopt.count[i])) return -EINVAL; - speed = ice_get_link_speed_kbps(vsi); - if (sum_max_rate && sum_max_rate > (u64)speed) { - dev_err(dev, "Invalid max Tx rate(%llu) Kbps > speed(%u) Kbps specified\n", - sum_max_rate, speed); - return -EINVAL; - } if (sum_min_rate && sum_min_rate > (u64)speed) { dev_err(dev, "Invalid min Tx rate(%llu) Kbps > speed (%u) Kbps specified\n", sum_min_rate, speed); diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.c b/drivers/net/ethernet/intel/ice/ice_tc_lib.c index b54052ef6050..4a34ef5f58d3 100644 --- a/drivers/net/ethernet/intel/ice/ice_tc_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.c @@ -750,17 +750,16 @@ exit: /** * ice_locate_vsi_using_queue - locate VSI using queue (forward to queue action) * @vsi: Pointer to VSI - * @tc_fltr: Pointer to tc_flower_filter + * @queue: Queue index * - * Locate the VSI using specified queue. When ADQ is not enabled, always - * return input VSI, otherwise locate corresponding VSI based on per channel - * offset and qcount + * Locate the VSI using specified "queue". When ADQ is not enabled, + * always return input VSI, otherwise locate corresponding + * VSI based on per channel "offset" and "qcount" */ -static struct ice_vsi * -ice_locate_vsi_using_queue(struct ice_vsi *vsi, - struct ice_tc_flower_fltr *tc_fltr) +struct ice_vsi * +ice_locate_vsi_using_queue(struct ice_vsi *vsi, int queue) { - int num_tc, tc, queue; + int num_tc, tc; /* if ADQ is not active, passed VSI is the candidate VSI */ if (!ice_is_adq_active(vsi->back)) @@ -770,7 +769,6 @@ ice_locate_vsi_using_queue(struct ice_vsi *vsi, * upon queue number) */ num_tc = vsi->mqprio_qopt.qopt.num_tc; - queue = tc_fltr->action.fwd.q.queue; for (tc = 0; tc < num_tc; tc++) { int qcount = vsi->mqprio_qopt.qopt.count[tc]; @@ -812,6 +810,7 @@ ice_tc_forward_action(struct ice_vsi *vsi, struct ice_tc_flower_fltr *tc_fltr) struct ice_pf *pf = vsi->back; struct device *dev; u32 tc_class; + int q; dev = ice_pf_to_dev(pf); @@ -840,7 +839,8 @@ ice_tc_forward_action(struct ice_vsi *vsi, struct ice_tc_flower_fltr *tc_fltr) /* Determine destination VSI even though the action is * FWD_TO_QUEUE, because QUEUE is associated with VSI */ - dest_vsi = tc_fltr->dest_vsi; + q = tc_fltr->action.fwd.q.queue; + dest_vsi = ice_locate_vsi_using_queue(vsi, q); break; default: dev_err(dev, @@ -1716,7 +1716,7 @@ ice_tc_forward_to_queue(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr, /* If ADQ is configured, and the queue belongs to ADQ VSI, then prepare * ADQ switch filter */ - ch_vsi = ice_locate_vsi_using_queue(vsi, fltr); + ch_vsi = ice_locate_vsi_using_queue(vsi, fltr->action.fwd.q.queue); if (!ch_vsi) return -EINVAL; fltr->dest_vsi = ch_vsi; diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.h b/drivers/net/ethernet/intel/ice/ice_tc_lib.h index 8bbc1a62bdb1..65d387163a46 100644 --- a/drivers/net/ethernet/intel/ice/ice_tc_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.h @@ -204,6 +204,7 @@ static inline int ice_chnl_dmac_fltr_cnt(struct ice_pf *pf) return pf->num_dmac_chnl_fltrs; } +struct ice_vsi *ice_locate_vsi_using_queue(struct ice_vsi *vsi, int queue); int ice_add_cls_flower(struct net_device *netdev, struct ice_vsi *vsi, struct flow_cls_offload *cls_flower); diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index 00a5ee487812..9db384f66a8e 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -14,6 +14,7 @@ #include <linux/timecounter.h> #include <linux/net_tstamp.h> #include <linux/bitfield.h> +#include <linux/hrtimer.h> #include "igc_hw.h" @@ -101,6 +102,8 @@ struct igc_ring { u32 start_time; u32 end_time; u32 max_sdu; + bool oper_gate_closed; /* Operating gate. True if the TX Queue is closed */ + bool admin_gate_closed; /* Future gate. True if the TX Queue will be closed */ /* CBS parameters */ bool cbs_enable; /* indicates if CBS is enabled */ @@ -160,6 +163,7 @@ struct igc_adapter { struct timer_list watchdog_timer; struct timer_list dma_err_timer; struct timer_list phy_info_timer; + struct hrtimer hrtimer; u32 wol; u32 en_mng_pt; @@ -184,10 +188,13 @@ struct igc_adapter { u32 max_frame_size; u32 min_frame_size; + int tc_setup_type; ktime_t base_time; ktime_t cycle_time; - bool qbv_enable; + bool taprio_offload_enable; u32 qbv_config_change_errors; + bool qbv_transition; + unsigned int qbv_count; /* OS defined structs */ struct pci_dev *pdev; diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c index 0e2cb00622d1..93bce729be76 100644 --- a/drivers/net/ethernet/intel/igc/igc_ethtool.c +++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c @@ -1708,6 +1708,8 @@ static int igc_ethtool_get_link_ksettings(struct net_device *netdev, /* twisted pair */ cmd->base.port = PORT_TP; cmd->base.phy_address = hw->phy.addr; + ethtool_link_ksettings_add_link_mode(cmd, supported, TP); + ethtool_link_ksettings_add_link_mode(cmd, advertising, TP); /* advertising link modes */ if (hw->phy.autoneg_advertised & ADVERTISE_10_HALF) diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 019ce91c45aa..9f93f0f4f752 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -711,7 +711,6 @@ static void igc_configure_tx_ring(struct igc_adapter *adapter, /* disable the queue */ wr32(IGC_TXDCTL(reg_idx), 0); wrfl(); - mdelay(10); wr32(IGC_TDLEN(reg_idx), ring->count * sizeof(union igc_adv_tx_desc)); @@ -1017,7 +1016,7 @@ static __le32 igc_tx_launchtime(struct igc_ring *ring, ktime_t txtime, ktime_t base_time = adapter->base_time; ktime_t now = ktime_get_clocktai(); ktime_t baset_est, end_of_cycle; - u32 launchtime; + s32 launchtime; s64 n; n = div64_s64(ktime_sub_ns(now, base_time), cycle_time); @@ -1030,7 +1029,7 @@ static __le32 igc_tx_launchtime(struct igc_ring *ring, ktime_t txtime, *first_flag = true; ring->last_ff_cycle = baset_est; - if (ktime_compare(txtime, ring->last_tx_cycle) > 0) + if (ktime_compare(end_of_cycle, ring->last_tx_cycle) > 0) *insert_empty = true; } } @@ -1573,16 +1572,12 @@ done: first->bytecount = skb->len; first->gso_segs = 1; - if (tx_ring->max_sdu > 0) { - u32 max_sdu = 0; - - max_sdu = tx_ring->max_sdu + - (skb_vlan_tagged(first->skb) ? VLAN_HLEN : 0); + if (adapter->qbv_transition || tx_ring->oper_gate_closed) + goto out_drop; - if (first->bytecount > max_sdu) { - adapter->stats.txdrop++; - goto out_drop; - } + if (tx_ring->max_sdu > 0 && first->bytecount > tx_ring->max_sdu) { + adapter->stats.txdrop++; + goto out_drop; } if (unlikely(test_bit(IGC_RING_FLAG_TX_HWTSTAMP, &tx_ring->flags) && @@ -3012,8 +3007,8 @@ static bool igc_clean_tx_irq(struct igc_q_vector *q_vector, int napi_budget) time_after(jiffies, tx_buffer->time_stamp + (adapter->tx_timeout_factor * HZ)) && !(rd32(IGC_STATUS) & IGC_STATUS_TXOFF) && - (rd32(IGC_TDH(tx_ring->reg_idx)) != - readl(tx_ring->tail))) { + (rd32(IGC_TDH(tx_ring->reg_idx)) != readl(tx_ring->tail)) && + !tx_ring->oper_gate_closed) { /* detected Tx unit hang */ netdev_err(tx_ring->netdev, "Detected Tx Unit Hang\n" @@ -6102,7 +6097,10 @@ static int igc_tsn_clear_schedule(struct igc_adapter *adapter) adapter->base_time = 0; adapter->cycle_time = NSEC_PER_SEC; + adapter->taprio_offload_enable = false; adapter->qbv_config_change_errors = 0; + adapter->qbv_transition = false; + adapter->qbv_count = 0; for (i = 0; i < adapter->num_tx_queues; i++) { struct igc_ring *ring = adapter->tx_ring[i]; @@ -6110,6 +6108,8 @@ static int igc_tsn_clear_schedule(struct igc_adapter *adapter) ring->start_time = 0; ring->end_time = NSEC_PER_SEC; ring->max_sdu = 0; + ring->oper_gate_closed = false; + ring->admin_gate_closed = false; } return 0; @@ -6121,27 +6121,20 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter, bool queue_configured[IGC_MAX_TX_QUEUES] = { }; struct igc_hw *hw = &adapter->hw; u32 start_time = 0, end_time = 0; + struct timespec64 now; size_t n; int i; - switch (qopt->cmd) { - case TAPRIO_CMD_REPLACE: - adapter->qbv_enable = true; - break; - case TAPRIO_CMD_DESTROY: - adapter->qbv_enable = false; - break; - default: - return -EOPNOTSUPP; - } - - if (!adapter->qbv_enable) + if (qopt->cmd == TAPRIO_CMD_DESTROY) return igc_tsn_clear_schedule(adapter); + if (qopt->cmd != TAPRIO_CMD_REPLACE) + return -EOPNOTSUPP; + if (qopt->base_time < 0) return -ERANGE; - if (igc_is_device_id_i225(hw) && adapter->base_time) + if (igc_is_device_id_i225(hw) && adapter->taprio_offload_enable) return -EALREADY; if (!validate_schedule(adapter, qopt)) @@ -6149,6 +6142,9 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter, adapter->cycle_time = qopt->cycle_time; adapter->base_time = qopt->base_time; + adapter->taprio_offload_enable = true; + + igc_ptp_read(adapter, &now); for (n = 0; n < qopt->num_entries; n++) { struct tc_taprio_sched_entry *e = &qopt->entries[n]; @@ -6184,7 +6180,10 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter, ring->start_time = start_time; ring->end_time = end_time; - queue_configured[i] = true; + if (ring->start_time >= adapter->cycle_time) + queue_configured[i] = false; + else + queue_configured[i] = true; } start_time += e->interval; @@ -6194,8 +6193,20 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter, * If not, set the start and end time to be end time. */ for (i = 0; i < adapter->num_tx_queues; i++) { + struct igc_ring *ring = adapter->tx_ring[i]; + + if (!is_base_time_past(qopt->base_time, &now)) { + ring->admin_gate_closed = false; + } else { + ring->oper_gate_closed = false; + ring->admin_gate_closed = false; + } + if (!queue_configured[i]) { - struct igc_ring *ring = adapter->tx_ring[i]; + if (!is_base_time_past(qopt->base_time, &now)) + ring->admin_gate_closed = true; + else + ring->oper_gate_closed = true; ring->start_time = end_time; ring->end_time = end_time; @@ -6207,7 +6218,7 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter, struct net_device *dev = adapter->netdev; if (qopt->max_sdu[i]) - ring->max_sdu = qopt->max_sdu[i] + dev->hard_header_len; + ring->max_sdu = qopt->max_sdu[i] + dev->hard_header_len - ETH_TLEN; else ring->max_sdu = 0; } @@ -6327,6 +6338,8 @@ static int igc_setup_tc(struct net_device *dev, enum tc_setup_type type, { struct igc_adapter *adapter = netdev_priv(dev); + adapter->tc_setup_type = type; + switch (type) { case TC_QUERY_CAPS: return igc_tc_query_caps(adapter, type_data); @@ -6574,6 +6587,27 @@ static const struct xdp_metadata_ops igc_xdp_metadata_ops = { .xmo_rx_timestamp = igc_xdp_rx_timestamp, }; +static enum hrtimer_restart igc_qbv_scheduling_timer(struct hrtimer *timer) +{ + struct igc_adapter *adapter = container_of(timer, struct igc_adapter, + hrtimer); + unsigned int i; + + adapter->qbv_transition = true; + for (i = 0; i < adapter->num_tx_queues; i++) { + struct igc_ring *tx_ring = adapter->tx_ring[i]; + + if (tx_ring->admin_gate_closed) { + tx_ring->admin_gate_closed = false; + tx_ring->oper_gate_closed = true; + } else { + tx_ring->oper_gate_closed = false; + } + } + adapter->qbv_transition = false; + return HRTIMER_NORESTART; +} + /** * igc_probe - Device Initialization Routine * @pdev: PCI device information struct @@ -6752,6 +6786,9 @@ static int igc_probe(struct pci_dev *pdev, INIT_WORK(&adapter->reset_task, igc_reset_task); INIT_WORK(&adapter->watchdog_task, igc_watchdog_task); + hrtimer_init(&adapter->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + adapter->hrtimer.function = &igc_qbv_scheduling_timer; + /* Initialize link properties that are user-changeable */ adapter->fc_autoneg = true; hw->mac.autoneg = true; @@ -6855,6 +6892,7 @@ static void igc_remove(struct pci_dev *pdev) cancel_work_sync(&adapter->reset_task); cancel_work_sync(&adapter->watchdog_task); + hrtimer_cancel(&adapter->hrtimer); /* Release control of h/w to f/w. If f/w is AMT enabled, this * would have already happened in close and is redundant. diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c index 32ef112f8291..f0b979a70655 100644 --- a/drivers/net/ethernet/intel/igc/igc_ptp.c +++ b/drivers/net/ethernet/intel/igc/igc_ptp.c @@ -356,16 +356,35 @@ static int igc_ptp_feature_enable_i225(struct ptp_clock_info *ptp, tsim &= ~IGC_TSICR_TT0; } if (on) { + struct timespec64 safe_start; int i = rq->perout.index; igc_pin_perout(igc, i, pin, use_freq); - igc->perout[i].start.tv_sec = rq->perout.start.sec; + igc_ptp_read(igc, &safe_start); + + /* PPS output start time is triggered by Target time(TT) + * register. Programming any past time value into TT + * register will cause PPS to never start. Need to make + * sure we program the TT register a time ahead in + * future. There isn't a stringent need to fire PPS out + * right away. Adding +2 seconds should take care of + * corner cases. Let's say if the SYSTIML is close to + * wrap up and the timer keeps ticking as we program the + * register, adding +2seconds is safe bet. + */ + safe_start.tv_sec += 2; + + if (rq->perout.start.sec < safe_start.tv_sec) + igc->perout[i].start.tv_sec = safe_start.tv_sec; + else + igc->perout[i].start.tv_sec = rq->perout.start.sec; igc->perout[i].start.tv_nsec = rq->perout.start.nsec; igc->perout[i].period.tv_sec = ts.tv_sec; igc->perout[i].period.tv_nsec = ts.tv_nsec; - wr32(trgttimh, rq->perout.start.sec); + wr32(trgttimh, (u32)igc->perout[i].start.tv_sec); /* For now, always select timer 0 as source. */ - wr32(trgttiml, rq->perout.start.nsec | IGC_TT_IO_TIMER_SEL_SYSTIM0); + wr32(trgttiml, (u32)(igc->perout[i].start.tv_nsec | + IGC_TT_IO_TIMER_SEL_SYSTIM0)); if (use_freq) wr32(freqout, ns); tsauxc |= tsauxc_mask; diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.c b/drivers/net/ethernet/intel/igc/igc_tsn.c index 94a2b0dfb54d..a9c08321aca9 100644 --- a/drivers/net/ethernet/intel/igc/igc_tsn.c +++ b/drivers/net/ethernet/intel/igc/igc_tsn.c @@ -37,7 +37,7 @@ static unsigned int igc_tsn_new_flags(struct igc_adapter *adapter) { unsigned int new_flags = adapter->flags & ~IGC_FLAG_TSN_ANY_ENABLED; - if (adapter->qbv_enable) + if (adapter->taprio_offload_enable) new_flags |= IGC_FLAG_TSN_QBV_ENABLED; if (is_any_launchtime(adapter)) @@ -114,7 +114,6 @@ static int igc_tsn_disable_offload(struct igc_adapter *adapter) static int igc_tsn_enable_offload(struct igc_adapter *adapter) { struct igc_hw *hw = &adapter->hw; - bool tsn_mode_reconfig = false; u32 tqavctrl, baset_l, baset_h; u32 sec, nsec, cycle; ktime_t base_time, systim; @@ -133,8 +132,28 @@ static int igc_tsn_enable_offload(struct igc_adapter *adapter) wr32(IGC_STQT(i), ring->start_time); wr32(IGC_ENDQT(i), ring->end_time); - txqctl |= IGC_TXQCTL_STRICT_CYCLE | - IGC_TXQCTL_STRICT_END; + if (adapter->taprio_offload_enable) { + /* If taprio_offload_enable is set we are in "taprio" + * mode and we need to be strict about the + * cycles: only transmit a packet if it can be + * completed during that cycle. + * + * If taprio_offload_enable is NOT true when + * enabling TSN offload, the cycle should have + * no external effects, but is only used internally + * to adapt the base time register after a second + * has passed. + * + * Enabling strict mode in this case would + * unnecessarily prevent the transmission of + * certain packets (i.e. at the boundary of a + * second) and thus interfere with the launchtime + * feature that promises transmission at a + * certain point in time. + */ + txqctl |= IGC_TXQCTL_STRICT_CYCLE | + IGC_TXQCTL_STRICT_END; + } if (ring->launchtime_enable) txqctl |= IGC_TXQCTL_QUEUE_MODE_LAUNCHT; @@ -228,11 +247,10 @@ skip_cbs: tqavctrl = rd32(IGC_TQAVCTRL) & ~IGC_TQAVCTRL_FUTSCDDIS; - if (tqavctrl & IGC_TQAVCTRL_TRANSMIT_MODE_TSN) - tsn_mode_reconfig = true; - tqavctrl |= IGC_TQAVCTRL_TRANSMIT_MODE_TSN | IGC_TQAVCTRL_ENHANCED_QAV; + adapter->qbv_count++; + cycle = adapter->cycle_time; base_time = adapter->base_time; @@ -249,17 +267,29 @@ skip_cbs: * Gate Control List (GCL) is running. */ if ((rd32(IGC_BASET_H) || rd32(IGC_BASET_L)) && - tsn_mode_reconfig) + (adapter->tc_setup_type == TC_SETUP_QDISC_TAPRIO) && + (adapter->qbv_count > 1)) adapter->qbv_config_change_errors++; } else { - /* According to datasheet section 7.5.2.9.3.3, FutScdDis bit - * has to be configured before the cycle time and base time. - * Tx won't hang if there is a GCL is already running, - * so in this case we don't need to set FutScdDis. - */ - if (igc_is_device_id_i226(hw) && - !(rd32(IGC_BASET_H) || rd32(IGC_BASET_L))) - tqavctrl |= IGC_TQAVCTRL_FUTSCDDIS; + if (igc_is_device_id_i226(hw)) { + ktime_t adjust_time, expires_time; + + /* According to datasheet section 7.5.2.9.3.3, FutScdDis bit + * has to be configured before the cycle time and base time. + * Tx won't hang if a GCL is already running, + * so in this case we don't need to set FutScdDis. + */ + if (!(rd32(IGC_BASET_H) || rd32(IGC_BASET_L))) + tqavctrl |= IGC_TQAVCTRL_FUTSCDDIS; + + nsec = rd32(IGC_SYSTIML); + sec = rd32(IGC_SYSTIMH); + systim = ktime_set(sec, nsec); + + adjust_time = adapter->base_time; + expires_time = ktime_sub_ns(adjust_time, systim); + hrtimer_start(&adapter->hrtimer, expires_time, HRTIMER_MODE_REL); + } } wr32(IGC_TQAVCTRL, tqavctrl); @@ -305,7 +335,11 @@ int igc_tsn_offload_apply(struct igc_adapter *adapter) { struct igc_hw *hw = &adapter->hw; - if (netif_running(adapter->netdev) && igc_is_device_id_i225(hw)) { + /* Per I225/6 HW Design Section 7.5.2.1, transmit mode + * cannot be changed dynamically. Require reset the adapter. + */ + if (netif_running(adapter->netdev) && + (igc_is_device_id_i225(hw) || !adapter->qbv_count)) { schedule_work(&adapter->reset_task); return 0; } diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index ff5647bcdfca..acf4f6ba73a6 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -1511,7 +1511,7 @@ static void mvneta_defaults_set(struct mvneta_port *pp) */ if (txq_number == 1) txq_map = (cpu == pp->rxq_def) ? - MVNETA_CPU_TXQ_ACCESS(1) : 0; + MVNETA_CPU_TXQ_ACCESS(0) : 0; } else { txq_map = MVNETA_CPU_TXQ_ACCESS_ALL_MASK; @@ -4356,7 +4356,7 @@ static void mvneta_percpu_elect(struct mvneta_port *pp) */ if (txq_number == 1) txq_map = (cpu == elected_cpu) ? - MVNETA_CPU_TXQ_ACCESS(1) : 0; + MVNETA_CPU_TXQ_ACCESS(0) : 0; else txq_map = mvreg_read(pp, MVNETA_CPU_MAP(cpu)) & MVNETA_CPU_TXQ_ACCESS_ALL_MASK; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/ptp.c b/drivers/net/ethernet/marvell/octeontx2/af/ptp.c index 3411e2e47d46..0ee420a489fc 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/ptp.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/ptp.c @@ -208,7 +208,7 @@ struct ptp *ptp_get(void) /* Check driver is bound to PTP block */ if (!ptp) ptp = ERR_PTR(-EPROBE_DEFER); - else + else if (!IS_ERR(ptp)) pci_dev_get(ptp->pdev); return ptp; @@ -388,11 +388,10 @@ static int ptp_extts_on(struct ptp *ptp, int on) static int ptp_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { - struct device *dev = &pdev->dev; struct ptp *ptp; int err; - ptp = devm_kzalloc(dev, sizeof(*ptp), GFP_KERNEL); + ptp = kzalloc(sizeof(*ptp), GFP_KERNEL); if (!ptp) { err = -ENOMEM; goto error; @@ -428,20 +427,19 @@ static int ptp_probe(struct pci_dev *pdev, return 0; error_free: - devm_kfree(dev, ptp); + kfree(ptp); error: /* For `ptp_get()` we need to differentiate between the case * when the core has not tried to probe this device and the case when - * the probe failed. In the later case we pretend that the - * initialization was successful and keep the error in + * the probe failed. In the later case we keep the error in * `dev->driver_data`. */ pci_set_drvdata(pdev, ERR_PTR(err)); if (!first_ptp_block) first_ptp_block = ERR_PTR(err); - return 0; + return err; } static void ptp_remove(struct pci_dev *pdev) @@ -449,16 +447,17 @@ static void ptp_remove(struct pci_dev *pdev) struct ptp *ptp = pci_get_drvdata(pdev); u64 clock_cfg; - if (cn10k_ptp_errata(ptp) && hrtimer_active(&ptp->hrtimer)) - hrtimer_cancel(&ptp->hrtimer); - if (IS_ERR_OR_NULL(ptp)) return; + if (cn10k_ptp_errata(ptp) && hrtimer_active(&ptp->hrtimer)) + hrtimer_cancel(&ptp->hrtimer); + /* Disable PTP clock */ clock_cfg = readq(ptp->reg_base + PTP_CLOCK_CFG); clock_cfg &= ~PTP_CLOCK_CFG_PTP_EN; writeq(clock_cfg, ptp->reg_base + PTP_CLOCK_CFG); + kfree(ptp); } static const struct pci_device_id ptp_id_table[] = { diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c index 8dbc35c481f6..73df2d564545 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c @@ -3252,7 +3252,7 @@ static int rvu_probe(struct pci_dev *pdev, const struct pci_device_id *id) rvu->ptp = ptp_get(); if (IS_ERR(rvu->ptp)) { err = PTR_ERR(rvu->ptp); - if (err == -EPROBE_DEFER) + if (err) goto err_release_regions; rvu->ptp = NULL; } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index 0d745ae1cc9a..04b0e885f9d2 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -4069,21 +4069,14 @@ int rvu_mbox_handler_nix_set_rx_mode(struct rvu *rvu, struct nix_rx_mode *req, } /* install/uninstall promisc entry */ - if (promisc) { + if (promisc) rvu_npc_install_promisc_entry(rvu, pcifunc, nixlf, pfvf->rx_chan_base, pfvf->rx_chan_cnt); - - if (rvu_npc_exact_has_match_table(rvu)) - rvu_npc_exact_promisc_enable(rvu, pcifunc); - } else { + else if (!nix_rx_multicast) rvu_npc_enable_promisc_entry(rvu, pcifunc, nixlf, false); - if (rvu_npc_exact_has_match_table(rvu)) - rvu_npc_exact_promisc_disable(rvu, pcifunc); - } - return 0; } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c index 9f11c1e40737..6fe67f3a7f6f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c @@ -1164,8 +1164,10 @@ static u16 __rvu_npc_exact_cmd_rules_cnt_update(struct rvu *rvu, int drop_mcam_i { struct npc_exact_table *table; u16 *cnt, old_cnt; + bool promisc; table = rvu->hw->table; + promisc = table->promisc_mode[drop_mcam_idx]; cnt = &table->cnt_cmd_rules[drop_mcam_idx]; old_cnt = *cnt; @@ -1177,13 +1179,18 @@ static u16 __rvu_npc_exact_cmd_rules_cnt_update(struct rvu *rvu, int drop_mcam_i *enable_or_disable_cam = false; - /* If all rules are deleted, disable cam */ + if (promisc) + goto done; + + /* If all rules are deleted and not already in promisc mode; + * disable cam + */ if (!*cnt && val < 0) { *enable_or_disable_cam = true; goto done; } - /* If rule got added, enable cam */ + /* If rule got added and not already in promisc mode; enable cam */ if (!old_cnt && val > 0) { *enable_or_disable_cam = true; goto done; @@ -1462,6 +1469,12 @@ int rvu_npc_exact_promisc_disable(struct rvu *rvu, u16 pcifunc) *promisc = false; mutex_unlock(&table->lock); + /* Enable drop rule */ + rvu_npc_enable_mcam_by_entry_index(rvu, drop_mcam_idx, NIX_INTF_RX, + true); + + dev_dbg(rvu->dev, "%s: disabled promisc mode (cgx=%d lmac=%d)\n", + __func__, cgx_id, lmac_id); return 0; } @@ -1503,6 +1516,12 @@ int rvu_npc_exact_promisc_enable(struct rvu *rvu, u16 pcifunc) *promisc = true; mutex_unlock(&table->lock); + /* disable drop rule */ + rvu_npc_enable_mcam_by_entry_index(rvu, drop_mcam_idx, NIX_INTF_RX, + false); + + dev_dbg(rvu->dev, "%s: Enabled promisc mode (cgx=%d lmac=%d)\n", + __func__, cgx_id, lmac_id); return 0; } diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c index 10e11262d48a..2d7713a1a153 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c @@ -872,6 +872,14 @@ static int otx2_prepare_flow_request(struct ethtool_rx_flow_spec *fsp, return -EINVAL; vlan_etype = be16_to_cpu(fsp->h_ext.vlan_etype); + + /* Drop rule with vlan_etype == 802.1Q + * and vlan_id == 0 is not supported + */ + if (vlan_etype == ETH_P_8021Q && !fsp->m_ext.vlan_tci && + fsp->ring_cookie == RX_CLS_FLOW_DISC) + return -EINVAL; + /* Only ETH_P_8021Q and ETH_P_802AD types supported */ if (vlan_etype != ETH_P_8021Q && vlan_etype != ETH_P_8021AD) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c index 8a13df592af6..5e56b6c3e60a 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c @@ -597,6 +597,21 @@ static int otx2_tc_prepare_flow(struct otx2_nic *nic, struct otx2_tc_flow *node, return -EOPNOTSUPP; } + if (!match.mask->vlan_id) { + struct flow_action_entry *act; + int i; + + flow_action_for_each(i, act, &rule->action) { + if (act->id == FLOW_ACTION_DROP) { + netdev_err(nic->netdev, + "vlan tpid 0x%x with vlan_id %d is not supported for DROP rule.\n", + ntohs(match.key->vlan_tpid), + match.key->vlan_id); + return -EOPNOTSUPP; + } + } + } + if (match.mask->vlan_id || match.mask->vlan_dei || match.mask->vlan_priority) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c b/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c index 03cb79adf912..be83ad9db82a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c @@ -594,7 +594,7 @@ int mlx5e_fs_tt_redirect_any_create(struct mlx5e_flow_steering *fs) err = fs_any_create_table(fs); if (err) - return err; + goto err_free_any; err = fs_any_enable(fs); if (err) @@ -606,8 +606,8 @@ int mlx5e_fs_tt_redirect_any_create(struct mlx5e_flow_steering *fs) err_destroy_table: fs_any_destroy_table(fs_any); - - kfree(fs_any); +err_free_any: mlx5e_fs_set_any(fs, NULL); + kfree(fs_any); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c index 3cbebfba582b..b0b429a0321e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c @@ -729,8 +729,10 @@ int mlx5e_ptp_open(struct mlx5e_priv *priv, struct mlx5e_params *params, c = kvzalloc_node(sizeof(*c), GFP_KERNEL, dev_to_node(mlx5_core_dma_dev(mdev))); cparams = kvzalloc(sizeof(*cparams), GFP_KERNEL); - if (!c || !cparams) - return -ENOMEM; + if (!c || !cparams) { + err = -ENOMEM; + goto err_free; + } c->priv = priv; c->mdev = priv->mdev; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c index a254e728ac95..fadfa8b50beb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c @@ -1545,7 +1545,8 @@ mlx5_tc_ct_parse_action(struct mlx5_tc_ct_priv *priv, attr->ct_attr.ct_action |= act->ct.action; /* So we can have clear + ct */ attr->ct_attr.zone = act->ct.zone; - attr->ct_attr.nf_ft = act->ct.flow_table; + if (!(act->ct.action & TCA_CT_ACT_CLEAR)) + attr->ct_attr.nf_ft = act->ct.flow_table; attr->ct_attr.act_miss_cookie = act->miss_cookie; return 0; @@ -1990,6 +1991,9 @@ mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *priv, struct mlx5_flow_attr *att if (!priv) return -EOPNOTSUPP; + if (attr->ct_attr.offloaded) + return 0; + if (attr->ct_attr.ct_action & TCA_CT_ACT_CLEAR) { err = mlx5_tc_ct_entry_set_registers(priv, &attr->parse_attr->mod_hdr_acts, 0, 0, 0, 0); @@ -1999,11 +2003,15 @@ mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *priv, struct mlx5_flow_attr *att attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; } - if (!attr->ct_attr.nf_ft) /* means only ct clear action, and not ct_clear,ct() */ + if (!attr->ct_attr.nf_ft) { /* means only ct clear action, and not ct_clear,ct() */ + attr->ct_attr.offloaded = true; return 0; + } mutex_lock(&priv->control_lock); err = __mlx5_tc_ct_flow_offload(priv, attr); + if (!err) + attr->ct_attr.offloaded = true; mutex_unlock(&priv->control_lock); return err; @@ -2021,7 +2029,7 @@ void mlx5_tc_ct_delete_flow(struct mlx5_tc_ct_priv *priv, struct mlx5_flow_attr *attr) { - if (!attr->ct_attr.ft) /* no ct action, return */ + if (!attr->ct_attr.offloaded) /* no ct action, return */ return; if (!attr->ct_attr.nf_ft) /* means only ct clear action, and not ct_clear,ct() */ return; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h index 8e9316fa46d4..b66c5f98067f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h @@ -29,6 +29,7 @@ struct mlx5_ct_attr { u32 ct_labels_id; u32 act_miss_mapping; u64 act_miss_cookie; + bool offloaded; struct mlx5_ct_ft *ft; }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index f0e6095809fa..40589cebb773 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -662,8 +662,7 @@ static void mlx5e_free_xdpsq_desc(struct mlx5e_xdpsq *sq, /* No need to check ((page->pp_magic & ~0x3UL) == PP_SIGNATURE) * as we know this is a page_pool page. */ - page_pool_put_defragged_page(page->pp, - page, -1, true); + page_pool_recycle_direct(page->pp, page); } while (++n < num); break; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c index 88a5aed9d678..c7d191f66ad1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c @@ -190,6 +190,7 @@ static int accel_fs_tcp_create_groups(struct mlx5e_flow_table *ft, in = kvzalloc(inlen, GFP_KERNEL); if (!in || !ft->g) { kfree(ft->g); + ft->g = NULL; kvfree(in); return -ENOMEM; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 704b022cd1f0..41d37159e027 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -390,10 +390,18 @@ static void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix) { struct mlx5e_wqe_frag_info *wi = get_frag(rq, ix); - if (rq->xsk_pool) + if (rq->xsk_pool) { mlx5e_xsk_free_rx_wqe(wi); - else + } else { mlx5e_free_rx_wqe(rq, wi); + + /* Avoid a second release of the wqe pages: dealloc is called + * for the same missing wqes on regular RQ flush and on regular + * RQ close. This happens when XSK RQs come into play. + */ + for (int i = 0; i < rq->wqe.info.num_frags; i++, wi++) + wi->flags |= BIT(MLX5E_WQE_FRAG_SKIP_RELEASE); + } } static void mlx5e_xsk_free_rx_wqes(struct mlx5e_rq *rq, u16 ix, int wqe_bulk) @@ -1743,11 +1751,11 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi prog = rcu_dereference(rq->xdp_prog); if (prog && mlx5e_xdp_handle(rq, prog, &mxbuf)) { - if (test_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) { + if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) { struct mlx5e_wqe_frag_info *pwi; for (pwi = head_wi; pwi < wi; pwi++) - pwi->flags |= BIT(MLX5E_WQE_FRAG_SKIP_RELEASE); + pwi->frag_page->frags++; } return NULL; /* page/packet was consumed by XDP */ } @@ -1817,12 +1825,8 @@ static void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) rq, wi, cqe, cqe_bcnt); if (!skb) { /* probably for XDP */ - if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) { - /* do not return page to cache, - * it will be returned on XDP_TX completion. - */ - wi->flags |= BIT(MLX5E_WQE_FRAG_SKIP_RELEASE); - } + if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) + wi->frag_page->frags++; goto wq_cyc_pop; } @@ -1868,12 +1872,8 @@ static void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) rq, wi, cqe, cqe_bcnt); if (!skb) { /* probably for XDP */ - if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) { - /* do not return page to cache, - * it will be returned on XDP_TX completion. - */ - wi->flags |= BIT(MLX5E_WQE_FRAG_SKIP_RELEASE); - } + if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) + wi->frag_page->frags++; goto wq_cyc_pop; } @@ -2052,12 +2052,12 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w if (prog) { if (mlx5e_xdp_handle(rq, prog, &mxbuf)) { if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) { - int i; + struct mlx5e_frag_page *pfp; + + for (pfp = head_page; pfp < frag_page; pfp++) + pfp->frags++; - for (i = 0; i < sinfo->nr_frags; i++) - /* non-atomic */ - __set_bit(page_idx + i, wi->skip_release_bitmap); - return NULL; + wi->linear_page.frags++; } mlx5e_page_release_fragmented(rq, &wi->linear_page); return NULL; /* page/packet was consumed by XDP */ @@ -2155,7 +2155,7 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, cqe_bcnt, &mxbuf); if (mlx5e_xdp_handle(rq, prog, &mxbuf)) { if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) - __set_bit(page_idx, wi->skip_release_bitmap); /* non-atomic */ + frag_page->frags++; return NULL; /* page/packet was consumed by XDP */ } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 41dc26800f48..8d0a3f69693e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1639,7 +1639,8 @@ static void remove_unready_flow(struct mlx5e_tc_flow *flow) uplink_priv = &rpriv->uplink_priv; mutex_lock(&uplink_priv->unready_flows_lock); - unready_flow_del(flow); + if (flow_flag_test(flow, NOT_READY)) + unready_flow_del(flow); mutex_unlock(&uplink_priv->unready_flows_lock); } @@ -1932,8 +1933,7 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, esw_attr = attr->esw_attr; mlx5e_put_flow_tunnel_id(flow); - if (flow_flag_test(flow, NOT_READY)) - remove_unready_flow(flow); + remove_unready_flow(flow); if (mlx5e_is_offloaded_flow(flow)) { if (flow_flag_test(flow, SLOW)) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index faec7d7a4400..243c455f1029 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -807,6 +807,9 @@ static int mlx5_esw_vport_caps_get(struct mlx5_eswitch *esw, struct mlx5_vport * hca_caps = MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability); vport->info.roce_enabled = MLX5_GET(cmd_hca_cap, hca_caps, roce); + if (!MLX5_CAP_GEN_MAX(esw->dev, hca_cap_2)) + goto out_free; + memset(query_ctx, 0, query_out_sz); err = mlx5_vport_get_other_func_cap(esw->dev, vport->vport, query_ctx, MLX5_CAP_GENERAL_2); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/thermal.c b/drivers/net/ethernet/mellanox/mlx5/core/thermal.c index 20bb5eb266c1..52199d39657e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/thermal.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/thermal.c @@ -68,14 +68,19 @@ static struct thermal_zone_device_ops mlx5_thermal_ops = { int mlx5_thermal_init(struct mlx5_core_dev *mdev) { + char data[THERMAL_NAME_LENGTH]; struct mlx5_thermal *thermal; - struct thermal_zone_device *tzd; - const char *data = "mlx5"; + int err; - tzd = thermal_zone_get_zone_by_name(data); - if (!IS_ERR(tzd)) + if (!mlx5_core_is_pf(mdev) && !mlx5_core_is_ecpf(mdev)) return 0; + err = snprintf(data, sizeof(data), "mlx5_%s", dev_name(mdev->device)); + if (err < 0 || err >= sizeof(data)) { + mlx5_core_err(mdev, "Failed to setup thermal zone name, %d\n", err); + return -EINVAL; + } + thermal = kzalloc(sizeof(*thermal), GFP_KERNEL); if (!thermal) return -ENOMEM; @@ -89,10 +94,10 @@ int mlx5_thermal_init(struct mlx5_core_dev *mdev) &mlx5_thermal_ops, NULL, 0, MLX5_THERMAL_POLL_INT_MSEC); if (IS_ERR(thermal->tzdev)) { - dev_err(mdev->device, "Failed to register thermal zone device (%s) %ld\n", - data, PTR_ERR(thermal->tzdev)); + err = PTR_ERR(thermal->tzdev); + mlx5_core_err(mdev, "Failed to register thermal zone device (%s) %d\n", data, err); kfree(thermal); - return -EINVAL; + return err; } mdev->thermal = thermal; diff --git a/drivers/net/ethernet/microchip/Kconfig b/drivers/net/ethernet/microchip/Kconfig index 24c994baad13..329e374b9539 100644 --- a/drivers/net/ethernet/microchip/Kconfig +++ b/drivers/net/ethernet/microchip/Kconfig @@ -46,7 +46,7 @@ config LAN743X tristate "LAN743x support" depends on PCI depends on PTP_1588_CLOCK_OPTIONAL - select PHYLIB + select FIXED_PHY select CRC16 select CRC32 help diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 2fa833d041ba..56ccbd4c37fe 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -2927,7 +2927,6 @@ int ocelot_init(struct ocelot *ocelot) mutex_init(&ocelot->mact_lock); mutex_init(&ocelot->fwd_domain_lock); - mutex_init(&ocelot->tas_lock); spin_lock_init(&ocelot->ptp_clock_lock); spin_lock_init(&ocelot->ts_id_lock); diff --git a/drivers/net/ethernet/mscc/ocelot_mm.c b/drivers/net/ethernet/mscc/ocelot_mm.c index fb3145118d68..c815ae64e39d 100644 --- a/drivers/net/ethernet/mscc/ocelot_mm.c +++ b/drivers/net/ethernet/mscc/ocelot_mm.c @@ -67,10 +67,13 @@ void ocelot_port_update_active_preemptible_tcs(struct ocelot *ocelot, int port) val = mm->preemptible_tcs; /* Cut through switching doesn't work for preemptible priorities, - * so first make sure it is disabled. + * so first make sure it is disabled. Also, changing the preemptible + * TCs affects the oversized frame dropping logic, so that needs to be + * re-triggered. And since tas_guard_bands_update() also implicitly + * calls cut_through_fwd(), we don't need to explicitly call it. */ mm->active_preemptible_tcs = val; - ocelot->ops->cut_through_fwd(ocelot); + ocelot->ops->tas_guard_bands_update(ocelot, port); dev_dbg(ocelot->dev, "port %d %s/%s, MM TX %s, preemptible TCs 0x%x, active 0x%x\n", @@ -89,17 +92,14 @@ void ocelot_port_change_fp(struct ocelot *ocelot, int port, { struct ocelot_mm_state *mm = &ocelot->mm[port]; - mutex_lock(&ocelot->fwd_domain_lock); + lockdep_assert_held(&ocelot->fwd_domain_lock); if (mm->preemptible_tcs == preemptible_tcs) - goto out_unlock; + return; mm->preemptible_tcs = preemptible_tcs; ocelot_port_update_active_preemptible_tcs(ocelot, port); - -out_unlock: - mutex_unlock(&ocelot->fwd_domain_lock); } static void ocelot_mm_update_port_status(struct ocelot *ocelot, int port) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c index b8678da1cce5..ab7d217b98b3 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c @@ -353,12 +353,6 @@ err_out_reset: ionic_reset(ionic); err_out_teardown: ionic_dev_teardown(ionic); - pci_clear_master(pdev); - /* Don't fail the probe for these errors, keep - * the hw interface around for inspection - */ - return 0; - err_out_unmap_bars: ionic_unmap_bars(ionic); err_out_pci_release_regions: diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 7c20a44e549b..612b0015dc43 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -475,11 +475,6 @@ static void ionic_qcqs_free(struct ionic_lif *lif) static void ionic_link_qcq_interrupts(struct ionic_qcq *src_qcq, struct ionic_qcq *n_qcq) { - if (WARN_ON(n_qcq->flags & IONIC_QCQ_F_INTR)) { - ionic_intr_free(n_qcq->cq.lif->ionic, n_qcq->intr.index); - n_qcq->flags &= ~IONIC_QCQ_F_INTR; - } - n_qcq->intr.vector = src_qcq->intr.vector; n_qcq->intr.index = src_qcq->intr.index; n_qcq->napi_qcq = src_qcq->napi_qcq; diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c index 12405d71c5ee..0772eb14eabf 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c @@ -186,9 +186,6 @@ static int txgbe_calc_eeprom_checksum(struct wx *wx, u16 *checksum) if (eeprom_ptrs) kvfree(eeprom_ptrs); - if (*checksum > TXGBE_EEPROM_SUM) - return -EINVAL; - *checksum = TXGBE_EEPROM_SUM - *checksum; return 0; diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c index 6045bece2654..b4d3b9cde8bd 100644 --- a/drivers/net/netdevsim/dev.c +++ b/drivers/net/netdevsim/dev.c @@ -184,13 +184,10 @@ static ssize_t nsim_dev_trap_fa_cookie_write(struct file *file, cookie_len = (count - 1) / 2; if ((count - 1) % 2) return -EINVAL; - buf = kmalloc(count, GFP_KERNEL | __GFP_NOWARN); - if (!buf) - return -ENOMEM; - ret = simple_write_to_buffer(buf, count, ppos, data, count); - if (ret < 0) - goto free_buf; + buf = memdup_user(data, count); + if (IS_ERR(buf)) + return PTR_ERR(buf); fa_cookie = kmalloc(sizeof(*fa_cookie) + cookie_len, GFP_KERNEL | __GFP_NOWARN); diff --git a/drivers/net/wireless/cisco/airo.c b/drivers/net/wireless/cisco/airo.c index 7c4cc5f5e1eb..dbd13f7aa3e6 100644 --- a/drivers/net/wireless/cisco/airo.c +++ b/drivers/net/wireless/cisco/airo.c @@ -6157,8 +6157,11 @@ static int airo_get_rate(struct net_device *dev, struct iw_param *vwrq = &wrqu->bitrate; struct airo_info *local = dev->ml_priv; StatusRid status_rid; /* Card status info */ + int ret; - readStatusRid(local, &status_rid, 1); + ret = readStatusRid(local, &status_rid, 1); + if (ret) + return -EBUSY; vwrq->value = le16_to_cpu(status_rid.currentXmitRate) * 500000; /* If more than one rate, set auto */ diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c index aa4320ca4c30..d594694206b3 100644 --- a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c +++ b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c @@ -84,7 +84,6 @@ const struct iwl_ht_params iwl_22000_ht_params = { .mac_addr_from_csr = 0x380, \ .ht_params = &iwl_22000_ht_params, \ .nvm_ver = IWL_22000_NVM_VERSION, \ - .trans.use_tfh = true, \ .trans.rf_id = true, \ .trans.gen2 = true, \ .nvm_type = IWL_NVM_EXT, \ @@ -122,7 +121,6 @@ const struct iwl_ht_params iwl_22000_ht_params = { const struct iwl_cfg_trans_params iwl_qu_trans_cfg = { .mq_rx_supported = true, - .use_tfh = true, .rf_id = true, .gen2 = true, .device_family = IWL_DEVICE_FAMILY_22000, @@ -134,7 +132,6 @@ const struct iwl_cfg_trans_params iwl_qu_trans_cfg = { const struct iwl_cfg_trans_params iwl_qu_medium_latency_trans_cfg = { .mq_rx_supported = true, - .use_tfh = true, .rf_id = true, .gen2 = true, .device_family = IWL_DEVICE_FAMILY_22000, @@ -146,7 +143,6 @@ const struct iwl_cfg_trans_params iwl_qu_medium_latency_trans_cfg = { const struct iwl_cfg_trans_params iwl_qu_long_latency_trans_cfg = { .mq_rx_supported = true, - .use_tfh = true, .rf_id = true, .gen2 = true, .device_family = IWL_DEVICE_FAMILY_22000, @@ -200,7 +196,6 @@ const struct iwl_cfg_trans_params iwl_ax200_trans_cfg = { .device_family = IWL_DEVICE_FAMILY_22000, .base_params = &iwl_22000_base_params, .mq_rx_supported = true, - .use_tfh = true, .rf_id = true, .gen2 = true, .bisr_workaround = 1, diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h index 742096c5a36a..241a9e3f2a1a 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h @@ -256,7 +256,6 @@ enum iwl_cfg_trans_ltr_delay { * @xtal_latency: power up latency to get the xtal stabilized * @extra_phy_cfg_flags: extra configuration flags to pass to the PHY * @rf_id: need to read rf_id to determine the firmware image - * @use_tfh: use TFH * @gen2: 22000 and on transport operation * @mq_rx_supported: multi-queue rx support * @integrated: discrete or integrated @@ -271,7 +270,6 @@ struct iwl_cfg_trans_params { u32 xtal_latency; u32 extra_phy_cfg_flags; u32 rf_id:1, - use_tfh:1, gen2:1, mq_rx_supported:1, integrated:1, diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-fh.h b/drivers/net/wireless/intel/iwlwifi/iwl-fh.h index bedd78a47f67..4e4a60ddf9b2 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-fh.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-fh.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ /* - * Copyright (C) 2005-2014, 2018-2021 Intel Corporation + * Copyright (C) 2005-2014, 2018-2021, 2023 Intel Corporation * Copyright (C) 2015-2017 Intel Deutschland GmbH */ #ifndef __iwl_fh_h__ @@ -71,7 +71,7 @@ static inline unsigned int FH_MEM_CBBC_QUEUE(struct iwl_trans *trans, unsigned int chnl) { - if (trans->trans_cfg->use_tfh) { + if (trans->trans_cfg->gen2) { WARN_ON_ONCE(chnl >= 64); return TFH_TFDQ_CBB_TABLE + 8 * chnl; } diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.c b/drivers/net/wireless/intel/iwlwifi/iwl-trans.c index b1af9359cea5..4bd759432d44 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.c @@ -2,7 +2,7 @@ /* * Copyright (C) 2015 Intel Mobile Communications GmbH * Copyright (C) 2016-2017 Intel Deutschland GmbH - * Copyright (C) 2019-2021 Intel Corporation + * Copyright (C) 2019-2021, 2023 Intel Corporation */ #include <linux/kernel.h> #include <linux/bsearch.h> @@ -42,7 +42,7 @@ struct iwl_trans *iwl_trans_alloc(unsigned int priv_size, WARN_ON(!ops->wait_txq_empty && !ops->wait_tx_queues_empty); - if (trans->trans_cfg->use_tfh) { + if (trans->trans_cfg->gen2) { trans->txqs.tfd.addr_size = 64; trans->txqs.tfd.max_tbs = IWL_TFH_NUM_TBS; trans->txqs.tfd.size = sizeof(struct iwl_tfh_tfd); @@ -101,7 +101,7 @@ int iwl_trans_init(struct iwl_trans *trans) /* Some things must not change even if the config does */ WARN_ON(trans->txqs.tfd.addr_size != - (trans->trans_cfg->use_tfh ? 64 : 36)); + (trans->trans_cfg->gen2 ? 64 : 36)); snprintf(trans->dev_cmd_pool_name, sizeof(trans->dev_cmd_pool_name), "iwl_cmd_pool:%s", dev_name(trans->dev)); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h index b83df0631279..b18c91c5dd5d 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h @@ -1450,7 +1450,7 @@ static inline bool iwl_mvm_has_new_station_api(const struct iwl_fw *fw) static inline bool iwl_mvm_has_new_tx_api(struct iwl_mvm *mvm) { /* TODO - replace with TLV once defined */ - return mvm->trans->trans_cfg->use_tfh; + return mvm->trans->trans_cfg->gen2; } static inline bool iwl_mvm_has_unified_ucode(struct iwl_mvm *mvm) diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c index eacbbdbffb5e..3e988da44973 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c @@ -819,7 +819,7 @@ static int iwl_pcie_load_cpu_sections_8000(struct iwl_trans *trans, iwl_enable_interrupts(trans); - if (trans->trans_cfg->use_tfh) { + if (trans->trans_cfg->gen2) { if (cpu == 1) iwl_write_prph(trans, UREG_UCODE_LOAD_STATUS, 0xFFFF); @@ -3394,7 +3394,7 @@ iwl_trans_pcie_dump_data(struct iwl_trans *trans, u8 tfdidx; u32 caplen, cmdlen; - if (trans->trans_cfg->use_tfh) + if (trans->trans_cfg->gen2) tfdidx = idx; else tfdidx = ptr; diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c index 1337fa95f657..790e5b124740 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c @@ -364,7 +364,7 @@ void iwl_trans_pcie_tx_reset(struct iwl_trans *trans) for (txq_id = 0; txq_id < trans->trans_cfg->base_params->num_of_queues; txq_id++) { struct iwl_txq *txq = trans->txqs.txq[txq_id]; - if (trans->trans_cfg->use_tfh) + if (trans->trans_cfg->gen2) iwl_write_direct64(trans, FH_MEM_CBBC_QUEUE(trans, txq_id), txq->dma_addr); diff --git a/drivers/net/wireless/intel/iwlwifi/queue/tx.c b/drivers/net/wireless/intel/iwlwifi/queue/tx.c index fbacbe9ada15..5bb3cc3367c9 100644 --- a/drivers/net/wireless/intel/iwlwifi/queue/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/queue/tx.c @@ -985,7 +985,7 @@ void iwl_txq_log_scd_error(struct iwl_trans *trans, struct iwl_txq *txq) bool active; u8 fifo; - if (trans->trans_cfg->use_tfh) { + if (trans->trans_cfg->gen2) { IWL_ERR(trans, "Queue %d is stuck %d %d\n", txq_id, txq->read_ptr, txq->write_ptr); /* TODO: access new SCD registers and dump them */ @@ -1040,7 +1040,7 @@ int iwl_txq_alloc(struct iwl_trans *trans, struct iwl_txq *txq, int slots_num, if (WARN_ON(txq->entries || txq->tfds)) return -EINVAL; - if (trans->trans_cfg->use_tfh) + if (trans->trans_cfg->gen2) tfd_sz = trans->txqs.tfd.size * slots_num; timer_setup(&txq->stuck_timer, iwl_txq_stuck_timer, 0); @@ -1347,7 +1347,7 @@ static inline dma_addr_t iwl_txq_gen1_tfd_tb_get_addr(struct iwl_trans *trans, dma_addr_t addr; dma_addr_t hi_len; - if (trans->trans_cfg->use_tfh) { + if (trans->trans_cfg->gen2) { struct iwl_tfh_tfd *tfh_tfd = _tfd; struct iwl_tfh_tb *tfh_tb = &tfh_tfd->tbs[idx]; @@ -1408,7 +1408,7 @@ void iwl_txq_gen1_tfd_unmap(struct iwl_trans *trans, meta->tbs = 0; - if (trans->trans_cfg->use_tfh) { + if (trans->trans_cfg->gen2) { struct iwl_tfh_tfd *tfd_fh = (void *)tfd; tfd_fh->num_tbs = 0; @@ -1625,7 +1625,7 @@ void iwl_txq_reclaim(struct iwl_trans *trans, int txq_id, int ssn, txq->entries[read_ptr].skb = NULL; - if (!trans->trans_cfg->use_tfh) + if (!trans->trans_cfg->gen2) iwl_txq_gen1_inval_byte_cnt_tbl(trans, txq); iwl_txq_free_tfd(trans, txq); diff --git a/drivers/net/wireless/intel/iwlwifi/queue/tx.h b/drivers/net/wireless/intel/iwlwifi/queue/tx.h index eca53bfd326d..1e4a24ab9bab 100644 --- a/drivers/net/wireless/intel/iwlwifi/queue/tx.h +++ b/drivers/net/wireless/intel/iwlwifi/queue/tx.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ /* - * Copyright (C) 2020-2022 Intel Corporation + * Copyright (C) 2020-2023 Intel Corporation */ #ifndef __iwl_trans_queue_tx_h__ #define __iwl_trans_queue_tx_h__ @@ -38,7 +38,7 @@ static inline void iwl_wake_queue(struct iwl_trans *trans, static inline void *iwl_txq_get_tfd(struct iwl_trans *trans, struct iwl_txq *txq, int idx) { - if (trans->trans_cfg->use_tfh) + if (trans->trans_cfg->gen2) idx = iwl_txq_get_cmd_index(txq, idx); return (u8 *)txq->tfds + trans->txqs.tfd.size * idx; @@ -135,7 +135,7 @@ static inline u8 iwl_txq_gen1_tfd_get_num_tbs(struct iwl_trans *trans, { struct iwl_tfd *tfd; - if (trans->trans_cfg->use_tfh) { + if (trans->trans_cfg->gen2) { struct iwl_tfh_tfd *tfh_tfd = _tfd; return le16_to_cpu(tfh_tfd->num_tbs) & 0x1f; @@ -151,7 +151,7 @@ static inline u16 iwl_txq_gen1_tfd_tb_get_len(struct iwl_trans *trans, struct iwl_tfd *tfd; struct iwl_tfd_tb *tb; - if (trans->trans_cfg->use_tfh) { + if (trans->trans_cfg->gen2) { struct iwl_tfh_tfd *tfh_tfd = _tfd; struct iwl_tfh_tb *tfh_tb = &tfh_tfd->tbs[idx]; diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/dma.c b/drivers/net/wireless/mediatek/mt76/mt7921/dma.c index f0a80c2b476a..4153cd6c2a01 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/dma.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/dma.c @@ -231,10 +231,6 @@ int mt7921_dma_init(struct mt7921_dev *dev) if (ret) return ret; - ret = mt7921_wfsys_reset(dev); - if (ret) - return ret; - /* init tx queue */ ret = mt76_connac_init_tx_queues(dev->phy.mt76, MT7921_TXQ_BAND0, MT7921_TX_RING_SIZE, diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c index c69ce6df4956..f55caa00ac69 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c @@ -476,12 +476,6 @@ static int mt7921_load_firmware(struct mt7921_dev *dev) { int ret; - ret = mt76_get_field(dev, MT_CONN_ON_MISC, MT_TOP_MISC2_FW_N9_RDY); - if (ret && mt76_is_mmio(&dev->mt76)) { - dev_dbg(dev->mt76.dev, "Firmware is already download\n"); - goto fw_loaded; - } - ret = mt76_connac2_load_patch(&dev->mt76, mt7921_patch_name(dev)); if (ret) return ret; @@ -504,8 +498,6 @@ static int mt7921_load_firmware(struct mt7921_dev *dev) return -EIO; } -fw_loaded: - #ifdef CONFIG_PM dev->mt76.hw->wiphy->wowlan = &mt76_connac_wowlan_support; #endif /* CONFIG_PM */ diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c index ddb1fa4ee01d..95610a117d2f 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c @@ -325,6 +325,10 @@ static int mt7921_pci_probe(struct pci_dev *pdev, bus_ops->rmw = mt7921_rmw; dev->mt76.bus = bus_ops; + ret = mt7921e_mcu_fw_pmctrl(dev); + if (ret) + goto err_free_dev; + ret = __mt7921e_mcu_drv_pmctrl(dev); if (ret) goto err_free_dev; @@ -333,6 +337,10 @@ static int mt7921_pci_probe(struct pci_dev *pdev, (mt7921_l1_rr(dev, MT_HW_REV) & 0xff); dev_info(mdev->dev, "ASIC revision: %04x\n", mdev->rev); + ret = mt7921_wfsys_reset(dev); + if (ret) + goto err_free_dev; + mt76_wr(dev, MT_WFDMA0_HOST_INT_ENA, 0); mt76_wr(dev, MT_PCIE_MAC_INT_ENABLE, 0xff); diff --git a/drivers/net/wireless/realtek/rtw89/debug.c b/drivers/net/wireless/realtek/rtw89/debug.c index 1db2d59d33ff..a4bbac916e22 100644 --- a/drivers/net/wireless/realtek/rtw89/debug.c +++ b/drivers/net/wireless/realtek/rtw89/debug.c @@ -3026,17 +3026,18 @@ static ssize_t rtw89_debug_priv_send_h2c_set(struct file *filp, struct rtw89_debugfs_priv *debugfs_priv = filp->private_data; struct rtw89_dev *rtwdev = debugfs_priv->rtwdev; u8 *h2c; + int ret; u16 h2c_len = count / 2; h2c = rtw89_hex2bin_user(rtwdev, user_buf, count); if (IS_ERR(h2c)) return -EFAULT; - rtw89_fw_h2c_raw(rtwdev, h2c, h2c_len); + ret = rtw89_fw_h2c_raw(rtwdev, h2c, h2c_len); kfree(h2c); - return count; + return ret ? ret : count; } static int diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c index 9b5fccdbc7d6..6df7f377d2f9 100644 --- a/drivers/s390/net/ism_drv.c +++ b/drivers/s390/net/ism_drv.c @@ -36,7 +36,7 @@ static const struct smcd_ops ism_ops; static struct ism_client *clients[MAX_CLIENTS]; /* use an array rather than */ /* a list for fast mapping */ static u8 max_client; -static DEFINE_SPINLOCK(clients_lock); +static DEFINE_MUTEX(clients_lock); struct ism_dev_list { struct list_head list; struct mutex mutex; /* protects ism device list */ @@ -47,14 +47,22 @@ static struct ism_dev_list ism_dev_list = { .mutex = __MUTEX_INITIALIZER(ism_dev_list.mutex), }; +static void ism_setup_forwarding(struct ism_client *client, struct ism_dev *ism) +{ + unsigned long flags; + + spin_lock_irqsave(&ism->lock, flags); + ism->subs[client->id] = client; + spin_unlock_irqrestore(&ism->lock, flags); +} + int ism_register_client(struct ism_client *client) { struct ism_dev *ism; - unsigned long flags; int i, rc = -ENOSPC; mutex_lock(&ism_dev_list.mutex); - spin_lock_irqsave(&clients_lock, flags); + mutex_lock(&clients_lock); for (i = 0; i < MAX_CLIENTS; ++i) { if (!clients[i]) { clients[i] = client; @@ -65,12 +73,14 @@ int ism_register_client(struct ism_client *client) break; } } - spin_unlock_irqrestore(&clients_lock, flags); + mutex_unlock(&clients_lock); + if (i < MAX_CLIENTS) { /* initialize with all devices that we got so far */ list_for_each_entry(ism, &ism_dev_list.list, list) { ism->priv[i] = NULL; client->add(ism); + ism_setup_forwarding(client, ism); } } mutex_unlock(&ism_dev_list.mutex); @@ -86,25 +96,32 @@ int ism_unregister_client(struct ism_client *client) int rc = 0; mutex_lock(&ism_dev_list.mutex); - spin_lock_irqsave(&clients_lock, flags); - clients[client->id] = NULL; - if (client->id + 1 == max_client) - max_client--; - spin_unlock_irqrestore(&clients_lock, flags); list_for_each_entry(ism, &ism_dev_list.list, list) { + spin_lock_irqsave(&ism->lock, flags); + /* Stop forwarding IRQs and events */ + ism->subs[client->id] = NULL; for (int i = 0; i < ISM_NR_DMBS; ++i) { if (ism->sba_client_arr[i] == client->id) { - pr_err("%s: attempt to unregister client '%s'" - "with registered dmb(s)\n", __func__, - client->name); + WARN(1, "%s: attempt to unregister '%s' with registered dmb(s)\n", + __func__, client->name); rc = -EBUSY; - goto out; + goto err_reg_dmb; } } + spin_unlock_irqrestore(&ism->lock, flags); } -out: mutex_unlock(&ism_dev_list.mutex); + mutex_lock(&clients_lock); + clients[client->id] = NULL; + if (client->id + 1 == max_client) + max_client--; + mutex_unlock(&clients_lock); + return rc; + +err_reg_dmb: + spin_unlock_irqrestore(&ism->lock, flags); + mutex_unlock(&ism_dev_list.mutex); return rc; } EXPORT_SYMBOL_GPL(ism_unregister_client); @@ -328,6 +345,7 @@ int ism_register_dmb(struct ism_dev *ism, struct ism_dmb *dmb, struct ism_client *client) { union ism_reg_dmb cmd; + unsigned long flags; int ret; ret = ism_alloc_dmb(ism, dmb); @@ -351,7 +369,9 @@ int ism_register_dmb(struct ism_dev *ism, struct ism_dmb *dmb, goto out; } dmb->dmb_tok = cmd.response.dmb_tok; + spin_lock_irqsave(&ism->lock, flags); ism->sba_client_arr[dmb->sba_idx - ISM_DMB_BIT_OFFSET] = client->id; + spin_unlock_irqrestore(&ism->lock, flags); out: return ret; } @@ -360,6 +380,7 @@ EXPORT_SYMBOL_GPL(ism_register_dmb); int ism_unregister_dmb(struct ism_dev *ism, struct ism_dmb *dmb) { union ism_unreg_dmb cmd; + unsigned long flags; int ret; memset(&cmd, 0, sizeof(cmd)); @@ -368,7 +389,9 @@ int ism_unregister_dmb(struct ism_dev *ism, struct ism_dmb *dmb) cmd.request.dmb_tok = dmb->dmb_tok; + spin_lock_irqsave(&ism->lock, flags); ism->sba_client_arr[dmb->sba_idx - ISM_DMB_BIT_OFFSET] = NO_CLIENT; + spin_unlock_irqrestore(&ism->lock, flags); ret = ism_cmd(ism, &cmd); if (ret && ret != ISM_ERROR) @@ -491,6 +514,7 @@ static u16 ism_get_chid(struct ism_dev *ism) static void ism_handle_event(struct ism_dev *ism) { struct ism_event *entry; + struct ism_client *clt; int i; while ((ism->ieq_idx + 1) != READ_ONCE(ism->ieq->header.idx)) { @@ -499,21 +523,21 @@ static void ism_handle_event(struct ism_dev *ism) entry = &ism->ieq->entry[ism->ieq_idx]; debug_event(ism_debug_info, 2, entry, sizeof(*entry)); - spin_lock(&clients_lock); - for (i = 0; i < max_client; ++i) - if (clients[i]) - clients[i]->handle_event(ism, entry); - spin_unlock(&clients_lock); + for (i = 0; i < max_client; ++i) { + clt = ism->subs[i]; + if (clt) + clt->handle_event(ism, entry); + } } } static irqreturn_t ism_handle_irq(int irq, void *data) { struct ism_dev *ism = data; - struct ism_client *clt; unsigned long bit, end; unsigned long *bv; u16 dmbemask; + u8 client_id; bv = (void *) &ism->sba->dmb_bits[ISM_DMB_WORD_OFFSET]; end = sizeof(ism->sba->dmb_bits) * BITS_PER_BYTE - ISM_DMB_BIT_OFFSET; @@ -530,8 +554,10 @@ static irqreturn_t ism_handle_irq(int irq, void *data) dmbemask = ism->sba->dmbe_mask[bit + ISM_DMB_BIT_OFFSET]; ism->sba->dmbe_mask[bit + ISM_DMB_BIT_OFFSET] = 0; barrier(); - clt = clients[ism->sba_client_arr[bit]]; - clt->handle_irq(ism, bit + ISM_DMB_BIT_OFFSET, dmbemask); + client_id = ism->sba_client_arr[bit]; + if (unlikely(client_id == NO_CLIENT || !ism->subs[client_id])) + continue; + ism->subs[client_id]->handle_irq(ism, bit + ISM_DMB_BIT_OFFSET, dmbemask); } if (ism->sba->e) { @@ -548,20 +574,9 @@ static u64 ism_get_local_gid(struct ism_dev *ism) return ism->local_gid; } -static void ism_dev_add_work_func(struct work_struct *work) -{ - struct ism_client *client = container_of(work, struct ism_client, - add_work); - - client->add(client->tgt_ism); - atomic_dec(&client->tgt_ism->add_dev_cnt); - wake_up(&client->tgt_ism->waitq); -} - static int ism_dev_init(struct ism_dev *ism) { struct pci_dev *pdev = ism->pdev; - unsigned long flags; int i, ret; ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSI); @@ -594,25 +609,16 @@ static int ism_dev_init(struct ism_dev *ism) /* hardware is V2 capable */ ism_create_system_eid(); - init_waitqueue_head(&ism->waitq); - atomic_set(&ism->free_clients_cnt, 0); - atomic_set(&ism->add_dev_cnt, 0); - - wait_event(ism->waitq, !atomic_read(&ism->add_dev_cnt)); - spin_lock_irqsave(&clients_lock, flags); - for (i = 0; i < max_client; ++i) + mutex_lock(&ism_dev_list.mutex); + mutex_lock(&clients_lock); + for (i = 0; i < max_client; ++i) { if (clients[i]) { - INIT_WORK(&clients[i]->add_work, - ism_dev_add_work_func); - clients[i]->tgt_ism = ism; - atomic_inc(&ism->add_dev_cnt); - schedule_work(&clients[i]->add_work); + clients[i]->add(ism); + ism_setup_forwarding(clients[i], ism); } - spin_unlock_irqrestore(&clients_lock, flags); - - wait_event(ism->waitq, !atomic_read(&ism->add_dev_cnt)); + } + mutex_unlock(&clients_lock); - mutex_lock(&ism_dev_list.mutex); list_add(&ism->list, &ism_dev_list.list); mutex_unlock(&ism_dev_list.mutex); @@ -687,36 +693,24 @@ err_dev: return ret; } -static void ism_dev_remove_work_func(struct work_struct *work) -{ - struct ism_client *client = container_of(work, struct ism_client, - remove_work); - - client->remove(client->tgt_ism); - atomic_dec(&client->tgt_ism->free_clients_cnt); - wake_up(&client->tgt_ism->waitq); -} - -/* Callers must hold ism_dev_list.mutex */ static void ism_dev_exit(struct ism_dev *ism) { struct pci_dev *pdev = ism->pdev; unsigned long flags; int i; - wait_event(ism->waitq, !atomic_read(&ism->free_clients_cnt)); - spin_lock_irqsave(&clients_lock, flags); + spin_lock_irqsave(&ism->lock, flags); for (i = 0; i < max_client; ++i) - if (clients[i]) { - INIT_WORK(&clients[i]->remove_work, - ism_dev_remove_work_func); - clients[i]->tgt_ism = ism; - atomic_inc(&ism->free_clients_cnt); - schedule_work(&clients[i]->remove_work); - } - spin_unlock_irqrestore(&clients_lock, flags); + ism->subs[i] = NULL; + spin_unlock_irqrestore(&ism->lock, flags); - wait_event(ism->waitq, !atomic_read(&ism->free_clients_cnt)); + mutex_lock(&ism_dev_list.mutex); + mutex_lock(&clients_lock); + for (i = 0; i < max_client; ++i) { + if (clients[i]) + clients[i]->remove(ism); + } + mutex_unlock(&clients_lock); if (SYSTEM_EID.serial_number[0] != '0' || SYSTEM_EID.type[0] != '0') @@ -727,15 +721,14 @@ static void ism_dev_exit(struct ism_dev *ism) kfree(ism->sba_client_arr); pci_free_irq_vectors(pdev); list_del_init(&ism->list); + mutex_unlock(&ism_dev_list.mutex); } static void ism_remove(struct pci_dev *pdev) { struct ism_dev *ism = dev_get_drvdata(&pdev->dev); - mutex_lock(&ism_dev_list.mutex); ism_dev_exit(ism); - mutex_unlock(&ism_dev_list.mutex); pci_release_mem_regions(pdev); pci_disable_device(pdev); diff --git a/include/linux/ism.h b/include/linux/ism.h index ea2bcdae7401..9a4c204df3da 100644 --- a/include/linux/ism.h +++ b/include/linux/ism.h @@ -44,9 +44,7 @@ struct ism_dev { u64 local_gid; int ieq_idx; - atomic_t free_clients_cnt; - atomic_t add_dev_cnt; - wait_queue_head_t waitq; + struct ism_client *subs[MAX_CLIENTS]; }; struct ism_event { @@ -68,9 +66,6 @@ struct ism_client { */ void (*handle_irq)(struct ism_dev *dev, unsigned int bit, u16 dmbemask); /* Private area - don't touch! */ - struct work_struct remove_work; - struct work_struct add_work; - struct ism_dev *tgt_ism; u8 id; }; diff --git a/include/net/netfilter/nf_conntrack_tuple.h b/include/net/netfilter/nf_conntrack_tuple.h index 9334371c94e2..f7dd950ff250 100644 --- a/include/net/netfilter/nf_conntrack_tuple.h +++ b/include/net/netfilter/nf_conntrack_tuple.h @@ -67,6 +67,9 @@ struct nf_conntrack_tuple { /* The protocol. */ u_int8_t protonum; + /* The direction must be ignored for the tuplehash */ + struct { } __nfct_hash_offsetend; + /* The direction (for tuplehash) */ u_int8_t dir; } dst; diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 84f2fd85fd5a..640441a2f926 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1211,6 +1211,29 @@ int __nft_release_basechain(struct nft_ctx *ctx); unsigned int nft_do_chain(struct nft_pktinfo *pkt, void *priv); +static inline bool nft_use_inc(u32 *use) +{ + if (*use == UINT_MAX) + return false; + + (*use)++; + + return true; +} + +static inline void nft_use_dec(u32 *use) +{ + WARN_ON_ONCE((*use)-- == 0); +} + +/* For error and abort path: restore use counter to previous state. */ +static inline void nft_use_inc_restore(u32 *use) +{ + WARN_ON_ONCE(!nft_use_inc(use)); +} + +#define nft_use_dec_restore nft_use_dec + /** * struct nft_table - nf_tables table * @@ -1296,8 +1319,8 @@ struct nft_object { struct list_head list; struct rhlist_head rhlhead; struct nft_object_hash_key key; - u32 genmask:2, - use:30; + u32 genmask:2; + u32 use; u64 handle; u16 udlen; u8 *udata; @@ -1399,8 +1422,8 @@ struct nft_flowtable { char *name; int hooknum; int ops_len; - u32 genmask:2, - use:30; + u32 genmask:2; + u32 use; u64 handle; /* runtime data below here */ struct list_head hook_list ____cacheline_aligned; diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index e98aac9d5ad5..15960564e0c3 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -134,7 +134,7 @@ extern const struct nla_policy rtm_tca_policy[TCA_MAX + 1]; */ static inline unsigned int psched_mtu(const struct net_device *dev) { - return dev->mtu + dev->hard_header_len; + return READ_ONCE(dev->mtu) + dev->hard_header_len; } static inline struct net *qdisc_net(struct Qdisc *q) diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 22aae505c813..a8c2817335b9 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -663,6 +663,7 @@ struct ocelot_ops { struct flow_stats *stats); void (*cut_through_fwd)(struct ocelot *ocelot); void (*tas_clock_adjust)(struct ocelot *ocelot); + void (*tas_guard_bands_update)(struct ocelot *ocelot, int port); void (*update_stats)(struct ocelot *ocelot); }; @@ -863,12 +864,12 @@ struct ocelot { struct mutex stat_view_lock; /* Lock for serializing access to the MAC table */ struct mutex mact_lock; - /* Lock for serializing forwarding domain changes */ + /* Lock for serializing forwarding domain changes, including the + * configuration of the Time-Aware Shaper, MAC Merge layer and + * cut-through forwarding, on which it depends + */ struct mutex fwd_domain_lock; - /* Lock for serializing Time-Aware Shaper changes */ - struct mutex tas_lock; - struct workqueue_struct *owq; u8 ptp:1; diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index 8a33e8747a0e..6ae02be7a48e 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -122,22 +122,6 @@ static void get_cpu_map_entry(struct bpf_cpu_map_entry *rcpu) atomic_inc(&rcpu->refcnt); } -/* called from workqueue, to workaround syscall using preempt_disable */ -static void cpu_map_kthread_stop(struct work_struct *work) -{ - struct bpf_cpu_map_entry *rcpu; - - rcpu = container_of(work, struct bpf_cpu_map_entry, kthread_stop_wq); - - /* Wait for flush in __cpu_map_entry_free(), via full RCU barrier, - * as it waits until all in-flight call_rcu() callbacks complete. - */ - rcu_barrier(); - - /* kthread_stop will wake_up_process and wait for it to complete */ - kthread_stop(rcpu->kthread); -} - static void __cpu_map_ring_cleanup(struct ptr_ring *ring) { /* The tear-down procedure should have made sure that queue is @@ -165,6 +149,30 @@ static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu) } } +/* called from workqueue, to workaround syscall using preempt_disable */ +static void cpu_map_kthread_stop(struct work_struct *work) +{ + struct bpf_cpu_map_entry *rcpu; + int err; + + rcpu = container_of(work, struct bpf_cpu_map_entry, kthread_stop_wq); + + /* Wait for flush in __cpu_map_entry_free(), via full RCU barrier, + * as it waits until all in-flight call_rcu() callbacks complete. + */ + rcu_barrier(); + + /* kthread_stop will wake_up_process and wait for it to complete */ + err = kthread_stop(rcpu->kthread); + if (err) { + /* kthread_stop may be called before cpu_map_kthread_run + * is executed, so we need to release the memory related + * to rcpu. + */ + put_cpu_map_entry(rcpu); + } +} + static void cpu_map_bpf_prog_run_skb(struct bpf_cpu_map_entry *rcpu, struct list_head *listp, struct xdp_cpumap_stats *stats) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 11e54dd8b6dd..930b5555cfd3 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5642,8 +5642,9 @@ continue_func: verbose(env, "verifier bug. subprog has tail_call and async cb\n"); return -EFAULT; } - /* async callbacks don't increase bpf prog stack size */ - continue; + /* async callbacks don't increase bpf prog stack size unless called directly */ + if (!bpf_pseudo_call(insn + i)) + continue; } i = next_insn; diff --git a/net/core/net-traces.c b/net/core/net-traces.c index 805b7385dd8d..6aef976bc1da 100644 --- a/net/core/net-traces.c +++ b/net/core/net-traces.c @@ -63,4 +63,6 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(napi_poll); EXPORT_TRACEPOINT_SYMBOL_GPL(tcp_send_reset); EXPORT_TRACEPOINT_SYMBOL_GPL(tcp_bad_csum); +EXPORT_TRACEPOINT_SYMBOL_GPL(udp_fail_queue_rcv_skb); + EXPORT_TRACEPOINT_SYMBOL_GPL(sk_data_ready); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 6c5915efbc17..a298992060e6 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4261,6 +4261,11 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb, skb_push(skb, -skb_network_offset(skb) + offset); + /* Ensure the head is writeable before touching the shared info */ + err = skb_unclone(skb, GFP_ATOMIC); + if (err) + goto err_linearize; + skb_shinfo(skb)->frag_list = NULL; while (list_skb) { diff --git a/net/core/xdp.c b/net/core/xdp.c index 41e5ca8643ec..8362130bf085 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -741,7 +741,7 @@ __bpf_kfunc int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, u32 *hash, __diag_pop(); BTF_SET8_START(xdp_metadata_kfunc_ids) -#define XDP_METADATA_KFUNC(_, name) BTF_ID_FLAGS(func, name, 0) +#define XDP_METADATA_KFUNC(_, name) BTF_ID_FLAGS(func, name, KF_TRUSTED_ARGS) XDP_METADATA_KFUNC_xxx #undef XDP_METADATA_KFUNC BTF_SET8_END(xdp_metadata_kfunc_ids) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 5479da08ef40..e5213e598a04 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -318,9 +318,8 @@ static void addrconf_del_dad_work(struct inet6_ifaddr *ifp) static void addrconf_mod_rs_timer(struct inet6_dev *idev, unsigned long when) { - if (!timer_pending(&idev->rs_timer)) + if (!mod_timer(&idev->rs_timer, jiffies + when)) in6_dev_hold(idev); - mod_timer(&idev->rs_timer, jiffies + when); } static void addrconf_mod_dad_work(struct inet6_ifaddr *ifp, diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 9edf1f45b1ed..65fa5014bc85 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -424,7 +424,10 @@ static struct net_device *icmp6_dev(const struct sk_buff *skb) if (unlikely(dev->ifindex == LOOPBACK_IFINDEX || netif_is_l3_master(skb->dev))) { const struct rt6_info *rt6 = skb_rt6_info(skb); - if (rt6) + /* The destination could be an external IP in Ext Hdr (SRv6, RPL, etc.), + * and ip6_null_entry could be set to skb if no route is found. + */ + if (rt6 && rt6->rt6i_idev) dev = rt6->rt6i_idev->dev; } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 317b01c9bc39..b7c972aa09a7 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -45,6 +45,7 @@ #include <net/tcp_states.h> #include <net/ip6_checksum.h> #include <net/ip6_tunnel.h> +#include <trace/events/udp.h> #include <net/xfrm.h> #include <net/inet_hashtables.h> #include <net/inet6_hashtables.h> @@ -90,7 +91,7 @@ static u32 udp6_ehashfn(const struct net *net, fhash = __ipv6_addr_jhash(faddr, udp_ipv6_hash_secret); return __inet6_ehashfn(lhash, lport, fhash, fport, - udp_ipv6_hash_secret + net_hash_mix(net)); + udp6_ehash_secret + net_hash_mix(net)); } int udp_v6_get_port(struct sock *sk, unsigned short snum) @@ -680,6 +681,7 @@ static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) } UDP6_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); kfree_skb_reason(skb, drop_reason); + trace_udp_fail_queue_rcv_skb(rc, sk); return -1; } diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index d119f1d4c2fc..992393102d5f 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -211,24 +211,18 @@ static u32 hash_conntrack_raw(const struct nf_conntrack_tuple *tuple, unsigned int zoneid, const struct net *net) { - u64 a, b, c, d; + siphash_key_t key; get_random_once(&nf_conntrack_hash_rnd, sizeof(nf_conntrack_hash_rnd)); - /* The direction must be ignored, handle usable tuplehash members manually */ - a = (u64)tuple->src.u3.all[0] << 32 | tuple->src.u3.all[3]; - b = (u64)tuple->dst.u3.all[0] << 32 | tuple->dst.u3.all[3]; + key = nf_conntrack_hash_rnd; - c = (__force u64)tuple->src.u.all << 32 | (__force u64)tuple->dst.u.all << 16; - c |= tuple->dst.protonum; + key.key[0] ^= zoneid; + key.key[1] ^= net_hash_mix(net); - d = (u64)zoneid << 32 | net_hash_mix(net); - - /* IPv4: u3.all[1,2,3] == 0 */ - c ^= (u64)tuple->src.u3.all[1] << 32 | tuple->src.u3.all[2]; - d += (u64)tuple->dst.u3.all[1] << 32 | tuple->dst.u3.all[2]; - - return (u32)siphash_4u64(a, b, c, d, &nf_conntrack_hash_rnd); + return siphash((void *)tuple, + offsetofend(struct nf_conntrack_tuple, dst.__nfct_hash_offsetend), + &key); } static u32 scale_hash(u32 hash) diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 0c4db2f2ac43..f22691f83853 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -360,6 +360,9 @@ int nf_conntrack_helper_register(struct nf_conntrack_helper *me) BUG_ON(me->expect_class_max >= NF_CT_MAX_EXPECT_CLASSES); BUG_ON(strlen(me->name) > NF_CT_HELPER_NAME_LEN - 1); + if (!nf_ct_helper_hash) + return -ENOENT; + if (me->expect_policy->max_expected > NF_CT_EXPECT_MAX_CNT) return -EINVAL; @@ -515,4 +518,5 @@ int nf_conntrack_helper_init(void) void nf_conntrack_helper_fini(void) { kvfree(nf_ct_helper_hash); + nf_ct_helper_hash = NULL; } diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index ad6f0ca40cd2..af369e686fc5 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -205,6 +205,8 @@ int nf_conntrack_gre_packet(struct nf_conn *ct, enum ip_conntrack_info ctinfo, const struct nf_hook_state *state) { + unsigned long status; + if (!nf_ct_is_confirmed(ct)) { unsigned int *timeouts = nf_ct_timeout_lookup(ct); @@ -217,11 +219,17 @@ int nf_conntrack_gre_packet(struct nf_conn *ct, ct->proto.gre.timeout = timeouts[GRE_CT_UNREPLIED]; } + status = READ_ONCE(ct->status); /* If we've seen traffic both ways, this is a GRE connection. * Extend timeout. */ - if (ct->status & IPS_SEEN_REPLY) { + if (status & IPS_SEEN_REPLY) { nf_ct_refresh_acct(ct, ctinfo, skb, ct->proto.gre.stream_timeout); + + /* never set ASSURED for IPS_NAT_CLASH, they time out soon */ + if (unlikely((status & IPS_NAT_CLASH))) + return NF_ACCEPT; + /* Also, more likely to be important, and not a probe. */ if (!test_and_set_bit(IPS_ASSURED_BIT, &ct->status)) nf_conntrack_event_cache(IPCT_ASSURED, ct); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 9573a8fcad79..237f739da3ca 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -253,8 +253,10 @@ int nf_tables_bind_chain(const struct nft_ctx *ctx, struct nft_chain *chain) if (chain->bound) return -EBUSY; + if (!nft_use_inc(&chain->use)) + return -EMFILE; + chain->bound = true; - chain->use++; nft_chain_trans_bind(ctx, chain); return 0; @@ -437,7 +439,7 @@ static int nft_delchain(struct nft_ctx *ctx) if (IS_ERR(trans)) return PTR_ERR(trans); - ctx->table->use--; + nft_use_dec(&ctx->table->use); nft_deactivate_next(ctx->net, ctx->chain); return 0; @@ -476,7 +478,7 @@ nf_tables_delrule_deactivate(struct nft_ctx *ctx, struct nft_rule *rule) /* You cannot delete the same rule twice */ if (nft_is_active_next(ctx->net, rule)) { nft_deactivate_next(ctx->net, rule); - ctx->chain->use--; + nft_use_dec(&ctx->chain->use); return 0; } return -ENOENT; @@ -644,7 +646,7 @@ static int nft_delset(const struct nft_ctx *ctx, struct nft_set *set) nft_map_deactivate(ctx, set); nft_deactivate_next(ctx->net, set); - ctx->table->use--; + nft_use_dec(&ctx->table->use); return err; } @@ -676,7 +678,7 @@ static int nft_delobj(struct nft_ctx *ctx, struct nft_object *obj) return err; nft_deactivate_next(ctx->net, obj); - ctx->table->use--; + nft_use_dec(&ctx->table->use); return err; } @@ -711,7 +713,7 @@ static int nft_delflowtable(struct nft_ctx *ctx, return err; nft_deactivate_next(ctx->net, flowtable); - ctx->table->use--; + nft_use_dec(&ctx->table->use); return err; } @@ -2396,9 +2398,6 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, struct nft_chain *chain; int err; - if (table->use == UINT_MAX) - return -EOVERFLOW; - if (nla[NFTA_CHAIN_HOOK]) { struct nft_stats __percpu *stats = NULL; struct nft_chain_hook hook = {}; @@ -2494,6 +2493,11 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, if (err < 0) goto err_destroy_chain; + if (!nft_use_inc(&table->use)) { + err = -EMFILE; + goto err_use; + } + trans = nft_trans_chain_add(ctx, NFT_MSG_NEWCHAIN); if (IS_ERR(trans)) { err = PTR_ERR(trans); @@ -2510,10 +2514,11 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, goto err_unregister_hook; } - table->use++; - return 0; + err_unregister_hook: + nft_use_dec_restore(&table->use); +err_use: nf_tables_unregister_hook(net, table, chain); err_destroy_chain: nf_tables_chain_destroy(ctx); @@ -2694,7 +2699,7 @@ err_hooks: static struct nft_chain *nft_chain_lookup_byid(const struct net *net, const struct nft_table *table, - const struct nlattr *nla) + const struct nlattr *nla, u8 genmask) { struct nftables_pernet *nft_net = nft_pernet(net); u32 id = ntohl(nla_get_be32(nla)); @@ -2705,7 +2710,8 @@ static struct nft_chain *nft_chain_lookup_byid(const struct net *net, if (trans->msg_type == NFT_MSG_NEWCHAIN && chain->table == table && - id == nft_trans_chain_id(trans)) + id == nft_trans_chain_id(trans) && + nft_active_genmask(chain, genmask)) return chain; } return ERR_PTR(-ENOENT); @@ -3809,7 +3815,8 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, return -EOPNOTSUPP; } else if (nla[NFTA_RULE_CHAIN_ID]) { - chain = nft_chain_lookup_byid(net, table, nla[NFTA_RULE_CHAIN_ID]); + chain = nft_chain_lookup_byid(net, table, nla[NFTA_RULE_CHAIN_ID], + genmask); if (IS_ERR(chain)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN_ID]); return PTR_ERR(chain); @@ -3840,9 +3847,6 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, return -EINVAL; handle = nf_tables_alloc_handle(table); - if (chain->use == UINT_MAX) - return -EOVERFLOW; - if (nla[NFTA_RULE_POSITION]) { pos_handle = be64_to_cpu(nla_get_be64(nla[NFTA_RULE_POSITION])); old_rule = __nft_rule_lookup(chain, pos_handle); @@ -3936,6 +3940,11 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, } } + if (!nft_use_inc(&chain->use)) { + err = -EMFILE; + goto err_release_rule; + } + if (info->nlh->nlmsg_flags & NLM_F_REPLACE) { err = nft_delrule(&ctx, old_rule); if (err < 0) @@ -3967,7 +3976,6 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, } } kvfree(expr_info); - chain->use++; if (flow) nft_trans_flow_rule(trans) = flow; @@ -3978,6 +3986,7 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, return 0; err_destroy_flow_rule: + nft_use_dec_restore(&chain->use); if (flow) nft_flow_rule_destroy(flow); err_release_rule: @@ -5014,9 +5023,15 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, alloc_size = sizeof(*set) + size + udlen; if (alloc_size < size || alloc_size > INT_MAX) return -ENOMEM; + + if (!nft_use_inc(&table->use)) + return -EMFILE; + set = kvzalloc(alloc_size, GFP_KERNEL_ACCOUNT); - if (!set) - return -ENOMEM; + if (!set) { + err = -ENOMEM; + goto err_alloc; + } name = nla_strdup(nla[NFTA_SET_NAME], GFP_KERNEL_ACCOUNT); if (!name) { @@ -5074,7 +5089,7 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, goto err_set_expr_alloc; list_add_tail_rcu(&set->list, &table->sets); - table->use++; + return 0; err_set_expr_alloc: @@ -5086,6 +5101,9 @@ err_set_init: kfree(set->name); err_set_name: kvfree(set); +err_alloc: + nft_use_dec_restore(&table->use); + return err; } @@ -5224,9 +5242,6 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_binding *i; struct nft_set_iter iter; - if (set->use == UINT_MAX) - return -EOVERFLOW; - if (!list_empty(&set->bindings) && nft_set_is_anonymous(set)) return -EBUSY; @@ -5254,10 +5269,12 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, return iter.err; } bind: + if (!nft_use_inc(&set->use)) + return -EMFILE; + binding->chain = ctx->chain; list_add_tail_rcu(&binding->list, &set->bindings); nft_set_trans_bind(ctx, set); - set->use++; return 0; } @@ -5331,7 +5348,7 @@ void nf_tables_activate_set(const struct nft_ctx *ctx, struct nft_set *set) nft_clear(ctx->net, set); } - set->use++; + nft_use_inc_restore(&set->use); } EXPORT_SYMBOL_GPL(nf_tables_activate_set); @@ -5347,7 +5364,7 @@ void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set, else list_del_rcu(&binding->list); - set->use--; + nft_use_dec(&set->use); break; case NFT_TRANS_PREPARE: if (nft_set_is_anonymous(set)) { @@ -5356,7 +5373,7 @@ void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set, nft_deactivate_next(ctx->net, set); } - set->use--; + nft_use_dec(&set->use); return; case NFT_TRANS_ABORT: case NFT_TRANS_RELEASE: @@ -5364,7 +5381,7 @@ void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set, set->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) nft_map_deactivate(ctx, set); - set->use--; + nft_use_dec(&set->use); fallthrough; default: nf_tables_unbind_set(ctx, set, binding, @@ -6155,7 +6172,7 @@ void nft_set_elem_destroy(const struct nft_set *set, void *elem, nft_set_elem_expr_destroy(&ctx, nft_set_ext_expr(ext)); if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF)) - (*nft_set_ext_obj(ext))->use--; + nft_use_dec(&(*nft_set_ext_obj(ext))->use); kfree(elem); } EXPORT_SYMBOL_GPL(nft_set_elem_destroy); @@ -6657,8 +6674,16 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, set->objtype, genmask); if (IS_ERR(obj)) { err = PTR_ERR(obj); + obj = NULL; + goto err_parse_key_end; + } + + if (!nft_use_inc(&obj->use)) { + err = -EMFILE; + obj = NULL; goto err_parse_key_end; } + err = nft_set_ext_add(&tmpl, NFT_SET_EXT_OBJREF); if (err < 0) goto err_parse_key_end; @@ -6727,10 +6752,9 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (flags) *nft_set_ext_flags(ext) = flags; - if (obj) { + if (obj) *nft_set_ext_obj(ext) = obj; - obj->use++; - } + if (ulen > 0) { if (nft_set_ext_check(&tmpl, NFT_SET_EXT_USERDATA, ulen) < 0) { err = -EINVAL; @@ -6798,12 +6822,13 @@ err_element_clash: kfree(trans); err_elem_free: nf_tables_set_elem_destroy(ctx, set, elem.priv); - if (obj) - obj->use--; err_parse_data: if (nla[NFTA_SET_ELEM_DATA] != NULL) nft_data_release(&elem.data.val, desc.type); err_parse_key_end: + if (obj) + nft_use_dec_restore(&obj->use); + nft_data_release(&elem.key_end.val, NFT_DATA_VALUE); err_parse_key: nft_data_release(&elem.key.val, NFT_DATA_VALUE); @@ -6883,7 +6908,7 @@ void nft_data_hold(const struct nft_data *data, enum nft_data_types type) case NFT_JUMP: case NFT_GOTO: chain = data->verdict.chain; - chain->use++; + nft_use_inc_restore(&chain->use); break; } } @@ -6898,7 +6923,7 @@ static void nft_setelem_data_activate(const struct net *net, if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA)) nft_data_hold(nft_set_ext_data(ext), set->dtype); if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF)) - (*nft_set_ext_obj(ext))->use++; + nft_use_inc_restore(&(*nft_set_ext_obj(ext))->use); } static void nft_setelem_data_deactivate(const struct net *net, @@ -6910,7 +6935,7 @@ static void nft_setelem_data_deactivate(const struct net *net, if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA)) nft_data_release(nft_set_ext_data(ext), set->dtype); if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF)) - (*nft_set_ext_obj(ext))->use--; + nft_use_dec(&(*nft_set_ext_obj(ext))->use); } static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, @@ -7453,9 +7478,14 @@ static int nf_tables_newobj(struct sk_buff *skb, const struct nfnl_info *info, nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); + if (!nft_use_inc(&table->use)) + return -EMFILE; + type = nft_obj_type_get(net, objtype); - if (IS_ERR(type)) - return PTR_ERR(type); + if (IS_ERR(type)) { + err = PTR_ERR(type); + goto err_type; + } obj = nft_obj_init(&ctx, type, nla[NFTA_OBJ_DATA]); if (IS_ERR(obj)) { @@ -7489,7 +7519,7 @@ static int nf_tables_newobj(struct sk_buff *skb, const struct nfnl_info *info, goto err_obj_ht; list_add_tail_rcu(&obj->list, &table->objects); - table->use++; + return 0; err_obj_ht: /* queued in transaction log */ @@ -7505,6 +7535,9 @@ err_strdup: kfree(obj); err_init: module_put(type->owner); +err_type: + nft_use_dec_restore(&table->use); + return err; } @@ -7906,7 +7939,7 @@ void nf_tables_deactivate_flowtable(const struct nft_ctx *ctx, case NFT_TRANS_PREPARE: case NFT_TRANS_ABORT: case NFT_TRANS_RELEASE: - flowtable->use--; + nft_use_dec(&flowtable->use); fallthrough; default: return; @@ -8260,9 +8293,14 @@ static int nf_tables_newflowtable(struct sk_buff *skb, nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); + if (!nft_use_inc(&table->use)) + return -EMFILE; + flowtable = kzalloc(sizeof(*flowtable), GFP_KERNEL_ACCOUNT); - if (!flowtable) - return -ENOMEM; + if (!flowtable) { + err = -ENOMEM; + goto flowtable_alloc; + } flowtable->table = table; flowtable->handle = nf_tables_alloc_handle(table); @@ -8317,7 +8355,6 @@ static int nf_tables_newflowtable(struct sk_buff *skb, goto err5; list_add_tail_rcu(&flowtable->list, &table->flowtables); - table->use++; return 0; err5: @@ -8334,6 +8371,9 @@ err2: kfree(flowtable->name); err1: kfree(flowtable); +flowtable_alloc: + nft_use_dec_restore(&table->use); + return err; } @@ -9713,7 +9753,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) */ if (nft_set_is_anonymous(nft_trans_set(trans)) && !list_empty(&nft_trans_set(trans)->bindings)) - trans->ctx.table->use--; + nft_use_dec(&trans->ctx.table->use); } nf_tables_set_notify(&trans->ctx, nft_trans_set(trans), NFT_MSG_NEWSET, GFP_KERNEL); @@ -9943,7 +9983,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_trans_destroy(trans); break; } - trans->ctx.table->use--; + nft_use_dec_restore(&trans->ctx.table->use); nft_chain_del(trans->ctx.chain); nf_tables_unregister_hook(trans->ctx.net, trans->ctx.table, @@ -9956,7 +9996,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) list_splice(&nft_trans_chain_hooks(trans), &nft_trans_basechain(trans)->hook_list); } else { - trans->ctx.table->use++; + nft_use_inc_restore(&trans->ctx.table->use); nft_clear(trans->ctx.net, trans->ctx.chain); } nft_trans_destroy(trans); @@ -9966,7 +10006,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_trans_destroy(trans); break; } - trans->ctx.chain->use--; + nft_use_dec_restore(&trans->ctx.chain->use); list_del_rcu(&nft_trans_rule(trans)->list); nft_rule_expr_deactivate(&trans->ctx, nft_trans_rule(trans), @@ -9976,7 +10016,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) break; case NFT_MSG_DELRULE: case NFT_MSG_DESTROYRULE: - trans->ctx.chain->use++; + nft_use_inc_restore(&trans->ctx.chain->use); nft_clear(trans->ctx.net, nft_trans_rule(trans)); nft_rule_expr_activate(&trans->ctx, nft_trans_rule(trans)); if (trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD) @@ -9989,7 +10029,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_trans_destroy(trans); break; } - trans->ctx.table->use--; + nft_use_dec_restore(&trans->ctx.table->use); if (nft_trans_set_bound(trans)) { nft_trans_destroy(trans); break; @@ -9998,7 +10038,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) break; case NFT_MSG_DELSET: case NFT_MSG_DESTROYSET: - trans->ctx.table->use++; + nft_use_inc_restore(&trans->ctx.table->use); nft_clear(trans->ctx.net, nft_trans_set(trans)); if (nft_trans_set(trans)->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) nft_map_activate(&trans->ctx, nft_trans_set(trans)); @@ -10042,13 +10082,13 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_obj_destroy(&trans->ctx, nft_trans_obj_newobj(trans)); nft_trans_destroy(trans); } else { - trans->ctx.table->use--; + nft_use_dec_restore(&trans->ctx.table->use); nft_obj_del(nft_trans_obj(trans)); } break; case NFT_MSG_DELOBJ: case NFT_MSG_DESTROYOBJ: - trans->ctx.table->use++; + nft_use_inc_restore(&trans->ctx.table->use); nft_clear(trans->ctx.net, nft_trans_obj(trans)); nft_trans_destroy(trans); break; @@ -10057,7 +10097,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_unregister_flowtable_net_hooks(net, &nft_trans_flowtable_hooks(trans)); } else { - trans->ctx.table->use--; + nft_use_dec_restore(&trans->ctx.table->use); list_del_rcu(&nft_trans_flowtable(trans)->list); nft_unregister_flowtable_net_hooks(net, &nft_trans_flowtable(trans)->hook_list); @@ -10069,7 +10109,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) list_splice(&nft_trans_flowtable_hooks(trans), &nft_trans_flowtable(trans)->hook_list); } else { - trans->ctx.table->use++; + nft_use_inc_restore(&trans->ctx.table->use); nft_clear(trans->ctx.net, nft_trans_flowtable(trans)); } nft_trans_destroy(trans); @@ -10502,7 +10542,8 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, genmask); } else if (tb[NFTA_VERDICT_CHAIN_ID]) { chain = nft_chain_lookup_byid(ctx->net, ctx->table, - tb[NFTA_VERDICT_CHAIN_ID]); + tb[NFTA_VERDICT_CHAIN_ID], + genmask); if (IS_ERR(chain)) return PTR_ERR(chain); } else { @@ -10518,8 +10559,9 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, if (desc->flags & NFT_DATA_DESC_SETELEM && chain->flags & NFT_CHAIN_BINDING) return -EINVAL; + if (!nft_use_inc(&chain->use)) + return -EMFILE; - chain->use++; data->verdict.chain = chain; break; } @@ -10537,7 +10579,7 @@ static void nft_verdict_uninit(const struct nft_data *data) case NFT_JUMP: case NFT_GOTO: chain = data->verdict.chain; - chain->use--; + nft_use_dec(&chain->use); break; } } @@ -10706,11 +10748,11 @@ int __nft_release_basechain(struct nft_ctx *ctx) nf_tables_unregister_hook(ctx->net, ctx->chain->table, ctx->chain); list_for_each_entry_safe(rule, nr, &ctx->chain->rules, list) { list_del(&rule->list); - ctx->chain->use--; + nft_use_dec(&ctx->chain->use); nf_tables_rule_release(ctx, rule); } nft_chain_del(ctx->chain); - ctx->table->use--; + nft_use_dec(&ctx->table->use); nf_tables_chain_destroy(ctx); return 0; @@ -10760,18 +10802,18 @@ static void __nft_release_table(struct net *net, struct nft_table *table) ctx.chain = chain; list_for_each_entry_safe(rule, nr, &chain->rules, list) { list_del(&rule->list); - chain->use--; + nft_use_dec(&chain->use); nf_tables_rule_release(&ctx, rule); } } list_for_each_entry_safe(flowtable, nf, &table->flowtables, list) { list_del(&flowtable->list); - table->use--; + nft_use_dec(&table->use); nf_tables_flowtable_destroy(flowtable); } list_for_each_entry_safe(set, ns, &table->sets, list) { list_del(&set->list); - table->use--; + nft_use_dec(&table->use); if (set->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) nft_map_deactivate(&ctx, set); @@ -10779,13 +10821,13 @@ static void __nft_release_table(struct net *net, struct nft_table *table) } list_for_each_entry_safe(obj, ne, &table->objects, list) { nft_obj_del(obj); - table->use--; + nft_use_dec(&table->use); nft_obj_destroy(&ctx, obj); } list_for_each_entry_safe(chain, nc, &table->chains, list) { ctx.chain = chain; nft_chain_del(chain); - table->use--; + nft_use_dec(&table->use); nf_tables_chain_destroy(&ctx); } nf_tables_table_destroy(&ctx); diff --git a/net/netfilter/nft_byteorder.c b/net/netfilter/nft_byteorder.c index 9a85e797ed58..e596d1a842f7 100644 --- a/net/netfilter/nft_byteorder.c +++ b/net/netfilter/nft_byteorder.c @@ -30,11 +30,11 @@ void nft_byteorder_eval(const struct nft_expr *expr, const struct nft_byteorder *priv = nft_expr_priv(expr); u32 *src = ®s->data[priv->sreg]; u32 *dst = ®s->data[priv->dreg]; - union { u32 u32; u16 u16; } *s, *d; + u16 *s16, *d16; unsigned int i; - s = (void *)src; - d = (void *)dst; + s16 = (void *)src; + d16 = (void *)dst; switch (priv->size) { case 8: { @@ -62,11 +62,11 @@ void nft_byteorder_eval(const struct nft_expr *expr, switch (priv->op) { case NFT_BYTEORDER_NTOH: for (i = 0; i < priv->len / 4; i++) - d[i].u32 = ntohl((__force __be32)s[i].u32); + dst[i] = ntohl((__force __be32)src[i]); break; case NFT_BYTEORDER_HTON: for (i = 0; i < priv->len / 4; i++) - d[i].u32 = (__force __u32)htonl(s[i].u32); + dst[i] = (__force __u32)htonl(src[i]); break; } break; @@ -74,11 +74,11 @@ void nft_byteorder_eval(const struct nft_expr *expr, switch (priv->op) { case NFT_BYTEORDER_NTOH: for (i = 0; i < priv->len / 2; i++) - d[i].u16 = ntohs((__force __be16)s[i].u16); + d16[i] = ntohs((__force __be16)s16[i]); break; case NFT_BYTEORDER_HTON: for (i = 0; i < priv->len / 2; i++) - d[i].u16 = (__force __u16)htons(s[i].u16); + d16[i] = (__force __u16)htons(s16[i]); break; } break; diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index 5ef9146e74ad..ab3362c483b4 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -408,8 +408,10 @@ static int nft_flow_offload_init(const struct nft_ctx *ctx, if (IS_ERR(flowtable)) return PTR_ERR(flowtable); + if (!nft_use_inc(&flowtable->use)) + return -EMFILE; + priv->flowtable = flowtable; - flowtable->use++; return nf_ct_netns_get(ctx->net, ctx->family); } @@ -428,7 +430,7 @@ static void nft_flow_offload_activate(const struct nft_ctx *ctx, { struct nft_flow_offload *priv = nft_expr_priv(expr); - priv->flowtable->use++; + nft_use_inc_restore(&priv->flowtable->use); } static void nft_flow_offload_destroy(const struct nft_ctx *ctx, diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c index 3d76ebfe8939..407d7197f75b 100644 --- a/net/netfilter/nft_immediate.c +++ b/net/netfilter/nft_immediate.c @@ -159,7 +159,7 @@ static void nft_immediate_deactivate(const struct nft_ctx *ctx, default: nft_chain_del(chain); chain->bound = false; - chain->table->use--; + nft_use_dec(&chain->table->use); break; } break; @@ -198,7 +198,7 @@ static void nft_immediate_destroy(const struct nft_ctx *ctx, * let the transaction records release this chain and its rules. */ if (chain->bound) { - chain->use--; + nft_use_dec(&chain->use); break; } @@ -206,9 +206,9 @@ static void nft_immediate_destroy(const struct nft_ctx *ctx, chain_ctx = *ctx; chain_ctx.chain = chain; - chain->use--; + nft_use_dec(&chain->use); list_for_each_entry_safe(rule, n, &chain->rules, list) { - chain->use--; + nft_use_dec(&chain->use); list_del(&rule->list); nf_tables_rule_destroy(&chain_ctx, rule); } diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c index a48dd5b5d45b..509011b1ef59 100644 --- a/net/netfilter/nft_objref.c +++ b/net/netfilter/nft_objref.c @@ -41,8 +41,10 @@ static int nft_objref_init(const struct nft_ctx *ctx, if (IS_ERR(obj)) return -ENOENT; + if (!nft_use_inc(&obj->use)) + return -EMFILE; + nft_objref_priv(expr) = obj; - obj->use++; return 0; } @@ -72,7 +74,7 @@ static void nft_objref_deactivate(const struct nft_ctx *ctx, if (phase == NFT_TRANS_COMMIT) return; - obj->use--; + nft_use_dec(&obj->use); } static void nft_objref_activate(const struct nft_ctx *ctx, @@ -80,7 +82,7 @@ static void nft_objref_activate(const struct nft_ctx *ctx, { struct nft_object *obj = nft_objref_priv(expr); - obj->use++; + nft_use_inc_restore(&obj->use); } static const struct nft_expr_ops nft_objref_ops = { diff --git a/net/sched/act_api.c b/net/sched/act_api.c index f7887f42d542..9d3f26bf0440 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -1320,7 +1320,7 @@ struct tc_action_ops *tc_action_load_ops(struct nlattr *nla, bool police, return ERR_PTR(err); } } else { - if (strlcpy(act_name, "police", IFNAMSIZ) >= IFNAMSIZ) { + if (strscpy(act_name, "police", IFNAMSIZ) < 0) { NL_SET_ERR_MSG(extack, "TC action name too long"); return ERR_PTR(-EINVAL); } diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 56065cc5a661..f2b0bc4142fe 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -812,6 +812,16 @@ static int fl_set_key_port_range(struct nlattr **tb, struct fl_flow_key *key, TCA_FLOWER_KEY_PORT_SRC_MAX, &mask->tp_range.tp_max.src, TCA_FLOWER_UNSPEC, sizeof(key->tp_range.tp_max.src)); + if (mask->tp_range.tp_min.dst != mask->tp_range.tp_max.dst) { + NL_SET_ERR_MSG(extack, + "Both min and max destination ports must be specified"); + return -EINVAL; + } + if (mask->tp_range.tp_min.src != mask->tp_range.tp_max.src) { + NL_SET_ERR_MSG(extack, + "Both min and max source ports must be specified"); + return -EINVAL; + } if (mask->tp_range.tp_min.dst && mask->tp_range.tp_max.dst && ntohs(key->tp_range.tp_max.dst) <= ntohs(key->tp_range.tp_min.dst)) { diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index ae9439a6c56c..8641f8059317 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -212,11 +212,6 @@ static int fw_set_parms(struct net *net, struct tcf_proto *tp, if (err < 0) return err; - if (tb[TCA_FW_CLASSID]) { - f->res.classid = nla_get_u32(tb[TCA_FW_CLASSID]); - tcf_bind_filter(tp, &f->res, base); - } - if (tb[TCA_FW_INDEV]) { int ret; ret = tcf_change_indev(net, tb[TCA_FW_INDEV], extack); @@ -233,6 +228,11 @@ static int fw_set_parms(struct net *net, struct tcf_proto *tp, } else if (head->mask != 0xFFFFFFFF) return err; + if (tb[TCA_FW_CLASSID]) { + f->res.classid = nla_get_u32(tb[TCA_FW_CLASSID]); + tcf_bind_filter(tp, &f->res, base); + } + return 0; } diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index dfd9a99e6257..befaf74b33ca 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -381,8 +381,13 @@ static int qfq_change_agg(struct Qdisc *sch, struct qfq_class *cl, u32 weight, u32 lmax) { struct qfq_sched *q = qdisc_priv(sch); - struct qfq_aggregate *new_agg = qfq_find_agg(q, lmax, weight); + struct qfq_aggregate *new_agg; + /* 'lmax' can range from [QFQ_MIN_LMAX, pktlen + stab overhead] */ + if (lmax > QFQ_MAX_LMAX) + return -EINVAL; + + new_agg = qfq_find_agg(q, lmax, weight); if (new_agg == NULL) { /* create new aggregate */ new_agg = kzalloc(sizeof(*new_agg), GFP_ATOMIC); if (new_agg == NULL) @@ -423,10 +428,17 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, else weight = 1; - if (tb[TCA_QFQ_LMAX]) + if (tb[TCA_QFQ_LMAX]) { lmax = nla_get_u32(tb[TCA_QFQ_LMAX]); - else + } else { + /* MTU size is user controlled */ lmax = psched_mtu(qdisc_dev(sch)); + if (lmax < QFQ_MIN_LMAX || lmax > QFQ_MAX_LMAX) { + NL_SET_ERR_MSG_MOD(extack, + "MTU size out of bounds for qfq"); + return -EINVAL; + } + } inv_w = ONE_FP / weight; weight = ONE_FP / inv_w; diff --git a/net/wireless/util.c b/net/wireless/util.c index 89c9ad6c886e..1783ab9d57a3 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -580,6 +580,8 @@ int ieee80211_strip_8023_mesh_hdr(struct sk_buff *skb) hdrlen += ETH_ALEN + 2; else if (!pskb_may_pull(skb, hdrlen)) return -EINVAL; + else + payload.eth.h_proto = htons(skb->len - hdrlen); mesh_addr = skb->data + sizeof(payload.eth) + ETH_ALEN; switch (payload.flags & MESH_FLAGS_AE) { diff --git a/tools/testing/selftests/bpf/prog_tests/async_stack_depth.c b/tools/testing/selftests/bpf/prog_tests/async_stack_depth.c new file mode 100644 index 000000000000..118abc29b236 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/async_stack_depth.c @@ -0,0 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> + +#include "async_stack_depth.skel.h" + +void test_async_stack_depth(void) +{ + RUN_TESTS(async_stack_depth); +} diff --git a/tools/testing/selftests/bpf/progs/async_stack_depth.c b/tools/testing/selftests/bpf/progs/async_stack_depth.c new file mode 100644 index 000000000000..477ba950bb43 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/async_stack_depth.c @@ -0,0 +1,40 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> + +#include "bpf_misc.h" + +struct hmap_elem { + struct bpf_timer timer; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 64); + __type(key, int); + __type(value, struct hmap_elem); +} hmap SEC(".maps"); + +__attribute__((noinline)) +static int timer_cb(void *map, int *key, struct bpf_timer *timer) +{ + volatile char buf[256] = {}; + return buf[69]; +} + +SEC("tc") +__failure __msg("combined stack size of 2 calls") +int prog(struct __sk_buff *ctx) +{ + struct hmap_elem *elem; + volatile char buf[256] = {}; + + elem = bpf_map_lookup_elem(&hmap, &(int){0}); + if (!elem) + return 0; + + timer_cb(NULL, NULL, NULL); + return bpf_timer_set_callback(&elem->timer, timer_cb) + buf[0]; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/qfq.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/qfq.json index 147899a868d3..976dffda4654 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/qfq.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/qfq.json @@ -213,5 +213,91 @@ "$TC qdisc del dev $DUMMY handle 1: root", "$IP link del dev $DUMMY type dummy" ] + }, + { + "id": "85ee", + "name": "QFQ with big MTU", + "category": [ + "qdisc", + "qfq" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true", + "$IP link set dev $DUMMY mtu 2147483647 || /bin/true", + "$TC qdisc add dev $DUMMY handle 1: root qfq" + ], + "cmdUnderTest": "$TC class add dev $DUMMY parent 1: classid 1:1 qfq weight 100", + "expExitCode": "2", + "verifyCmd": "$TC class show dev $DUMMY", + "matchPattern": "class qfq 1:", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "ddfa", + "name": "QFQ with small MTU", + "category": [ + "qdisc", + "qfq" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true", + "$IP link set dev $DUMMY mtu 256 || /bin/true", + "$TC qdisc add dev $DUMMY handle 1: root qfq" + ], + "cmdUnderTest": "$TC class add dev $DUMMY parent 1: classid 1:1 qfq weight 100", + "expExitCode": "2", + "verifyCmd": "$TC class show dev $DUMMY", + "matchPattern": "class qfq 1:", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "5993", + "name": "QFQ with stab overhead greater than max packet len", + "category": [ + "qdisc", + "qfq", + "scapy" + ], + "plugins": { + "requires": [ + "nsPlugin", + "scapyPlugin" + ] + }, + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true", + "$IP link set dev $DUMMY up || /bin/true", + "$TC qdisc add dev $DUMMY handle 1: stab mtu 2048 tsize 512 mpu 0 overhead 999999999 linklayer ethernet root qfq", + "$TC class add dev $DUMMY parent 1: classid 1:1 qfq weight 100", + "$TC qdisc add dev $DEV1 clsact", + "$TC filter add dev $DEV1 ingress protocol ip flower dst_ip 1.3.3.7/32 action mirred egress mirror dev $DUMMY" + ], + "cmdUnderTest": "$TC filter add dev $DUMMY parent 1: matchall classid 1:1", + "scapy": [ + { + "iface": "$DEV0", + "count": 22, + "packet": "Ether(type=0x800)/IP(src='10.0.0.10',dst='1.3.3.7')/TCP(sport=5000,dport=10)" + } + ], + "expExitCode": "0", + "verifyCmd": "$TC -s qdisc ls dev $DUMMY", + "matchPattern": "dropped 22", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root qfq" + ] } ] |