diff options
84 files changed, 1152 insertions, 713 deletions
@@ -241,6 +241,7 @@ Jisheng Zhang <jszhang@kernel.org> <Jisheng.Zhang@synaptics.com> Johan Hovold <johan@kernel.org> <jhovold@gmail.com> Johan Hovold <johan@kernel.org> <johan@hovoldconsulting.com> John Crispin <john@phrozen.org> <blogic@openwrt.org> +John Fastabend <john.fastabend@gmail.com> <john.r.fastabend@intel.com> John Keeping <john@keeping.me.uk> <john@metanate.com> John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de> John Stultz <johnstul@us.ibm.com> @@ -454,6 +455,8 @@ Sebastian Reichel <sre@kernel.org> <sre@debian.org> Sedat Dilek <sedat.dilek@gmail.com> <sedat.dilek@credativ.de> Seth Forshee <sforshee@kernel.org> <seth.forshee@canonical.com> Shannon Nelson <shannon.nelson@amd.com> <snelson@pensando.io> +Shannon Nelson <shannon.nelson@amd.com> <shannon.nelson@intel.com> +Shannon Nelson <shannon.nelson@amd.com> <shannon.nelson@oracle.com> Shiraz Hashim <shiraz.linux.kernel@gmail.com> <shiraz.hashim@st.com> Shuah Khan <shuah@kernel.org> <shuahkhan@gmail.com> Shuah Khan <shuah@kernel.org> <shuah.khan@hp.com> diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 145b540ec34f..ec2174838f2a 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -322,7 +322,13 @@ static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf) * */ - emit_bti(A64_BTI_C, ctx); + /* bpf function may be invoked by 3 instruction types: + * 1. bl, attached via freplace to bpf prog via short jump + * 2. br, attached via freplace to bpf prog via long jump + * 3. blr, working as a function pointer, used by emit_call. + * So BTI_JC should used here to support both br and blr. + */ + emit_bti(A64_BTI_JC, ctx); emit(A64_MOV(1, A64_R(9), A64_LR), ctx); emit(A64_NOP, ctx); diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 5ec4ad0a5c86..764d176e9735 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -4104,6 +4104,7 @@ static int btusb_probe(struct usb_interface *intf, BT_DBG("intf %p id %p", intf, id); if ((id->driver_info & BTUSB_IFNUM_2) && + (intf->cur_altsetting->desc.bInterfaceNumber != 0) && (intf->cur_altsetting->desc.bInterfaceNumber != 2)) return -ENODEV; diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c index 68df6d4641b5..eebf967f4711 100644 --- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c +++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c @@ -227,6 +227,8 @@ static int __mcp251xfd_chip_set_mode(const struct mcp251xfd_priv *priv, const u8 mode_req, bool nowait) { + const struct can_bittiming *bt = &priv->can.bittiming; + unsigned long timeout_us = MCP251XFD_POLL_TIMEOUT_US; u32 con = 0, con_reqop, osc = 0; u8 mode; int err; @@ -246,12 +248,16 @@ __mcp251xfd_chip_set_mode(const struct mcp251xfd_priv *priv, if (mode_req == MCP251XFD_REG_CON_MODE_SLEEP || nowait) return 0; + if (bt->bitrate) + timeout_us = max_t(unsigned long, timeout_us, + MCP251XFD_FRAME_LEN_MAX_BITS * USEC_PER_SEC / + bt->bitrate); + err = regmap_read_poll_timeout(priv->map_reg, MCP251XFD_REG_CON, con, !mcp251xfd_reg_invalid(con) && FIELD_GET(MCP251XFD_REG_CON_OPMOD_MASK, con) == mode_req, - MCP251XFD_POLL_SLEEP_US, - MCP251XFD_POLL_TIMEOUT_US); + MCP251XFD_POLL_SLEEP_US, timeout_us); if (err != -ETIMEDOUT && err != -EBADMSG) return err; diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd.h b/drivers/net/can/spi/mcp251xfd/mcp251xfd.h index 7024ff0cc2c0..24510b3b8020 100644 --- a/drivers/net/can/spi/mcp251xfd/mcp251xfd.h +++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd.h @@ -387,6 +387,7 @@ static_assert(MCP251XFD_TIMESTAMP_WORK_DELAY_SEC < #define MCP251XFD_OSC_STAB_TIMEOUT_US (10 * MCP251XFD_OSC_STAB_SLEEP_US) #define MCP251XFD_POLL_SLEEP_US (10) #define MCP251XFD_POLL_TIMEOUT_US (USEC_PER_MSEC) +#define MCP251XFD_FRAME_LEN_MAX_BITS (736) /* Misc */ #define MCP251XFD_NAPI_WEIGHT 32 diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c index d476c2884008..f418066569fc 100644 --- a/drivers/net/can/usb/gs_usb.c +++ b/drivers/net/can/usb/gs_usb.c @@ -303,12 +303,6 @@ struct gs_can { struct can_bittiming_const bt_const, data_bt_const; unsigned int channel; /* channel number */ - /* time counter for hardware timestamps */ - struct cyclecounter cc; - struct timecounter tc; - spinlock_t tc_lock; /* spinlock to guard access tc->cycle_last */ - struct delayed_work timestamp; - u32 feature; unsigned int hf_size_tx; @@ -325,6 +319,13 @@ struct gs_usb { struct gs_can *canch[GS_MAX_INTF]; struct usb_anchor rx_submitted; struct usb_device *udev; + + /* time counter for hardware timestamps */ + struct cyclecounter cc; + struct timecounter tc; + spinlock_t tc_lock; /* spinlock to guard access tc->cycle_last */ + struct delayed_work timestamp; + unsigned int hf_size_rx; u8 active_channels; }; @@ -388,15 +389,15 @@ static int gs_cmd_reset(struct gs_can *dev) GFP_KERNEL); } -static inline int gs_usb_get_timestamp(const struct gs_can *dev, +static inline int gs_usb_get_timestamp(const struct gs_usb *parent, u32 *timestamp_p) { __le32 timestamp; int rc; - rc = usb_control_msg_recv(dev->udev, 0, GS_USB_BREQ_TIMESTAMP, + rc = usb_control_msg_recv(parent->udev, 0, GS_USB_BREQ_TIMESTAMP, USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_INTERFACE, - dev->channel, 0, + 0, 0, ×tamp, sizeof(timestamp), USB_CTRL_GET_TIMEOUT, GFP_KERNEL); @@ -410,20 +411,20 @@ static inline int gs_usb_get_timestamp(const struct gs_can *dev, static u64 gs_usb_timestamp_read(const struct cyclecounter *cc) __must_hold(&dev->tc_lock) { - struct gs_can *dev = container_of(cc, struct gs_can, cc); + struct gs_usb *parent = container_of(cc, struct gs_usb, cc); u32 timestamp = 0; int err; - lockdep_assert_held(&dev->tc_lock); + lockdep_assert_held(&parent->tc_lock); /* drop lock for synchronous USB transfer */ - spin_unlock_bh(&dev->tc_lock); - err = gs_usb_get_timestamp(dev, ×tamp); - spin_lock_bh(&dev->tc_lock); + spin_unlock_bh(&parent->tc_lock); + err = gs_usb_get_timestamp(parent, ×tamp); + spin_lock_bh(&parent->tc_lock); if (err) - netdev_err(dev->netdev, - "Error %d while reading timestamp. HW timestamps may be inaccurate.", - err); + dev_err(&parent->udev->dev, + "Error %d while reading timestamp. HW timestamps may be inaccurate.", + err); return timestamp; } @@ -431,14 +432,14 @@ static u64 gs_usb_timestamp_read(const struct cyclecounter *cc) __must_hold(&dev static void gs_usb_timestamp_work(struct work_struct *work) { struct delayed_work *delayed_work = to_delayed_work(work); - struct gs_can *dev; + struct gs_usb *parent; - dev = container_of(delayed_work, struct gs_can, timestamp); - spin_lock_bh(&dev->tc_lock); - timecounter_read(&dev->tc); - spin_unlock_bh(&dev->tc_lock); + parent = container_of(delayed_work, struct gs_usb, timestamp); + spin_lock_bh(&parent->tc_lock); + timecounter_read(&parent->tc); + spin_unlock_bh(&parent->tc_lock); - schedule_delayed_work(&dev->timestamp, + schedule_delayed_work(&parent->timestamp, GS_USB_TIMESTAMP_WORK_DELAY_SEC * HZ); } @@ -446,37 +447,38 @@ static void gs_usb_skb_set_timestamp(struct gs_can *dev, struct sk_buff *skb, u32 timestamp) { struct skb_shared_hwtstamps *hwtstamps = skb_hwtstamps(skb); + struct gs_usb *parent = dev->parent; u64 ns; - spin_lock_bh(&dev->tc_lock); - ns = timecounter_cyc2time(&dev->tc, timestamp); - spin_unlock_bh(&dev->tc_lock); + spin_lock_bh(&parent->tc_lock); + ns = timecounter_cyc2time(&parent->tc, timestamp); + spin_unlock_bh(&parent->tc_lock); hwtstamps->hwtstamp = ns_to_ktime(ns); } -static void gs_usb_timestamp_init(struct gs_can *dev) +static void gs_usb_timestamp_init(struct gs_usb *parent) { - struct cyclecounter *cc = &dev->cc; + struct cyclecounter *cc = &parent->cc; cc->read = gs_usb_timestamp_read; cc->mask = CYCLECOUNTER_MASK(32); cc->shift = 32 - bits_per(NSEC_PER_SEC / GS_USB_TIMESTAMP_TIMER_HZ); cc->mult = clocksource_hz2mult(GS_USB_TIMESTAMP_TIMER_HZ, cc->shift); - spin_lock_init(&dev->tc_lock); - spin_lock_bh(&dev->tc_lock); - timecounter_init(&dev->tc, &dev->cc, ktime_get_real_ns()); - spin_unlock_bh(&dev->tc_lock); + spin_lock_init(&parent->tc_lock); + spin_lock_bh(&parent->tc_lock); + timecounter_init(&parent->tc, &parent->cc, ktime_get_real_ns()); + spin_unlock_bh(&parent->tc_lock); - INIT_DELAYED_WORK(&dev->timestamp, gs_usb_timestamp_work); - schedule_delayed_work(&dev->timestamp, + INIT_DELAYED_WORK(&parent->timestamp, gs_usb_timestamp_work); + schedule_delayed_work(&parent->timestamp, GS_USB_TIMESTAMP_WORK_DELAY_SEC * HZ); } -static void gs_usb_timestamp_stop(struct gs_can *dev) +static void gs_usb_timestamp_stop(struct gs_usb *parent) { - cancel_delayed_work_sync(&dev->timestamp); + cancel_delayed_work_sync(&parent->timestamp); } static void gs_update_state(struct gs_can *dev, struct can_frame *cf) @@ -560,6 +562,9 @@ static void gs_usb_receive_bulk_callback(struct urb *urb) if (!netif_device_present(netdev)) return; + if (!netif_running(netdev)) + goto resubmit_urb; + if (hf->echo_id == -1) { /* normal rx */ if (hf->flags & GS_CAN_FLAG_FD) { skb = alloc_canfd_skb(dev->netdev, &cfd); @@ -833,6 +838,7 @@ static int gs_can_open(struct net_device *netdev) .mode = cpu_to_le32(GS_CAN_MODE_START), }; struct gs_host_frame *hf; + struct urb *urb = NULL; u32 ctrlmode; u32 flags = 0; int rc, i; @@ -855,14 +861,18 @@ static int gs_can_open(struct net_device *netdev) } if (!parent->active_channels) { + if (dev->feature & GS_CAN_FEATURE_HW_TIMESTAMP) + gs_usb_timestamp_init(parent); + for (i = 0; i < GS_MAX_RX_URBS; i++) { - struct urb *urb; u8 *buf; /* alloc rx urb */ urb = usb_alloc_urb(0, GFP_KERNEL); - if (!urb) - return -ENOMEM; + if (!urb) { + rc = -ENOMEM; + goto out_usb_kill_anchored_urbs; + } /* alloc rx buffer */ buf = kmalloc(dev->parent->hf_size_rx, @@ -870,8 +880,8 @@ static int gs_can_open(struct net_device *netdev) if (!buf) { netdev_err(netdev, "No memory left for USB buffer\n"); - usb_free_urb(urb); - return -ENOMEM; + rc = -ENOMEM; + goto out_usb_free_urb; } /* fill, anchor, and submit rx urb */ @@ -894,9 +904,7 @@ static int gs_can_open(struct net_device *netdev) netdev_err(netdev, "usb_submit failed (err=%d)\n", rc); - usb_unanchor_urb(urb); - usb_free_urb(urb); - break; + goto out_usb_unanchor_urb; } /* Drop reference, @@ -926,13 +934,9 @@ static int gs_can_open(struct net_device *netdev) flags |= GS_CAN_MODE_FD; /* if hardware supports timestamps, enable it */ - if (dev->feature & GS_CAN_FEATURE_HW_TIMESTAMP) { + if (dev->feature & GS_CAN_FEATURE_HW_TIMESTAMP) flags |= GS_CAN_MODE_HW_TIMESTAMP; - /* start polling timestamp */ - gs_usb_timestamp_init(dev); - } - /* finally start device */ dev->can.state = CAN_STATE_ERROR_ACTIVE; dm.flags = cpu_to_le32(flags); @@ -942,10 +946,9 @@ static int gs_can_open(struct net_device *netdev) GFP_KERNEL); if (rc) { netdev_err(netdev, "Couldn't start device (err=%d)\n", rc); - if (dev->feature & GS_CAN_FEATURE_HW_TIMESTAMP) - gs_usb_timestamp_stop(dev); dev->can.state = CAN_STATE_STOPPED; - return rc; + + goto out_usb_kill_anchored_urbs; } parent->active_channels++; @@ -953,6 +956,22 @@ static int gs_can_open(struct net_device *netdev) netif_start_queue(netdev); return 0; + +out_usb_unanchor_urb: + usb_unanchor_urb(urb); +out_usb_free_urb: + usb_free_urb(urb); +out_usb_kill_anchored_urbs: + if (!parent->active_channels) { + usb_kill_anchored_urbs(&dev->tx_submitted); + + if (dev->feature & GS_CAN_FEATURE_HW_TIMESTAMP) + gs_usb_timestamp_stop(parent); + } + + close_candev(netdev); + + return rc; } static int gs_usb_get_state(const struct net_device *netdev, @@ -998,14 +1017,13 @@ static int gs_can_close(struct net_device *netdev) netif_stop_queue(netdev); - /* stop polling timestamp */ - if (dev->feature & GS_CAN_FEATURE_HW_TIMESTAMP) - gs_usb_timestamp_stop(dev); - /* Stop polling */ parent->active_channels--; if (!parent->active_channels) { usb_kill_anchored_urbs(&parent->rx_submitted); + + if (dev->feature & GS_CAN_FEATURE_HW_TIMESTAMP) + gs_usb_timestamp_stop(parent); } /* Stop sending URBs */ diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c index 84d502589f8e..91aba470fb2f 100644 --- a/drivers/net/dsa/microchip/ksz8795.c +++ b/drivers/net/dsa/microchip/ksz8795.c @@ -506,7 +506,13 @@ static int ksz8_r_sta_mac_table(struct ksz_device *dev, u16 addr, (data_hi & masks[STATIC_MAC_TABLE_FWD_PORTS]) >> shifts[STATIC_MAC_FWD_PORTS]; alu->is_override = (data_hi & masks[STATIC_MAC_TABLE_OVERRIDE]) ? 1 : 0; - data_hi >>= 1; + + /* KSZ8795 family switches have STATIC_MAC_TABLE_USE_FID and + * STATIC_MAC_TABLE_FID definitions off by 1 when doing read on the + * static MAC table compared to doing write. + */ + if (ksz_is_ksz87xx(dev)) + data_hi >>= 1; alu->is_static = true; alu->is_use_fid = (data_hi & masks[STATIC_MAC_TABLE_USE_FID]) ? 1 : 0; alu->fid = (data_hi & masks[STATIC_MAC_TABLE_FID]) >> diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index 813b91a816bb..b18cd170ec06 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -331,13 +331,13 @@ static const u32 ksz8795_masks[] = { [STATIC_MAC_TABLE_VALID] = BIT(21), [STATIC_MAC_TABLE_USE_FID] = BIT(23), [STATIC_MAC_TABLE_FID] = GENMASK(30, 24), - [STATIC_MAC_TABLE_OVERRIDE] = BIT(26), - [STATIC_MAC_TABLE_FWD_PORTS] = GENMASK(24, 20), + [STATIC_MAC_TABLE_OVERRIDE] = BIT(22), + [STATIC_MAC_TABLE_FWD_PORTS] = GENMASK(20, 16), [DYNAMIC_MAC_TABLE_ENTRIES_H] = GENMASK(6, 0), - [DYNAMIC_MAC_TABLE_MAC_EMPTY] = BIT(8), + [DYNAMIC_MAC_TABLE_MAC_EMPTY] = BIT(7), [DYNAMIC_MAC_TABLE_NOT_READY] = BIT(7), [DYNAMIC_MAC_TABLE_ENTRIES] = GENMASK(31, 29), - [DYNAMIC_MAC_TABLE_FID] = GENMASK(26, 20), + [DYNAMIC_MAC_TABLE_FID] = GENMASK(22, 16), [DYNAMIC_MAC_TABLE_SRC_PORT] = GENMASK(26, 24), [DYNAMIC_MAC_TABLE_TIMESTAMP] = GENMASK(28, 27), [P_MII_TX_FLOW_CTRL] = BIT(5), diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h index 28444e5924f9..a4de58847dea 100644 --- a/drivers/net/dsa/microchip/ksz_common.h +++ b/drivers/net/dsa/microchip/ksz_common.h @@ -601,6 +601,13 @@ static inline void ksz_regmap_unlock(void *__mtx) mutex_unlock(mtx); } +static inline bool ksz_is_ksz87xx(struct ksz_device *dev) +{ + return dev->chip_id == KSZ8795_CHIP_ID || + dev->chip_id == KSZ8794_CHIP_ID || + dev->chip_id == KSZ8765_CHIP_ID; +} + static inline bool ksz_is_ksz88x3(struct ksz_device *dev) { return dev->chip_id == KSZ8830_CHIP_ID; diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 8b51756bd805..c7d51a539451 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -109,6 +109,13 @@ int mv88e6xxx_wait_mask(struct mv88e6xxx_chip *chip, int addr, int reg, usleep_range(1000, 2000); } + err = mv88e6xxx_read(chip, addr, reg, &data); + if (err) + return err; + + if ((data & mask) == val) + return 0; + dev_err(chip->dev, "Timeout while waiting for switch\n"); return -ETIMEDOUT; } diff --git a/drivers/net/dsa/qca/ar9331.c b/drivers/net/dsa/qca/ar9331.c index b2bf78ac485e..3b0937031499 100644 --- a/drivers/net/dsa/qca/ar9331.c +++ b/drivers/net/dsa/qca/ar9331.c @@ -1002,6 +1002,8 @@ static const struct regmap_config ar9331_mdio_regmap_config = { .val_bits = 32, .reg_stride = 4, .max_register = AR9331_SW_REG_PAGE, + .use_single_read = true, + .use_single_write = true, .ranges = ar9331_regmap_range, .num_ranges = ARRAY_SIZE(ar9331_regmap_range), @@ -1018,8 +1020,6 @@ static struct regmap_bus ar9331_sw_bus = { .val_format_endian_default = REGMAP_ENDIAN_NATIVE, .read = ar9331_mdio_read, .write = ar9331_sw_bus_write, - .max_raw_read = 4, - .max_raw_write = 4, }; static int ar9331_sw_probe(struct mdio_device *mdiodev) diff --git a/drivers/net/ethernet/brocade/bna/bnad_debugfs.c b/drivers/net/ethernet/brocade/bna/bnad_debugfs.c index 04ad0f2b9677..7246e13dd559 100644 --- a/drivers/net/ethernet/brocade/bna/bnad_debugfs.c +++ b/drivers/net/ethernet/brocade/bna/bnad_debugfs.c @@ -512,11 +512,6 @@ bnad_debugfs_init(struct bnad *bnad) if (!bnad->port_debugfs_root) { bnad->port_debugfs_root = debugfs_create_dir(name, bna_debugfs_root); - if (!bnad->port_debugfs_root) { - netdev_warn(bnad->netdev, - "debugfs root dir creation failed\n"); - return; - } atomic_inc(&bna_debugfs_port_count); diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index f80f2735e688..8cbdebc5b698 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -255,8 +255,10 @@ struct iavf_adapter { struct workqueue_struct *wq; struct work_struct reset_task; struct work_struct adminq_task; + struct work_struct finish_config; struct delayed_work client_task; wait_queue_head_t down_waitqueue; + wait_queue_head_t reset_waitqueue; wait_queue_head_t vc_waitqueue; struct iavf_q_vector *q_vectors; struct list_head vlan_filter_list; @@ -518,8 +520,9 @@ int iavf_up(struct iavf_adapter *adapter); void iavf_down(struct iavf_adapter *adapter); int iavf_process_config(struct iavf_adapter *adapter); int iavf_parse_vf_resource_msg(struct iavf_adapter *adapter); -void iavf_schedule_reset(struct iavf_adapter *adapter); +void iavf_schedule_reset(struct iavf_adapter *adapter, u64 flags); void iavf_schedule_request_stats(struct iavf_adapter *adapter); +void iavf_schedule_finish_config(struct iavf_adapter *adapter); void iavf_reset(struct iavf_adapter *adapter); void iavf_set_ethtool_ops(struct net_device *netdev); void iavf_update_stats(struct iavf_adapter *adapter); @@ -582,4 +585,5 @@ void iavf_add_adv_rss_cfg(struct iavf_adapter *adapter); void iavf_del_adv_rss_cfg(struct iavf_adapter *adapter); struct iavf_mac_filter *iavf_add_filter(struct iavf_adapter *adapter, const u8 *macaddr); +int iavf_wait_for_reset(struct iavf_adapter *adapter); #endif /* _IAVF_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index 6f171d1d85b7..2f47cfa7f06e 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -484,6 +484,7 @@ static int iavf_set_priv_flags(struct net_device *netdev, u32 flags) { struct iavf_adapter *adapter = netdev_priv(netdev); u32 orig_flags, new_flags, changed_flags; + int ret = 0; u32 i; orig_flags = READ_ONCE(adapter->flags); @@ -531,12 +532,14 @@ static int iavf_set_priv_flags(struct net_device *netdev, u32 flags) /* issue a reset to force legacy-rx change to take effect */ if (changed_flags & IAVF_FLAG_LEGACY_RX) { if (netif_running(netdev)) { - adapter->flags |= IAVF_FLAG_RESET_NEEDED; - queue_work(adapter->wq, &adapter->reset_task); + iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED); + ret = iavf_wait_for_reset(adapter); + if (ret) + netdev_warn(netdev, "Changing private flags timeout or interrupted waiting for reset"); } } - return 0; + return ret; } /** @@ -627,6 +630,7 @@ static int iavf_set_ringparam(struct net_device *netdev, { struct iavf_adapter *adapter = netdev_priv(netdev); u32 new_rx_count, new_tx_count; + int ret = 0; if ((ring->rx_mini_pending) || (ring->rx_jumbo_pending)) return -EINVAL; @@ -671,11 +675,13 @@ static int iavf_set_ringparam(struct net_device *netdev, } if (netif_running(netdev)) { - adapter->flags |= IAVF_FLAG_RESET_NEEDED; - queue_work(adapter->wq, &adapter->reset_task); + iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED); + ret = iavf_wait_for_reset(adapter); + if (ret) + netdev_warn(netdev, "Changing ring parameters timeout or interrupted waiting for reset"); } - return 0; + return ret; } /** @@ -1830,7 +1836,7 @@ static int iavf_set_channels(struct net_device *netdev, { struct iavf_adapter *adapter = netdev_priv(netdev); u32 num_req = ch->combined_count; - int i; + int ret = 0; if ((adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) && adapter->num_tc) { @@ -1852,22 +1858,13 @@ static int iavf_set_channels(struct net_device *netdev, adapter->num_req_queues = num_req; adapter->flags |= IAVF_FLAG_REINIT_ITR_NEEDED; - iavf_schedule_reset(adapter); + iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED); - /* wait for the reset is done */ - for (i = 0; i < IAVF_RESET_WAIT_COMPLETE_COUNT; i++) { - msleep(IAVF_RESET_WAIT_MS); - if (adapter->flags & IAVF_FLAG_RESET_PENDING) - continue; - break; - } - if (i == IAVF_RESET_WAIT_COMPLETE_COUNT) { - adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED; - adapter->num_active_queues = num_req; - return -EOPNOTSUPP; - } + ret = iavf_wait_for_reset(adapter); + if (ret) + netdev_warn(netdev, "Changing channel count timeout or interrupted waiting for reset"); - return 0; + return ret; } /** diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index a483eb185c99..3a88d413ddee 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -167,6 +167,45 @@ static struct iavf_adapter *iavf_pdev_to_adapter(struct pci_dev *pdev) } /** + * iavf_is_reset_in_progress - Check if a reset is in progress + * @adapter: board private structure + */ +static bool iavf_is_reset_in_progress(struct iavf_adapter *adapter) +{ + if (adapter->state == __IAVF_RESETTING || + adapter->flags & (IAVF_FLAG_RESET_PENDING | + IAVF_FLAG_RESET_NEEDED)) + return true; + + return false; +} + +/** + * iavf_wait_for_reset - Wait for reset to finish. + * @adapter: board private structure + * + * Returns 0 if reset finished successfully, negative on timeout or interrupt. + */ +int iavf_wait_for_reset(struct iavf_adapter *adapter) +{ + int ret = wait_event_interruptible_timeout(adapter->reset_waitqueue, + !iavf_is_reset_in_progress(adapter), + msecs_to_jiffies(5000)); + + /* If ret < 0 then it means wait was interrupted. + * If ret == 0 then it means we got a timeout while waiting + * for reset to finish. + * If ret > 0 it means reset has finished. + */ + if (ret > 0) + return 0; + else if (ret < 0) + return -EINTR; + else + return -EBUSY; +} + +/** * iavf_allocate_dma_mem_d - OS specific memory alloc for shared code * @hw: pointer to the HW structure * @mem: ptr to mem struct to fill out @@ -262,12 +301,14 @@ static int iavf_lock_timeout(struct mutex *lock, unsigned int msecs) /** * iavf_schedule_reset - Set the flags and schedule a reset event * @adapter: board private structure + * @flags: IAVF_FLAG_RESET_PENDING or IAVF_FLAG_RESET_NEEDED **/ -void iavf_schedule_reset(struct iavf_adapter *adapter) +void iavf_schedule_reset(struct iavf_adapter *adapter, u64 flags) { - if (!(adapter->flags & - (IAVF_FLAG_RESET_PENDING | IAVF_FLAG_RESET_NEEDED))) { - adapter->flags |= IAVF_FLAG_RESET_NEEDED; + if (!test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section) && + !(adapter->flags & + (IAVF_FLAG_RESET_PENDING | IAVF_FLAG_RESET_NEEDED))) { + adapter->flags |= flags; queue_work(adapter->wq, &adapter->reset_task); } } @@ -295,7 +336,7 @@ static void iavf_tx_timeout(struct net_device *netdev, unsigned int txqueue) struct iavf_adapter *adapter = netdev_priv(netdev); adapter->tx_timeout_count++; - iavf_schedule_reset(adapter); + iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED); } /** @@ -1651,10 +1692,10 @@ static int iavf_set_interrupt_capability(struct iavf_adapter *adapter) adapter->msix_entries[vector].entry = vector; err = iavf_acquire_msix_vectors(adapter, v_budget); + if (!err) + iavf_schedule_finish_config(adapter); out: - netif_set_real_num_rx_queues(adapter->netdev, pairs); - netif_set_real_num_tx_queues(adapter->netdev, pairs); return err; } @@ -1828,19 +1869,16 @@ static int iavf_alloc_q_vectors(struct iavf_adapter *adapter) static void iavf_free_q_vectors(struct iavf_adapter *adapter) { int q_idx, num_q_vectors; - int napi_vectors; if (!adapter->q_vectors) return; num_q_vectors = adapter->num_msix_vectors - NONQ_VECS; - napi_vectors = adapter->num_active_queues; for (q_idx = 0; q_idx < num_q_vectors; q_idx++) { struct iavf_q_vector *q_vector = &adapter->q_vectors[q_idx]; - if (q_idx < napi_vectors) - netif_napi_del(&q_vector->napi); + netif_napi_del(&q_vector->napi); } kfree(adapter->q_vectors); adapter->q_vectors = NULL; @@ -1877,9 +1915,7 @@ static int iavf_init_interrupt_scheme(struct iavf_adapter *adapter) goto err_alloc_queues; } - rtnl_lock(); err = iavf_set_interrupt_capability(adapter); - rtnl_unlock(); if (err) { dev_err(&adapter->pdev->dev, "Unable to setup interrupt capabilities\n"); @@ -1932,15 +1968,16 @@ static void iavf_free_rss(struct iavf_adapter *adapter) /** * iavf_reinit_interrupt_scheme - Reallocate queues and vectors * @adapter: board private structure + * @running: true if adapter->state == __IAVF_RUNNING * * Returns 0 on success, negative on failure **/ -static int iavf_reinit_interrupt_scheme(struct iavf_adapter *adapter) +static int iavf_reinit_interrupt_scheme(struct iavf_adapter *adapter, bool running) { struct net_device *netdev = adapter->netdev; int err; - if (netif_running(netdev)) + if (running) iavf_free_traffic_irqs(adapter); iavf_free_misc_irq(adapter); iavf_reset_interrupt_capability(adapter); @@ -1965,6 +2002,78 @@ err: } /** + * iavf_finish_config - do all netdev work that needs RTNL + * @work: our work_struct + * + * Do work that needs both RTNL and crit_lock. + **/ +static void iavf_finish_config(struct work_struct *work) +{ + struct iavf_adapter *adapter; + int pairs, err; + + adapter = container_of(work, struct iavf_adapter, finish_config); + + /* Always take RTNL first to prevent circular lock dependency */ + rtnl_lock(); + mutex_lock(&adapter->crit_lock); + + if ((adapter->flags & IAVF_FLAG_SETUP_NETDEV_FEATURES) && + adapter->netdev_registered && + !test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section)) { + netdev_update_features(adapter->netdev); + adapter->flags &= ~IAVF_FLAG_SETUP_NETDEV_FEATURES; + } + + switch (adapter->state) { + case __IAVF_DOWN: + if (!adapter->netdev_registered) { + err = register_netdevice(adapter->netdev); + if (err) { + dev_err(&adapter->pdev->dev, "Unable to register netdev (%d)\n", + err); + + /* go back and try again.*/ + iavf_free_rss(adapter); + iavf_free_misc_irq(adapter); + iavf_reset_interrupt_capability(adapter); + iavf_change_state(adapter, + __IAVF_INIT_CONFIG_ADAPTER); + goto out; + } + adapter->netdev_registered = true; + } + + /* Set the real number of queues when reset occurs while + * state == __IAVF_DOWN + */ + fallthrough; + case __IAVF_RUNNING: + pairs = adapter->num_active_queues; + netif_set_real_num_rx_queues(adapter->netdev, pairs); + netif_set_real_num_tx_queues(adapter->netdev, pairs); + break; + + default: + break; + } + +out: + mutex_unlock(&adapter->crit_lock); + rtnl_unlock(); +} + +/** + * iavf_schedule_finish_config - Set the flags and schedule a reset event + * @adapter: board private structure + **/ +void iavf_schedule_finish_config(struct iavf_adapter *adapter) +{ + if (!test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section)) + queue_work(adapter->wq, &adapter->finish_config); +} + +/** * iavf_process_aq_command - process aq_required flags * and sends aq command * @adapter: pointer to iavf adapter structure @@ -2371,7 +2480,7 @@ int iavf_parse_vf_resource_msg(struct iavf_adapter *adapter) adapter->vsi_res->num_queue_pairs); adapter->flags |= IAVF_FLAG_REINIT_MSIX_NEEDED; adapter->num_req_queues = adapter->vsi_res->num_queue_pairs; - iavf_schedule_reset(adapter); + iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED); return -EAGAIN; } @@ -2601,22 +2710,8 @@ static void iavf_init_config_adapter(struct iavf_adapter *adapter) netif_carrier_off(netdev); adapter->link_up = false; - - /* set the semaphore to prevent any callbacks after device registration - * up to time when state of driver will be set to __IAVF_DOWN - */ - rtnl_lock(); - if (!adapter->netdev_registered) { - err = register_netdevice(netdev); - if (err) { - rtnl_unlock(); - goto err_register; - } - } - - adapter->netdev_registered = true; - netif_tx_stop_all_queues(netdev); + if (CLIENT_ALLOWED(adapter)) { err = iavf_lan_add_device(adapter); if (err) @@ -2629,7 +2724,6 @@ static void iavf_init_config_adapter(struct iavf_adapter *adapter) iavf_change_state(adapter, __IAVF_DOWN); set_bit(__IAVF_VSI_DOWN, adapter->vsi.state); - rtnl_unlock(); iavf_misc_irq_enable(adapter); wake_up(&adapter->down_waitqueue); @@ -2649,10 +2743,11 @@ static void iavf_init_config_adapter(struct iavf_adapter *adapter) /* request initial VLAN offload settings */ iavf_set_vlan_offload_features(adapter, 0, netdev->features); + iavf_schedule_finish_config(adapter); return; + err_mem: iavf_free_rss(adapter); -err_register: iavf_free_misc_irq(adapter); err_sw_init: iavf_reset_interrupt_capability(adapter); @@ -2679,26 +2774,9 @@ static void iavf_watchdog_task(struct work_struct *work) goto restart_watchdog; } - if ((adapter->flags & IAVF_FLAG_SETUP_NETDEV_FEATURES) && - adapter->netdev_registered && - !test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section) && - rtnl_trylock()) { - netdev_update_features(adapter->netdev); - rtnl_unlock(); - adapter->flags &= ~IAVF_FLAG_SETUP_NETDEV_FEATURES; - } - if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) iavf_change_state(adapter, __IAVF_COMM_FAILED); - if (adapter->flags & IAVF_FLAG_RESET_NEEDED) { - adapter->aq_required = 0; - adapter->current_op = VIRTCHNL_OP_UNKNOWN; - mutex_unlock(&adapter->crit_lock); - queue_work(adapter->wq, &adapter->reset_task); - return; - } - switch (adapter->state) { case __IAVF_STARTUP: iavf_startup(adapter); @@ -2826,11 +2904,10 @@ static void iavf_watchdog_task(struct work_struct *work) /* check for hw reset */ reg_val = rd32(hw, IAVF_VF_ARQLEN1) & IAVF_VF_ARQLEN1_ARQENABLE_MASK; if (!reg_val) { - adapter->flags |= IAVF_FLAG_RESET_PENDING; adapter->aq_required = 0; adapter->current_op = VIRTCHNL_OP_UNKNOWN; dev_err(&adapter->pdev->dev, "Hardware reset detected\n"); - queue_work(adapter->wq, &adapter->reset_task); + iavf_schedule_reset(adapter, IAVF_FLAG_RESET_PENDING); mutex_unlock(&adapter->crit_lock); queue_delayed_work(adapter->wq, &adapter->watchdog_task, HZ * 2); @@ -2940,11 +3017,6 @@ static void iavf_reset_task(struct work_struct *work) int i = 0, err; bool running; - /* Detach interface to avoid subsequent NDO callbacks */ - rtnl_lock(); - netif_device_detach(netdev); - rtnl_unlock(); - /* When device is being removed it doesn't make sense to run the reset * task, just return in such a case. */ @@ -2952,7 +3024,7 @@ static void iavf_reset_task(struct work_struct *work) if (adapter->state != __IAVF_REMOVE) queue_work(adapter->wq, &adapter->reset_task); - goto reset_finish; + return; } while (!mutex_trylock(&adapter->client_lock)) @@ -3010,11 +3082,6 @@ static void iavf_reset_task(struct work_struct *work) iavf_disable_vf(adapter); mutex_unlock(&adapter->client_lock); mutex_unlock(&adapter->crit_lock); - if (netif_running(netdev)) { - rtnl_lock(); - dev_close(netdev); - rtnl_unlock(); - } return; /* Do not attempt to reinit. It's dead, Jim. */ } @@ -3056,7 +3123,7 @@ continue_reset: if ((adapter->flags & IAVF_FLAG_REINIT_MSIX_NEEDED) || (adapter->flags & IAVF_FLAG_REINIT_ITR_NEEDED)) { - err = iavf_reinit_interrupt_scheme(adapter); + err = iavf_reinit_interrupt_scheme(adapter, running); if (err) goto reset_err; } @@ -3151,10 +3218,11 @@ continue_reset: adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED; + wake_up(&adapter->reset_waitqueue); mutex_unlock(&adapter->client_lock); mutex_unlock(&adapter->crit_lock); - goto reset_finish; + return; reset_err: if (running) { set_bit(__IAVF_VSI_DOWN, adapter->vsi.state); @@ -3164,21 +3232,7 @@ reset_err: mutex_unlock(&adapter->client_lock); mutex_unlock(&adapter->crit_lock); - - if (netif_running(netdev)) { - /* Close device to ensure that Tx queues will not be started - * during netif_device_attach() at the end of the reset task. - */ - rtnl_lock(); - dev_close(netdev); - rtnl_unlock(); - } - dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit\n"); -reset_finish: - rtnl_lock(); - netif_device_attach(netdev); - rtnl_unlock(); } /** @@ -3227,9 +3281,7 @@ static void iavf_adminq_task(struct work_struct *work) } while (pending); mutex_unlock(&adapter->crit_lock); - if ((adapter->flags & - (IAVF_FLAG_RESET_PENDING | IAVF_FLAG_RESET_NEEDED)) || - adapter->state == __IAVF_RESETTING) + if (iavf_is_reset_in_progress(adapter)) goto freedom; /* check for error indications */ @@ -4315,6 +4367,7 @@ static int iavf_close(struct net_device *netdev) static int iavf_change_mtu(struct net_device *netdev, int new_mtu) { struct iavf_adapter *adapter = netdev_priv(netdev); + int ret = 0; netdev_dbg(netdev, "changing MTU from %d to %d\n", netdev->mtu, new_mtu); @@ -4325,11 +4378,15 @@ static int iavf_change_mtu(struct net_device *netdev, int new_mtu) } if (netif_running(netdev)) { - adapter->flags |= IAVF_FLAG_RESET_NEEDED; - queue_work(adapter->wq, &adapter->reset_task); + iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED); + ret = iavf_wait_for_reset(adapter); + if (ret < 0) + netdev_warn(netdev, "MTU change interrupted waiting for reset"); + else if (ret) + netdev_warn(netdev, "MTU change timed out waiting for reset"); } - return 0; + return ret; } #define NETIF_VLAN_OFFLOAD_FEATURES (NETIF_F_HW_VLAN_CTAG_RX | \ @@ -4922,6 +4979,7 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) INIT_WORK(&adapter->reset_task, iavf_reset_task); INIT_WORK(&adapter->adminq_task, iavf_adminq_task); + INIT_WORK(&adapter->finish_config, iavf_finish_config); INIT_DELAYED_WORK(&adapter->watchdog_task, iavf_watchdog_task); INIT_DELAYED_WORK(&adapter->client_task, iavf_client_task); queue_delayed_work(adapter->wq, &adapter->watchdog_task, @@ -4930,6 +4988,9 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* Setup the wait queue for indicating transition to down status */ init_waitqueue_head(&adapter->down_waitqueue); + /* Setup the wait queue for indicating transition to running state */ + init_waitqueue_head(&adapter->reset_waitqueue); + /* Setup the wait queue for indicating virtchannel events */ init_waitqueue_head(&adapter->vc_waitqueue); @@ -5061,13 +5122,15 @@ static void iavf_remove(struct pci_dev *pdev) usleep_range(500, 1000); } cancel_delayed_work_sync(&adapter->watchdog_task); + cancel_work_sync(&adapter->finish_config); + rtnl_lock(); if (adapter->netdev_registered) { - rtnl_lock(); unregister_netdevice(netdev); adapter->netdev_registered = false; - rtnl_unlock(); } + rtnl_unlock(); + if (CLIENT_ALLOWED(adapter)) { err = iavf_lan_del_device(adapter); if (err) diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 7c0578b5457b..be3c007ce90a 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -1961,9 +1961,8 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, case VIRTCHNL_EVENT_RESET_IMPENDING: dev_info(&adapter->pdev->dev, "Reset indication received from the PF\n"); if (!(adapter->flags & IAVF_FLAG_RESET_PENDING)) { - adapter->flags |= IAVF_FLAG_RESET_PENDING; dev_info(&adapter->pdev->dev, "Scheduling reset task\n"); - queue_work(adapter->wq, &adapter->reset_task); + iavf_schedule_reset(adapter, IAVF_FLAG_RESET_PENDING); } break; default: @@ -2237,6 +2236,7 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, iavf_process_config(adapter); adapter->flags |= IAVF_FLAG_SETUP_NETDEV_FEATURES; + iavf_schedule_finish_config(adapter); iavf_set_queue_vlan_tag_loc(adapter); @@ -2285,6 +2285,7 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, case VIRTCHNL_OP_ENABLE_QUEUES: /* enable transmits */ iavf_irq_enable(adapter, true); + wake_up(&adapter->reset_waitqueue); adapter->flags &= ~IAVF_FLAG_QUEUES_DISABLED; break; case VIRTCHNL_OP_DISABLE_QUEUES: diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index 4a12316f7b46..b678bdf96f3a 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -800,6 +800,8 @@ void ice_vsi_free_q_vectors(struct ice_vsi *vsi) ice_for_each_q_vector(vsi, v_idx) ice_free_q_vector(vsi, v_idx); + + vsi->num_q_vectors = 0; } /** diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 8d5cbbd0b3d5..ad4d4702129f 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -2681,8 +2681,13 @@ ice_get_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring, ring->rx_max_pending = ICE_MAX_NUM_DESC; ring->tx_max_pending = ICE_MAX_NUM_DESC; - ring->rx_pending = vsi->rx_rings[0]->count; - ring->tx_pending = vsi->tx_rings[0]->count; + if (vsi->tx_rings && vsi->rx_rings) { + ring->rx_pending = vsi->rx_rings[0]->count; + ring->tx_pending = vsi->tx_rings[0]->count; + } else { + ring->rx_pending = 0; + ring->tx_pending = 0; + } /* Rx mini and jumbo rings are not supported */ ring->rx_mini_max_pending = 0; @@ -2716,6 +2721,10 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring, return -EINVAL; } + /* Return if there is no rings (device is reloading) */ + if (!vsi->tx_rings || !vsi->rx_rings) + return -EBUSY; + new_tx_cnt = ALIGN(ring->tx_pending, ICE_REQ_DESC_MULTIPLE); if (new_tx_cnt != ring->tx_pending) netdev_info(netdev, "Requested Tx descriptor count rounded up to %d\n", diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 00e3afd507a4..0054d7e64ec3 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -2972,39 +2972,12 @@ int ice_vsi_release(struct ice_vsi *vsi) return -ENODEV; pf = vsi->back; - /* do not unregister while driver is in the reset recovery pending - * state. Since reset/rebuild happens through PF service task workqueue, - * it's not a good idea to unregister netdev that is associated to the - * PF that is running the work queue items currently. This is done to - * avoid check_flush_dependency() warning on this wq - */ - if (vsi->netdev && !ice_is_reset_in_progress(pf->state) && - (test_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state))) { - unregister_netdev(vsi->netdev); - clear_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state); - } - - if (vsi->type == ICE_VSI_PF) - ice_devlink_destroy_pf_port(pf); - if (test_bit(ICE_FLAG_RSS_ENA, pf->flags)) ice_rss_clean(vsi); ice_vsi_close(vsi); ice_vsi_decfg(vsi); - if (vsi->netdev) { - if (test_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state)) { - unregister_netdev(vsi->netdev); - clear_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state); - } - if (test_bit(ICE_VSI_NETDEV_ALLOCD, vsi->state)) { - free_netdev(vsi->netdev); - vsi->netdev = NULL; - clear_bit(ICE_VSI_NETDEV_ALLOCD, vsi->state); - } - } - /* retain SW VSI data structure since it is needed to unregister and * free VSI netdev when PF is not in reset recovery pending state,\ * for ex: during rmmod. diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 19a5e7f3a075..f02d44455772 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -4430,9 +4430,9 @@ static int ice_start_eth(struct ice_vsi *vsi) if (err) return err; - rtnl_lock(); err = ice_vsi_open(vsi); - rtnl_unlock(); + if (err) + ice_fltr_remove_all(vsi); return err; } @@ -4895,6 +4895,7 @@ int ice_load(struct ice_pf *pf) params = ice_vsi_to_params(vsi); params.flags = ICE_VSI_FLAG_INIT; + rtnl_lock(); err = ice_vsi_cfg(vsi, ¶ms); if (err) goto err_vsi_cfg; @@ -4902,6 +4903,7 @@ int ice_load(struct ice_pf *pf) err = ice_start_eth(ice_get_main_vsi(pf)); if (err) goto err_start_eth; + rtnl_unlock(); err = ice_init_rdma(pf); if (err) @@ -4916,9 +4918,11 @@ int ice_load(struct ice_pf *pf) err_init_rdma: ice_vsi_close(ice_get_main_vsi(pf)); + rtnl_lock(); err_start_eth: ice_vsi_decfg(ice_get_main_vsi(pf)); err_vsi_cfg: + rtnl_unlock(); ice_deinit_dev(pf); return err; } @@ -4931,8 +4935,10 @@ void ice_unload(struct ice_pf *pf) { ice_deinit_features(pf); ice_deinit_rdma(pf); + rtnl_lock(); ice_stop_eth(ice_get_main_vsi(pf)); ice_vsi_decfg(ice_get_main_vsi(pf)); + rtnl_unlock(); ice_deinit_dev(pf); } diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 9f93f0f4f752..f36bc2a1849a 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -2828,9 +2828,8 @@ static void igc_xdp_xmit_zc(struct igc_ring *ring) struct netdev_queue *nq = txring_txq(ring); union igc_adv_tx_desc *tx_desc = NULL; int cpu = smp_processor_id(); - u16 ntu = ring->next_to_use; struct xdp_desc xdp_desc; - u16 budget; + u16 budget, ntu; if (!netif_carrier_ok(ring->netdev)) return; @@ -2840,6 +2839,7 @@ static void igc_xdp_xmit_zc(struct igc_ring *ring) /* Avoid transmit queue timeout since we share it with the slow path */ txq_trans_cond_update(nq); + ntu = ring->next_to_use; budget = igc_desc_unused(ring); while (xsk_tx_peek_desc(pool, &xdp_desc) && budget--) { diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c index 6e2fb24be8c1..59b138214af2 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c @@ -4,6 +4,7 @@ * Copyright (C) 2022 Marvell. */ +#include <crypto/skcipher.h> #include <linux/rtnetlink.h> #include <linux/bitfield.h> #include "otx2_common.h" @@ -42,6 +43,56 @@ #define MCS_TCI_E 0x08 /* encryption */ #define MCS_TCI_C 0x04 /* changed text */ +#define CN10K_MAX_HASH_LEN 16 +#define CN10K_MAX_SAK_LEN 32 + +static int cn10k_ecb_aes_encrypt(struct otx2_nic *pfvf, u8 *sak, + u16 sak_len, u8 *hash) +{ + u8 data[CN10K_MAX_HASH_LEN] = { 0 }; + struct skcipher_request *req = NULL; + struct scatterlist sg_src, sg_dst; + struct crypto_skcipher *tfm; + DECLARE_CRYPTO_WAIT(wait); + int err; + + tfm = crypto_alloc_skcipher("ecb(aes)", 0, 0); + if (IS_ERR(tfm)) { + dev_err(pfvf->dev, "failed to allocate transform for ecb-aes\n"); + return PTR_ERR(tfm); + } + + req = skcipher_request_alloc(tfm, GFP_KERNEL); + if (!req) { + dev_err(pfvf->dev, "failed to allocate request for skcipher\n"); + err = -ENOMEM; + goto free_tfm; + } + + err = crypto_skcipher_setkey(tfm, sak, sak_len); + if (err) { + dev_err(pfvf->dev, "failed to set key for skcipher\n"); + goto free_req; + } + + /* build sg list */ + sg_init_one(&sg_src, data, CN10K_MAX_HASH_LEN); + sg_init_one(&sg_dst, hash, CN10K_MAX_HASH_LEN); + + skcipher_request_set_callback(req, 0, crypto_req_done, &wait); + skcipher_request_set_crypt(req, &sg_src, &sg_dst, + CN10K_MAX_HASH_LEN, NULL); + + err = crypto_skcipher_encrypt(req); + err = crypto_wait_req(err, &wait); + +free_req: + skcipher_request_free(req); +free_tfm: + crypto_free_skcipher(tfm); + return err; +} + static struct cn10k_mcs_txsc *cn10k_mcs_get_txsc(struct cn10k_mcs_cfg *cfg, struct macsec_secy *secy) { @@ -330,19 +381,53 @@ fail: return ret; } +static int cn10k_mcs_write_keys(struct otx2_nic *pfvf, + struct macsec_secy *secy, + struct mcs_sa_plcy_write_req *req, + u8 *sak, u8 *salt, ssci_t ssci) +{ + u8 hash_rev[CN10K_MAX_HASH_LEN]; + u8 sak_rev[CN10K_MAX_SAK_LEN]; + u8 salt_rev[MACSEC_SALT_LEN]; + u8 hash[CN10K_MAX_HASH_LEN]; + u32 ssci_63_32; + int err, i; + + err = cn10k_ecb_aes_encrypt(pfvf, sak, secy->key_len, hash); + if (err) { + dev_err(pfvf->dev, "Generating hash using ECB(AES) failed\n"); + return err; + } + + for (i = 0; i < secy->key_len; i++) + sak_rev[i] = sak[secy->key_len - 1 - i]; + + for (i = 0; i < CN10K_MAX_HASH_LEN; i++) + hash_rev[i] = hash[CN10K_MAX_HASH_LEN - 1 - i]; + + for (i = 0; i < MACSEC_SALT_LEN; i++) + salt_rev[i] = salt[MACSEC_SALT_LEN - 1 - i]; + + ssci_63_32 = (__force u32)cpu_to_be32((__force u32)ssci); + + memcpy(&req->plcy[0][0], sak_rev, secy->key_len); + memcpy(&req->plcy[0][4], hash_rev, CN10K_MAX_HASH_LEN); + memcpy(&req->plcy[0][6], salt_rev, MACSEC_SALT_LEN); + req->plcy[0][7] |= (u64)ssci_63_32 << 32; + + return 0; +} + static int cn10k_mcs_write_rx_sa_plcy(struct otx2_nic *pfvf, struct macsec_secy *secy, struct cn10k_mcs_rxsc *rxsc, u8 assoc_num, bool sa_in_use) { - unsigned char *src = rxsc->sa_key[assoc_num]; struct mcs_sa_plcy_write_req *plcy_req; - u8 *salt_p = rxsc->salt[assoc_num]; + u8 *sak = rxsc->sa_key[assoc_num]; + u8 *salt = rxsc->salt[assoc_num]; struct mcs_rx_sc_sa_map *map_req; struct mbox *mbox = &pfvf->mbox; - u64 ssci_salt_95_64 = 0; - u8 reg, key_len; - u64 salt_63_0; int ret; mutex_lock(&mbox->lock); @@ -360,20 +445,10 @@ static int cn10k_mcs_write_rx_sa_plcy(struct otx2_nic *pfvf, goto fail; } - for (reg = 0, key_len = 0; key_len < secy->key_len; key_len += 8) { - memcpy((u8 *)&plcy_req->plcy[0][reg], - (src + reg * 8), 8); - reg++; - } - - if (secy->xpn) { - memcpy((u8 *)&salt_63_0, salt_p, 8); - memcpy((u8 *)&ssci_salt_95_64, salt_p + 8, 4); - ssci_salt_95_64 |= (__force u64)rxsc->ssci[assoc_num] << 32; - - plcy_req->plcy[0][6] = salt_63_0; - plcy_req->plcy[0][7] = ssci_salt_95_64; - } + ret = cn10k_mcs_write_keys(pfvf, secy, plcy_req, sak, + salt, rxsc->ssci[assoc_num]); + if (ret) + goto fail; plcy_req->sa_index[0] = rxsc->hw_sa_id[assoc_num]; plcy_req->sa_cnt = 1; @@ -586,13 +661,10 @@ static int cn10k_mcs_write_tx_sa_plcy(struct otx2_nic *pfvf, struct cn10k_mcs_txsc *txsc, u8 assoc_num) { - unsigned char *src = txsc->sa_key[assoc_num]; struct mcs_sa_plcy_write_req *plcy_req; - u8 *salt_p = txsc->salt[assoc_num]; + u8 *sak = txsc->sa_key[assoc_num]; + u8 *salt = txsc->salt[assoc_num]; struct mbox *mbox = &pfvf->mbox; - u64 ssci_salt_95_64 = 0; - u8 reg, key_len; - u64 salt_63_0; int ret; mutex_lock(&mbox->lock); @@ -603,19 +675,10 @@ static int cn10k_mcs_write_tx_sa_plcy(struct otx2_nic *pfvf, goto fail; } - for (reg = 0, key_len = 0; key_len < secy->key_len; key_len += 8) { - memcpy((u8 *)&plcy_req->plcy[0][reg], (src + reg * 8), 8); - reg++; - } - - if (secy->xpn) { - memcpy((u8 *)&salt_63_0, salt_p, 8); - memcpy((u8 *)&ssci_salt_95_64, salt_p + 8, 4); - ssci_salt_95_64 |= (__force u64)txsc->ssci[assoc_num] << 32; - - plcy_req->plcy[0][6] = salt_63_0; - plcy_req->plcy[0][7] = ssci_salt_95_64; - } + ret = cn10k_mcs_write_keys(pfvf, secy, plcy_req, sak, + salt, txsc->ssci[assoc_num]); + if (ret) + goto fail; plcy_req->plcy[0][8] = assoc_num; plcy_req->sa_index[0] = txsc->hw_sa_id[assoc_num]; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index fe8ea4e531b7..9551b422622a 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -1454,8 +1454,9 @@ static int otx2_init_hw_resources(struct otx2_nic *pf) if (err) goto err_free_npa_lf; - /* Enable backpressure */ - otx2_nix_config_bp(pf, true); + /* Enable backpressure for CGX mapped PF/VFs */ + if (!is_otx2_lbkvf(pf->pdev)) + otx2_nix_config_bp(pf, true); /* Init Auras and pools used by NIX RQ, for free buffer ptrs */ err = otx2_rq_aura_pool_init(pf); diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 834c644b67db..2d15342c260a 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -3846,23 +3846,6 @@ static int mtk_hw_deinit(struct mtk_eth *eth) return 0; } -static int __init mtk_init(struct net_device *dev) -{ - struct mtk_mac *mac = netdev_priv(dev); - struct mtk_eth *eth = mac->hw; - int ret; - - ret = of_get_ethdev_address(mac->of_node, dev); - if (ret) { - /* If the mac address is invalid, use random mac address */ - eth_hw_addr_random(dev); - dev_err(eth->dev, "generated random MAC address %pM\n", - dev->dev_addr); - } - - return 0; -} - static void mtk_uninit(struct net_device *dev) { struct mtk_mac *mac = netdev_priv(dev); @@ -4278,7 +4261,6 @@ static const struct ethtool_ops mtk_ethtool_ops = { }; static const struct net_device_ops mtk_netdev_ops = { - .ndo_init = mtk_init, .ndo_uninit = mtk_uninit, .ndo_open = mtk_open, .ndo_stop = mtk_stop, @@ -4340,6 +4322,17 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np) mac->hw = eth; mac->of_node = np; + err = of_get_ethdev_address(mac->of_node, eth->netdev[id]); + if (err == -EPROBE_DEFER) + return err; + + if (err) { + /* If the mac address is invalid, use random mac address */ + eth_hw_addr_random(eth->netdev[id]); + dev_err(eth->dev, "generated random MAC address %pM\n", + eth->netdev[id]->dev_addr); + } + memset(mac->hwlro_ip, 0, sizeof(mac->hwlro_ip)); mac->hwlro_ip_cnt = 0; diff --git a/drivers/net/ethernet/mediatek/mtk_ppe_debugfs.c b/drivers/net/ethernet/mediatek/mtk_ppe_debugfs.c index 316fe2e70fea..1a97feca77f2 100644 --- a/drivers/net/ethernet/mediatek/mtk_ppe_debugfs.c +++ b/drivers/net/ethernet/mediatek/mtk_ppe_debugfs.c @@ -98,7 +98,7 @@ mtk_ppe_debugfs_foe_show(struct seq_file *m, void *private, bool bind) acct = mtk_foe_entry_get_mib(ppe, i, NULL); - type = FIELD_GET(MTK_FOE_IB1_PACKET_TYPE, entry->ib1); + type = mtk_get_ib1_pkt_type(ppe->eth, entry->ib1); seq_printf(m, "%05x %s %7s", i, mtk_foe_entry_state_str(state), mtk_foe_pkt_type_str(type)); diff --git a/drivers/net/ethernet/mscc/ocelot_fdma.c b/drivers/net/ethernet/mscc/ocelot_fdma.c index 8e3894cf5f7c..83a3ce0c568e 100644 --- a/drivers/net/ethernet/mscc/ocelot_fdma.c +++ b/drivers/net/ethernet/mscc/ocelot_fdma.c @@ -368,7 +368,8 @@ static bool ocelot_fdma_receive_skb(struct ocelot *ocelot, struct sk_buff *skb) if (unlikely(!ndev)) return false; - pskb_trim(skb, skb->len - ETH_FCS_LEN); + if (pskb_trim(skb, skb->len - ETH_FCS_LEN)) + return false; skb->dev = ndev; skb->protocol = eth_type_trans(skb, skb->dev); diff --git a/drivers/net/ethernet/qualcomm/emac/emac-mac.c b/drivers/net/ethernet/qualcomm/emac/emac-mac.c index 0d80447d4d3b..d5c688a8d7be 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac-mac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac-mac.c @@ -1260,8 +1260,11 @@ static int emac_tso_csum(struct emac_adapter *adpt, if (skb->protocol == htons(ETH_P_IP)) { u32 pkt_len = ((unsigned char *)ip_hdr(skb) - skb->data) + ntohs(ip_hdr(skb)->tot_len); - if (skb->len > pkt_len) - pskb_trim(skb, pkt_len); + if (skb->len > pkt_len) { + ret = pskb_trim(skb, pkt_len); + if (unlikely(ret)) + return ret; + } } hdr_len = skb_tcp_all_headers(skb); diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 9445f04f8d48..5eb50b265c0b 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -623,6 +623,7 @@ struct rtl8169_private { int cfg9346_usage_count; unsigned supports_gmii:1; + unsigned aspm_manageable:1; dma_addr_t counters_phys_addr; struct rtl8169_counters *counters; struct rtl8169_tc_offsets tc_offset; @@ -2746,7 +2747,15 @@ static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable) if (tp->mac_version < RTL_GIGA_MAC_VER_32) return; - if (enable) { + /* Don't enable ASPM in the chip if OS can't control ASPM */ + if (enable && tp->aspm_manageable) { + /* On these chip versions ASPM can even harm + * bus communication of other PCI devices. + */ + if (tp->mac_version == RTL_GIGA_MAC_VER_42 || + tp->mac_version == RTL_GIGA_MAC_VER_43) + return; + rtl_mod_config5(tp, 0, ASPM_en); rtl_mod_config2(tp, 0, ClkReqEn); @@ -4514,10 +4523,6 @@ static irqreturn_t rtl8169_interrupt(int irq, void *dev_instance) } if (napi_schedule_prep(&tp->napi)) { - rtl_unlock_config_regs(tp); - rtl_hw_aspm_clkreq_enable(tp, false); - rtl_lock_config_regs(tp); - rtl_irq_disable(tp); __napi_schedule(&tp->napi); } @@ -4577,14 +4582,9 @@ static int rtl8169_poll(struct napi_struct *napi, int budget) work_done = rtl_rx(dev, tp, budget); - if (work_done < budget && napi_complete_done(napi, work_done)) { + if (work_done < budget && napi_complete_done(napi, work_done)) rtl_irq_enable(tp); - rtl_unlock_config_regs(tp); - rtl_hw_aspm_clkreq_enable(tp, true); - rtl_lock_config_regs(tp); - } - return work_done; } @@ -5158,6 +5158,16 @@ done: rtl_rar_set(tp, mac_addr); } +/* register is set if system vendor successfully tested ASPM 1.2 */ +static bool rtl_aspm_is_safe(struct rtl8169_private *tp) +{ + if (tp->mac_version >= RTL_GIGA_MAC_VER_61 && + r8168_mac_ocp_read(tp, 0xc0b2) & 0xf) + return true; + + return false; +} + static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) { struct rtl8169_private *tp; @@ -5227,6 +5237,19 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) xid); tp->mac_version = chipset; + /* Disable ASPM L1 as that cause random device stop working + * problems as well as full system hangs for some PCIe devices users. + * Chips from RTL8168h partially have issues with L1.2, but seem + * to work fine with L1 and L1.1. + */ + if (rtl_aspm_is_safe(tp)) + rc = 0; + else if (tp->mac_version >= RTL_GIGA_MAC_VER_46) + rc = pci_disable_link_state(pdev, PCIE_LINK_STATE_L1_2); + else + rc = pci_disable_link_state(pdev, PCIE_LINK_STATE_L1); + tp->aspm_manageable = !rc; + tp->dash_type = rtl_check_dash(tp); tp->cp_cmd = RTL_R16(tp, CPlusCmd) & CPCMD_MASK; diff --git a/drivers/net/ethernet/ti/cpsw_ale.c b/drivers/net/ethernet/ti/cpsw_ale.c index 0c5e783e574c..64bf22cd860c 100644 --- a/drivers/net/ethernet/ti/cpsw_ale.c +++ b/drivers/net/ethernet/ti/cpsw_ale.c @@ -106,23 +106,37 @@ struct cpsw_ale_dev_id { static inline int cpsw_ale_get_field(u32 *ale_entry, u32 start, u32 bits) { - int idx; + int idx, idx2; + u32 hi_val = 0; idx = start / 32; + idx2 = (start + bits - 1) / 32; + /* Check if bits to be fetched exceed a word */ + if (idx != idx2) { + idx2 = 2 - idx2; /* flip */ + hi_val = ale_entry[idx2] << ((idx2 * 32) - start); + } start -= idx * 32; idx = 2 - idx; /* flip */ - return (ale_entry[idx] >> start) & BITMASK(bits); + return (hi_val + (ale_entry[idx] >> start)) & BITMASK(bits); } static inline void cpsw_ale_set_field(u32 *ale_entry, u32 start, u32 bits, u32 value) { - int idx; + int idx, idx2; value &= BITMASK(bits); - idx = start / 32; + idx = start / 32; + idx2 = (start + bits - 1) / 32; + /* Check if bits to be set exceed a word */ + if (idx != idx2) { + idx2 = 2 - idx2; /* flip */ + ale_entry[idx2] &= ~(BITMASK(bits + start - (idx2 * 32))); + ale_entry[idx2] |= (value >> ((idx2 * 32) - start)); + } start -= idx * 32; - idx = 2 - idx; /* flip */ + idx = 2 - idx; /* flip */ ale_entry[idx] &= ~(BITMASK(bits) << start); ale_entry[idx] |= (value << start); } diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.c b/drivers/net/ethernet/wangxun/libwx/wx_hw.c index 39a9aeee7aab..6321178fc814 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_hw.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.c @@ -1511,7 +1511,6 @@ static void wx_configure_rx(struct wx *wx) psrtype = WX_RDB_PL_CFG_L4HDR | WX_RDB_PL_CFG_L3HDR | WX_RDB_PL_CFG_L2HDR | - WX_RDB_PL_CFG_TUN_TUNHDR | WX_RDB_PL_CFG_TUN_TUNHDR; wr32(wx, WX_RDB_PL_CFG(0), psrtype); diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 0c2014accba7..61921d4dbb13 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -3451,23 +3451,30 @@ static int __init phy_init(void) { int rc; + ethtool_set_ethtool_phy_ops(&phy_ethtool_phy_ops); + rc = mdio_bus_init(); if (rc) - return rc; + goto err_ethtool_phy_ops; - ethtool_set_ethtool_phy_ops(&phy_ethtool_phy_ops); features_init(); rc = phy_driver_register(&genphy_c45_driver, THIS_MODULE); if (rc) - goto err_c45; + goto err_mdio_bus; rc = phy_driver_register(&genphy_driver, THIS_MODULE); - if (rc) { - phy_driver_unregister(&genphy_c45_driver); + if (rc) + goto err_c45; + + return 0; + err_c45: - mdio_bus_exit(); - } + phy_driver_unregister(&genphy_c45_driver); +err_mdio_bus: + mdio_bus_exit(); +err_ethtool_phy_ops: + ethtool_set_ethtool_phy_ops(NULL); return rc; } diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 283ffddda821..2d14b0d78541 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -1775,6 +1775,10 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod) } else if (!info->in || !info->out) status = usbnet_get_endpoints (dev, udev); else { + u8 ep_addrs[3] = { + info->in + USB_DIR_IN, info->out + USB_DIR_OUT, 0 + }; + dev->in = usb_rcvbulkpipe (xdev, info->in); dev->out = usb_sndbulkpipe (xdev, info->out); if (!(info->flags & FLAG_NO_SETINT)) @@ -1784,6 +1788,8 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod) else status = 0; + if (status == 0 && !usb_check_bulk_endpoints(udev, ep_addrs)) + status = -EINVAL; } if (status >= 0 && dev->status) status = init_status (dev, udev); diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index bdb3a76a352e..6043e63b42f9 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -664,7 +664,7 @@ static int vrf_finish_output6(struct net *net, struct sock *sk, skb->protocol = htons(ETH_P_IPV6); skb->dev = dev; - rcu_read_lock_bh(); + rcu_read_lock(); nexthop = rt6_nexthop((struct rt6_info *)dst, &ipv6_hdr(skb)->daddr); neigh = __ipv6_neigh_lookup_noref(dst->dev, nexthop); if (unlikely(!neigh)) @@ -672,10 +672,10 @@ static int vrf_finish_output6(struct net *net, struct sock *sk, if (!IS_ERR(neigh)) { sock_confirm_neigh(skb, neigh); ret = neigh_output(neigh, skb, false); - rcu_read_unlock_bh(); + rcu_read_unlock(); return ret; } - rcu_read_unlock_bh(); + rcu_read_unlock(); IP6_INC_STATS(dev_net(dst->dev), ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); @@ -889,7 +889,7 @@ static int vrf_finish_output(struct net *net, struct sock *sk, struct sk_buff *s } } - rcu_read_lock_bh(); + rcu_read_lock(); neigh = ip_neigh_for_gw(rt, skb, &is_v6gw); if (!IS_ERR(neigh)) { @@ -898,11 +898,11 @@ static int vrf_finish_output(struct net *net, struct sock *sk, struct sk_buff *s sock_confirm_neigh(skb, neigh); /* if crossing protocols, can not use the cached header */ ret = neigh_output(neigh, skb, is_v6gw); - rcu_read_unlock_bh(); + rcu_read_unlock(); return ret; } - rcu_read_unlock_bh(); + rcu_read_unlock(); vrf_tx_error(skb->dev, skb); return -EINVAL; } diff --git a/include/linux/tcp.h b/include/linux/tcp.h index b4c08ac86983..91a37c99ba66 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -513,7 +513,7 @@ static inline void fastopen_queue_tune(struct sock *sk, int backlog) struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue; int somaxconn = READ_ONCE(sock_net(sk)->core.sysctl_somaxconn); - queue->fastopenq.max_qlen = min_t(unsigned int, backlog, somaxconn); + WRITE_ONCE(queue->fastopenq.max_qlen, min_t(unsigned int, backlog, somaxconn)); } static inline void tcp_move_syn(struct tcp_sock *tp, diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 9654567cfae3..e01d52cb668c 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -593,9 +593,7 @@ struct hci_dev { const char *fw_info; struct dentry *debugfs; -#ifdef CONFIG_DEV_COREDUMP struct hci_devcoredump dump; -#endif struct device dev; @@ -822,6 +820,7 @@ struct hci_conn_params { struct hci_conn *conn; bool explicit_connect; + /* Accessed without hdev->lock: */ hci_conn_flags_t flags; u8 privacy_mode; }; @@ -1573,7 +1572,11 @@ struct hci_conn_params *hci_conn_params_add(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type); void hci_conn_params_del(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type); void hci_conn_params_clear_disabled(struct hci_dev *hdev); +void hci_conn_params_free(struct hci_conn_params *param); +void hci_pend_le_list_del_init(struct hci_conn_params *param); +void hci_pend_le_list_add(struct hci_conn_params *param, + struct list_head *list); struct hci_conn_params *hci_pend_le_action_lookup(struct list_head *list, bdaddr_t *addr, u8 addr_type); diff --git a/include/net/bonding.h b/include/net/bonding.h index b57bec6e737e..30ac427cf0c6 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -277,7 +277,7 @@ struct bond_vlan_tag { unsigned short vlan_id; }; -/** +/* * Returns NULL if the net_device does not belong to any of the bond's slaves * * Caller must hold bond lock for read diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h index e00057984489..f79ce133e51a 100644 --- a/include/net/cfg802154.h +++ b/include/net/cfg802154.h @@ -170,7 +170,8 @@ wpan_phy_cca_cmp(const struct wpan_phy_cca *a, const struct wpan_phy_cca *b) } /** - * @WPAN_PHY_FLAG_TRANSMIT_POWER: Indicates that transceiver will support + * enum wpan_phy_flags - WPAN PHY state flags + * @WPAN_PHY_FLAG_TXPOWER: Indicates that transceiver will support * transmit power setting. * @WPAN_PHY_FLAG_CCA_ED_LEVEL: Indicates that transceiver will support cca ed * level setting. diff --git a/include/net/codel.h b/include/net/codel.h index 5fed2f16cb8d..aa80f744826c 100644 --- a/include/net/codel.h +++ b/include/net/codel.h @@ -145,8 +145,8 @@ struct codel_vars { * @maxpacket: largest packet we've seen so far * @drop_count: temp count of dropped packets in dequeue() * @drop_len: bytes of dropped packets in dequeue() - * ecn_mark: number of packets we ECN marked instead of dropping - * ce_mark: number of packets CE marked because sojourn time was above ce_threshold + * @ecn_mark: number of packets we ECN marked instead of dropping + * @ce_mark: number of packets CE marked because sojourn time was above ce_threshold */ struct codel_stats { u32 maxpacket; diff --git a/include/net/devlink.h b/include/net/devlink.h index 9a3c51aa6e81..0cdb4b16e5b5 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -221,7 +221,7 @@ struct devlink_dpipe_field { /** * struct devlink_dpipe_header - dpipe header object * @name: header name - * @id: index, global/local detrmined by global bit + * @id: index, global/local determined by global bit * @fields: fields * @fields_count: number of fields * @global: indicates if header is shared like most protocol header @@ -241,7 +241,7 @@ struct devlink_dpipe_header { * @header_index: header index (packets can have several headers of same * type like in case of tunnels) * @header: header - * @fieled_id: field index + * @field_id: field index */ struct devlink_dpipe_match { enum devlink_dpipe_match_type type; @@ -256,7 +256,7 @@ struct devlink_dpipe_match { * @header_index: header index (packets can have several headers of same * type like in case of tunnels) * @header: header - * @fieled_id: field index + * @field_id: field index */ struct devlink_dpipe_action { enum devlink_dpipe_action_type type; @@ -292,7 +292,7 @@ struct devlink_dpipe_value { * struct devlink_dpipe_entry - table entry object * @index: index of the entry in the table * @match_values: match values - * @matche_values_count: count of matches tuples + * @match_values_count: count of matches tuples * @action_values: actions values * @action_values_count: count of actions values * @counter: value of counter @@ -342,7 +342,9 @@ struct devlink_dpipe_table_ops; */ struct devlink_dpipe_table { void *priv; + /* private: */ struct list_head list; + /* public: */ const char *name; bool counters_enabled; bool counter_control_extern; @@ -355,13 +357,13 @@ struct devlink_dpipe_table { /** * struct devlink_dpipe_table_ops - dpipe_table ops - * @actions_dump - dumps all tables actions - * @matches_dump - dumps all tables matches - * @entries_dump - dumps all active entries in the table - * @counters_set_update - when changing the counter status hardware sync + * @actions_dump: dumps all tables actions + * @matches_dump: dumps all tables matches + * @entries_dump: dumps all active entries in the table + * @counters_set_update: when changing the counter status hardware sync * maybe needed to allocate/free counter related * resources - * @size_get - get size + * @size_get: get size */ struct devlink_dpipe_table_ops { int (*actions_dump)(void *priv, struct sk_buff *skb); @@ -374,8 +376,8 @@ struct devlink_dpipe_table_ops { /** * struct devlink_dpipe_headers - dpipe headers - * @headers - header array can be shared (global bit) or driver specific - * @headers_count - count of headers + * @headers: header array can be shared (global bit) or driver specific + * @headers_count: count of headers */ struct devlink_dpipe_headers { struct devlink_dpipe_header **headers; @@ -387,7 +389,7 @@ struct devlink_dpipe_headers { * @size_min: minimum size which can be set * @size_max: maximum size which can be set * @size_granularity: size granularity - * @size_unit: resource's basic unit + * @unit: resource's basic unit */ struct devlink_resource_size_params { u64 size_min; @@ -457,6 +459,7 @@ struct devlink_flash_notify { /** * struct devlink_param - devlink configuration parameter data + * @id: devlink parameter id number * @name: name of the parameter * @generic: indicates if the parameter is generic or driver specific * @type: parameter type @@ -632,6 +635,7 @@ enum devlink_param_generic_id { * struct devlink_flash_update_params - Flash Update parameters * @fw: pointer to the firmware data to update from * @component: the flash component to update + * @overwrite_mask: which types of flash update are supported (may be %0) * * With the exception of fw, drivers must opt-in to parameters by * setting the appropriate bit in the supported_flash_update_params field in diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index 325ad893f624..153960663ce4 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -29,7 +29,7 @@ struct fqdir { }; /** - * fragment queue flags + * enum: fragment queue flags * * @INET_FRAG_FIRST_IN: first fragment has arrived * @INET_FRAG_LAST_IN: final fragment has arrived diff --git a/include/net/llc_conn.h b/include/net/llc_conn.h index 2c1ea3414640..374411b3066c 100644 --- a/include/net/llc_conn.h +++ b/include/net/llc_conn.h @@ -111,7 +111,7 @@ void llc_conn_resend_i_pdu_as_cmd(struct sock *sk, u8 nr, u8 first_p_bit); void llc_conn_resend_i_pdu_as_rsp(struct sock *sk, u8 nr, u8 first_f_bit); int llc_conn_remove_acked_pdus(struct sock *conn, u8 nr, u16 *how_many_unacked); struct sock *llc_lookup_established(struct llc_sap *sap, struct llc_addr *daddr, - struct llc_addr *laddr); + struct llc_addr *laddr, const struct net *net); void llc_sap_add_socket(struct llc_sap *sap, struct sock *sk); void llc_sap_remove_socket(struct llc_sap *sap, struct sock *sk); diff --git a/include/net/llc_pdu.h b/include/net/llc_pdu.h index 49aa79c7b278..7e73f8e5e497 100644 --- a/include/net/llc_pdu.h +++ b/include/net/llc_pdu.h @@ -269,7 +269,7 @@ static inline void llc_pdu_decode_sa(struct sk_buff *skb, u8 *sa) /** * llc_pdu_decode_da - extracts dest address of input frame * @skb: input skb that destination address must be extracted from it - * @sa: pointer to destination address (6 byte array). + * @da: pointer to destination address (6 byte array). * * This function extracts destination address(MAC) of input frame. */ @@ -321,7 +321,7 @@ static inline void llc_pdu_init_as_ui_cmd(struct sk_buff *skb) /** * llc_pdu_init_as_test_cmd - sets PDU as TEST - * @skb - Address of the skb to build + * @skb: Address of the skb to build * * Sets a PDU as TEST */ @@ -369,6 +369,8 @@ struct llc_xid_info { /** * llc_pdu_init_as_xid_cmd - sets bytes 3, 4 & 5 of LLC header as XID * @skb: input skb that header must be set into it. + * @svcs_supported: The class of the LLC (I or II) + * @rx_window: The size of the receive window of the LLC * * This function sets third,fourth,fifth and sixth bytes of LLC header as * a XID PDU. diff --git a/include/net/nsh.h b/include/net/nsh.h index 350b1ad11c7f..16a751093896 100644 --- a/include/net/nsh.h +++ b/include/net/nsh.h @@ -192,7 +192,7 @@ /** * struct nsh_md1_ctx - Keeps track of NSH context data - * @nshc<1-4>: NSH Contexts. + * @context: NSH Contexts. */ struct nsh_md1_ctx { __be32 context[4]; diff --git a/include/net/pie.h b/include/net/pie.h index 3fe2361e03b4..01cbc66825a4 100644 --- a/include/net/pie.h +++ b/include/net/pie.h @@ -17,7 +17,7 @@ /** * struct pie_params - contains pie parameters * @target: target delay in pschedtime - * @tudpate: interval at which drop probability is calculated + * @tupdate: interval at which drop probability is calculated * @limit: total number of packets that can be in the queue * @alpha: parameter to control drop probability * @beta: parameter to control drop probability diff --git a/include/net/rsi_91x.h b/include/net/rsi_91x.h index 040f07b47f1f..b2283762e446 100644 --- a/include/net/rsi_91x.h +++ b/include/net/rsi_91x.h @@ -1,4 +1,4 @@ -/** +/* * Copyright (c) 2017 Redpine Signals Inc. * * Permission to use, copy, modify, and/or distribute this software for any diff --git a/include/net/tcp.h b/include/net/tcp.h index 226bce6d1e8c..0ca972ebd3dd 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1509,25 +1509,38 @@ void tcp_leave_memory_pressure(struct sock *sk); static inline int keepalive_intvl_when(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); + int val; - return tp->keepalive_intvl ? : - READ_ONCE(net->ipv4.sysctl_tcp_keepalive_intvl); + /* Paired with WRITE_ONCE() in tcp_sock_set_keepintvl() + * and do_tcp_setsockopt(). + */ + val = READ_ONCE(tp->keepalive_intvl); + + return val ? : READ_ONCE(net->ipv4.sysctl_tcp_keepalive_intvl); } static inline int keepalive_time_when(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); + int val; - return tp->keepalive_time ? : - READ_ONCE(net->ipv4.sysctl_tcp_keepalive_time); + /* Paired with WRITE_ONCE() in tcp_sock_set_keepidle_locked() */ + val = READ_ONCE(tp->keepalive_time); + + return val ? : READ_ONCE(net->ipv4.sysctl_tcp_keepalive_time); } static inline int keepalive_probes(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); + int val; - return tp->keepalive_probes ? : - READ_ONCE(net->ipv4.sysctl_tcp_keepalive_probes); + /* Paired with WRITE_ONCE() in tcp_sock_set_keepcnt() + * and do_tcp_setsockopt(). + */ + val = READ_ONCE(tp->keepalive_probes); + + return val ? : READ_ONCE(net->ipv4.sysctl_tcp_keepalive_probes); } static inline u32 keepalive_time_elapsed(const struct tcp_sock *tp) @@ -2048,7 +2061,11 @@ void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr); static inline u32 tcp_notsent_lowat(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); - return tp->notsent_lowat ?: READ_ONCE(net->ipv4.sysctl_tcp_notsent_lowat); + u32 val; + + val = READ_ONCE(tp->notsent_lowat); + + return val ?: READ_ONCE(net->ipv4.sysctl_tcp_notsent_lowat); } bool tcp_stream_memory_free(const struct sock *sk, int wake); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 930b5555cfd3..02a021c524ab 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5573,16 +5573,17 @@ static int update_stack_depth(struct bpf_verifier_env *env, * Since recursion is prevented by check_cfg() this algorithm * only needs a local stack of MAX_CALL_FRAMES to remember callsites */ -static int check_max_stack_depth(struct bpf_verifier_env *env) +static int check_max_stack_depth_subprog(struct bpf_verifier_env *env, int idx) { - int depth = 0, frame = 0, idx = 0, i = 0, subprog_end; struct bpf_subprog_info *subprog = env->subprog_info; struct bpf_insn *insn = env->prog->insnsi; + int depth = 0, frame = 0, i, subprog_end; bool tail_call_reachable = false; int ret_insn[MAX_CALL_FRAMES]; int ret_prog[MAX_CALL_FRAMES]; int j; + i = subprog[idx].start; process_func: /* protect against potential stack overflow that might happen when * bpf2bpf calls get combined with tailcalls. Limit the caller's stack @@ -5621,7 +5622,7 @@ process_func: continue_func: subprog_end = subprog[idx + 1].start; for (; i < subprog_end; i++) { - int next_insn; + int next_insn, sidx; if (!bpf_pseudo_call(insn + i) && !bpf_pseudo_func(insn + i)) continue; @@ -5631,14 +5632,14 @@ continue_func: /* find the callee */ next_insn = i + insn[i].imm + 1; - idx = find_subprog(env, next_insn); - if (idx < 0) { + sidx = find_subprog(env, next_insn); + if (sidx < 0) { WARN_ONCE(1, "verifier bug. No program starts at insn %d\n", next_insn); return -EFAULT; } - if (subprog[idx].is_async_cb) { - if (subprog[idx].has_tail_call) { + if (subprog[sidx].is_async_cb) { + if (subprog[sidx].has_tail_call) { verbose(env, "verifier bug. subprog has tail_call and async cb\n"); return -EFAULT; } @@ -5647,6 +5648,7 @@ continue_func: continue; } i = next_insn; + idx = sidx; if (subprog[idx].has_tail_call) tail_call_reachable = true; @@ -5682,6 +5684,22 @@ continue_func: goto continue_func; } +static int check_max_stack_depth(struct bpf_verifier_env *env) +{ + struct bpf_subprog_info *si = env->subprog_info; + int ret; + + for (int i = 0; i < env->subprog_cnt; i++) { + if (!i || si[i].is_async_cb) { + ret = check_max_stack_depth_subprog(env, i); + if (ret < 0) + return ret; + } + continue; + } + return 0; +} + #ifndef CONFIG_BPF_JIT_ALWAYS_ON static int get_callee_stack_depth(struct bpf_verifier_env *env, const struct bpf_insn *insn, int idx) diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 056f9516e46d..76222565e2df 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -118,7 +118,7 @@ static void hci_connect_le_scan_cleanup(struct hci_conn *conn, u8 status) */ params->explicit_connect = false; - list_del_init(¶ms->action); + hci_pend_le_list_del_init(params); switch (params->auto_connect) { case HCI_AUTO_CONN_EXPLICIT: @@ -127,10 +127,10 @@ static void hci_connect_le_scan_cleanup(struct hci_conn *conn, u8 status) return; case HCI_AUTO_CONN_DIRECT: case HCI_AUTO_CONN_ALWAYS: - list_add(¶ms->action, &hdev->pend_le_conns); + hci_pend_le_list_add(params, &hdev->pend_le_conns); break; case HCI_AUTO_CONN_REPORT: - list_add(¶ms->action, &hdev->pend_le_reports); + hci_pend_le_list_add(params, &hdev->pend_le_reports); break; default: break; @@ -1426,8 +1426,8 @@ static int hci_explicit_conn_params_set(struct hci_dev *hdev, if (params->auto_connect == HCI_AUTO_CONN_DISABLED || params->auto_connect == HCI_AUTO_CONN_REPORT || params->auto_connect == HCI_AUTO_CONN_EXPLICIT) { - list_del_init(¶ms->action); - list_add(¶ms->action, &hdev->pend_le_conns); + hci_pend_le_list_del_init(params); + hci_pend_le_list_add(params, &hdev->pend_le_conns); } params->explicit_connect = true; @@ -1684,7 +1684,7 @@ struct hci_conn *hci_connect_sco(struct hci_dev *hdev, int type, bdaddr_t *dst, if (!link) { hci_conn_drop(acl); hci_conn_drop(sco); - return NULL; + return ERR_PTR(-ENOLINK); } sco->setting = setting; @@ -2254,7 +2254,7 @@ struct hci_conn *hci_connect_cis(struct hci_dev *hdev, bdaddr_t *dst, if (!link) { hci_conn_drop(le); hci_conn_drop(cis); - return NULL; + return ERR_PTR(-ENOLINK); } /* If LE is already connected and CIS handle is already set proceed to diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 48917c68358d..1ec83985f1ab 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -1972,6 +1972,7 @@ static int hci_remove_adv_monitor(struct hci_dev *hdev, struct adv_monitor *monitor) { int status = 0; + int handle; switch (hci_get_adv_monitor_offload_ext(hdev)) { case HCI_ADV_MONITOR_EXT_NONE: /* also goes here when powered off */ @@ -1980,9 +1981,10 @@ static int hci_remove_adv_monitor(struct hci_dev *hdev, goto free_monitor; case HCI_ADV_MONITOR_EXT_MSFT: + handle = monitor->handle; status = msft_remove_monitor(hdev, monitor); bt_dev_dbg(hdev, "%s remove monitor %d msft status %d", - hdev->name, monitor->handle, status); + hdev->name, handle, status); break; } @@ -2249,22 +2251,46 @@ struct hci_conn_params *hci_conn_params_lookup(struct hci_dev *hdev, return NULL; } -/* This function requires the caller holds hdev->lock */ +/* This function requires the caller holds hdev->lock or rcu_read_lock */ struct hci_conn_params *hci_pend_le_action_lookup(struct list_head *list, bdaddr_t *addr, u8 addr_type) { struct hci_conn_params *param; - list_for_each_entry(param, list, action) { + rcu_read_lock(); + + list_for_each_entry_rcu(param, list, action) { if (bacmp(¶m->addr, addr) == 0 && - param->addr_type == addr_type) + param->addr_type == addr_type) { + rcu_read_unlock(); return param; + } } + rcu_read_unlock(); + return NULL; } /* This function requires the caller holds hdev->lock */ +void hci_pend_le_list_del_init(struct hci_conn_params *param) +{ + if (list_empty(¶m->action)) + return; + + list_del_rcu(¶m->action); + synchronize_rcu(); + INIT_LIST_HEAD(¶m->action); +} + +/* This function requires the caller holds hdev->lock */ +void hci_pend_le_list_add(struct hci_conn_params *param, + struct list_head *list) +{ + list_add_rcu(¶m->action, list); +} + +/* This function requires the caller holds hdev->lock */ struct hci_conn_params *hci_conn_params_add(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type) { @@ -2297,14 +2323,15 @@ struct hci_conn_params *hci_conn_params_add(struct hci_dev *hdev, return params; } -static void hci_conn_params_free(struct hci_conn_params *params) +void hci_conn_params_free(struct hci_conn_params *params) { + hci_pend_le_list_del_init(params); + if (params->conn) { hci_conn_drop(params->conn); hci_conn_put(params->conn); } - list_del(¶ms->action); list_del(¶ms->list); kfree(params); } @@ -2342,8 +2369,7 @@ void hci_conn_params_clear_disabled(struct hci_dev *hdev) continue; } - list_del(¶ms->list); - kfree(params); + hci_conn_params_free(params); } BT_DBG("All LE disabled connection parameters were removed"); diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 95816a938cea..31ca320ce38d 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -1564,7 +1564,7 @@ static u8 hci_cc_le_set_privacy_mode(struct hci_dev *hdev, void *data, params = hci_conn_params_lookup(hdev, &cp->bdaddr, cp->bdaddr_type); if (params) - params->privacy_mode = cp->mode; + WRITE_ONCE(params->privacy_mode, cp->mode); hci_dev_unlock(hdev); @@ -2784,6 +2784,9 @@ static void hci_cs_disconnect(struct hci_dev *hdev, u8 status) hci_enable_advertising(hdev); } + /* Inform sockets conn is gone before we delete it */ + hci_disconn_cfm(conn, HCI_ERROR_UNSPECIFIED); + goto done; } @@ -2804,8 +2807,8 @@ static void hci_cs_disconnect(struct hci_dev *hdev, u8 status) case HCI_AUTO_CONN_DIRECT: case HCI_AUTO_CONN_ALWAYS: - list_del_init(¶ms->action); - list_add(¶ms->action, &hdev->pend_le_conns); + hci_pend_le_list_del_init(params); + hci_pend_le_list_add(params, &hdev->pend_le_conns); break; default: @@ -3423,8 +3426,8 @@ static void hci_disconn_complete_evt(struct hci_dev *hdev, void *data, case HCI_AUTO_CONN_DIRECT: case HCI_AUTO_CONN_ALWAYS: - list_del_init(¶ms->action); - list_add(¶ms->action, &hdev->pend_le_conns); + hci_pend_le_list_del_init(params); + hci_pend_le_list_add(params, &hdev->pend_le_conns); hci_update_passive_scan(hdev); break; @@ -5962,7 +5965,7 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, params = hci_pend_le_action_lookup(&hdev->pend_le_conns, &conn->dst, conn->dst_type); if (params) { - list_del_init(¶ms->action); + hci_pend_le_list_del_init(params); if (params->conn) { hci_conn_drop(params->conn); hci_conn_put(params->conn); diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 8561616abbe5..4d1e32bb6a9c 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -2160,15 +2160,23 @@ static int hci_le_del_accept_list_sync(struct hci_dev *hdev, return 0; } +struct conn_params { + bdaddr_t addr; + u8 addr_type; + hci_conn_flags_t flags; + u8 privacy_mode; +}; + /* Adds connection to resolve list if needed. * Setting params to NULL programs local hdev->irk */ static int hci_le_add_resolve_list_sync(struct hci_dev *hdev, - struct hci_conn_params *params) + struct conn_params *params) { struct hci_cp_le_add_to_resolv_list cp; struct smp_irk *irk; struct bdaddr_list_with_irk *entry; + struct hci_conn_params *p; if (!use_ll_privacy(hdev)) return 0; @@ -2203,6 +2211,16 @@ static int hci_le_add_resolve_list_sync(struct hci_dev *hdev, /* Default privacy mode is always Network */ params->privacy_mode = HCI_NETWORK_PRIVACY; + rcu_read_lock(); + p = hci_pend_le_action_lookup(&hdev->pend_le_conns, + ¶ms->addr, params->addr_type); + if (!p) + p = hci_pend_le_action_lookup(&hdev->pend_le_reports, + ¶ms->addr, params->addr_type); + if (p) + WRITE_ONCE(p->privacy_mode, HCI_NETWORK_PRIVACY); + rcu_read_unlock(); + done: if (hci_dev_test_flag(hdev, HCI_PRIVACY)) memcpy(cp.local_irk, hdev->irk, 16); @@ -2215,7 +2233,7 @@ done: /* Set Device Privacy Mode. */ static int hci_le_set_privacy_mode_sync(struct hci_dev *hdev, - struct hci_conn_params *params) + struct conn_params *params) { struct hci_cp_le_set_privacy_mode cp; struct smp_irk *irk; @@ -2240,6 +2258,8 @@ static int hci_le_set_privacy_mode_sync(struct hci_dev *hdev, bacpy(&cp.bdaddr, &irk->bdaddr); cp.mode = HCI_DEVICE_PRIVACY; + /* Note: params->privacy_mode is not updated since it is a copy */ + return __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_PRIVACY_MODE, sizeof(cp), &cp, HCI_CMD_TIMEOUT); } @@ -2249,7 +2269,7 @@ static int hci_le_set_privacy_mode_sync(struct hci_dev *hdev, * properly set the privacy mode. */ static int hci_le_add_accept_list_sync(struct hci_dev *hdev, - struct hci_conn_params *params, + struct conn_params *params, u8 *num_entries) { struct hci_cp_le_add_to_accept_list cp; @@ -2447,6 +2467,52 @@ struct sk_buff *hci_read_local_oob_data_sync(struct hci_dev *hdev, return __hci_cmd_sync_sk(hdev, opcode, 0, NULL, 0, HCI_CMD_TIMEOUT, sk); } +static struct conn_params *conn_params_copy(struct list_head *list, size_t *n) +{ + struct hci_conn_params *params; + struct conn_params *p; + size_t i; + + rcu_read_lock(); + + i = 0; + list_for_each_entry_rcu(params, list, action) + ++i; + *n = i; + + rcu_read_unlock(); + + p = kvcalloc(*n, sizeof(struct conn_params), GFP_KERNEL); + if (!p) + return NULL; + + rcu_read_lock(); + + i = 0; + list_for_each_entry_rcu(params, list, action) { + /* Racing adds are handled in next scan update */ + if (i >= *n) + break; + + /* No hdev->lock, but: addr, addr_type are immutable. + * privacy_mode is only written by us or in + * hci_cc_le_set_privacy_mode that we wait for. + * We should be idempotent so MGMT updating flags + * while we are processing is OK. + */ + bacpy(&p[i].addr, ¶ms->addr); + p[i].addr_type = params->addr_type; + p[i].flags = READ_ONCE(params->flags); + p[i].privacy_mode = READ_ONCE(params->privacy_mode); + ++i; + } + + rcu_read_unlock(); + + *n = i; + return p; +} + /* Device must not be scanning when updating the accept list. * * Update is done using the following sequence: @@ -2466,11 +2532,12 @@ struct sk_buff *hci_read_local_oob_data_sync(struct hci_dev *hdev, */ static u8 hci_update_accept_list_sync(struct hci_dev *hdev) { - struct hci_conn_params *params; + struct conn_params *params; struct bdaddr_list *b, *t; u8 num_entries = 0; bool pend_conn, pend_report; u8 filter_policy; + size_t i, n; int err; /* Pause advertising if resolving list can be used as controllers @@ -2504,6 +2571,7 @@ static u8 hci_update_accept_list_sync(struct hci_dev *hdev) if (hci_conn_hash_lookup_le(hdev, &b->bdaddr, b->bdaddr_type)) continue; + /* Pointers not dereferenced, no locks needed */ pend_conn = hci_pend_le_action_lookup(&hdev->pend_le_conns, &b->bdaddr, b->bdaddr_type); @@ -2532,23 +2600,50 @@ static u8 hci_update_accept_list_sync(struct hci_dev *hdev) * available accept list entries in the controller, then * just abort and return filer policy value to not use the * accept list. + * + * The list and params may be mutated while we wait for events, + * so make a copy and iterate it. */ - list_for_each_entry(params, &hdev->pend_le_conns, action) { - err = hci_le_add_accept_list_sync(hdev, params, &num_entries); - if (err) + + params = conn_params_copy(&hdev->pend_le_conns, &n); + if (!params) { + err = -ENOMEM; + goto done; + } + + for (i = 0; i < n; ++i) { + err = hci_le_add_accept_list_sync(hdev, ¶ms[i], + &num_entries); + if (err) { + kvfree(params); goto done; + } } + kvfree(params); + /* After adding all new pending connections, walk through * the list of pending reports and also add these to the * accept list if there is still space. Abort if space runs out. */ - list_for_each_entry(params, &hdev->pend_le_reports, action) { - err = hci_le_add_accept_list_sync(hdev, params, &num_entries); - if (err) + + params = conn_params_copy(&hdev->pend_le_reports, &n); + if (!params) { + err = -ENOMEM; + goto done; + } + + for (i = 0; i < n; ++i) { + err = hci_le_add_accept_list_sync(hdev, ¶ms[i], + &num_entries); + if (err) { + kvfree(params); goto done; + } } + kvfree(params); + /* Use the allowlist unless the following conditions are all true: * - We are not currently suspending * - There are 1 or more ADV monitors registered and it's not offloaded @@ -4837,12 +4932,12 @@ static void hci_pend_le_actions_clear(struct hci_dev *hdev) struct hci_conn_params *p; list_for_each_entry(p, &hdev->le_conn_params, list) { + hci_pend_le_list_del_init(p); if (p->conn) { hci_conn_drop(p->conn); hci_conn_put(p->conn); p->conn = NULL; } - list_del_init(&p->action); } BT_DBG("All LE pending actions cleared"); diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index 0e6cc57b3911..505d62247268 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -123,8 +123,11 @@ static struct iso_conn *iso_conn_add(struct hci_conn *hcon) { struct iso_conn *conn = hcon->iso_data; - if (conn) + if (conn) { + if (!conn->hcon) + conn->hcon = hcon; return conn; + } conn = kzalloc(sizeof(*conn), GFP_KERNEL); if (!conn) @@ -300,14 +303,13 @@ static int iso_connect_bis(struct sock *sk) goto unlock; } - hci_dev_unlock(hdev); - hci_dev_put(hdev); + lock_sock(sk); err = iso_chan_add(conn, sk, NULL); - if (err) - return err; - - lock_sock(sk); + if (err) { + release_sock(sk); + goto unlock; + } /* Update source addr of the socket */ bacpy(&iso_pi(sk)->src, &hcon->src); @@ -321,7 +323,6 @@ static int iso_connect_bis(struct sock *sk) } release_sock(sk); - return err; unlock: hci_dev_unlock(hdev); @@ -389,14 +390,13 @@ static int iso_connect_cis(struct sock *sk) goto unlock; } - hci_dev_unlock(hdev); - hci_dev_put(hdev); + lock_sock(sk); err = iso_chan_add(conn, sk, NULL); - if (err) - return err; - - lock_sock(sk); + if (err) { + release_sock(sk); + goto unlock; + } /* Update source addr of the socket */ bacpy(&iso_pi(sk)->src, &hcon->src); @@ -413,7 +413,6 @@ static int iso_connect_cis(struct sock *sk) } release_sock(sk); - return err; unlock: hci_dev_unlock(hdev); @@ -1072,8 +1071,8 @@ static int iso_sock_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; - struct iso_conn *conn = iso_pi(sk)->conn; struct sk_buff *skb, **frag; + size_t mtu; int err; BT_DBG("sock %p, sk %p", sock, sk); @@ -1085,11 +1084,18 @@ static int iso_sock_sendmsg(struct socket *sock, struct msghdr *msg, if (msg->msg_flags & MSG_OOB) return -EOPNOTSUPP; - if (sk->sk_state != BT_CONNECTED) + lock_sock(sk); + + if (sk->sk_state != BT_CONNECTED) { + release_sock(sk); return -ENOTCONN; + } + + mtu = iso_pi(sk)->conn->hcon->hdev->iso_mtu; + + release_sock(sk); - skb = bt_skb_sendmsg(sk, msg, len, conn->hcon->hdev->iso_mtu, - HCI_ISO_DATA_HDR_SIZE, 0); + skb = bt_skb_sendmsg(sk, msg, len, mtu, HCI_ISO_DATA_HDR_SIZE, 0); if (IS_ERR(skb)) return PTR_ERR(skb); @@ -1102,8 +1108,7 @@ static int iso_sock_sendmsg(struct socket *sock, struct msghdr *msg, while (len) { struct sk_buff *tmp; - tmp = bt_skb_sendmsg(sk, msg, len, conn->hcon->hdev->iso_mtu, - 0, 0); + tmp = bt_skb_sendmsg(sk, msg, len, mtu, 0, 0); if (IS_ERR(tmp)) { kfree_skb(skb); return PTR_ERR(tmp); @@ -1158,15 +1163,19 @@ static int iso_sock_recvmsg(struct socket *sock, struct msghdr *msg, BT_DBG("sk %p", sk); if (test_and_clear_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) { + lock_sock(sk); switch (sk->sk_state) { case BT_CONNECT2: - lock_sock(sk); iso_conn_defer_accept(pi->conn->hcon); sk->sk_state = BT_CONFIG; release_sock(sk); return 0; case BT_CONNECT: + release_sock(sk); return iso_connect_cis(sk); + default: + release_sock(sk); + break; } } diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index f7b2d0971f24..d4498037fadc 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -1297,15 +1297,15 @@ static void restart_le_actions(struct hci_dev *hdev) /* Needed for AUTO_OFF case where might not "really" * have been powered off. */ - list_del_init(&p->action); + hci_pend_le_list_del_init(p); switch (p->auto_connect) { case HCI_AUTO_CONN_DIRECT: case HCI_AUTO_CONN_ALWAYS: - list_add(&p->action, &hdev->pend_le_conns); + hci_pend_le_list_add(p, &hdev->pend_le_conns); break; case HCI_AUTO_CONN_REPORT: - list_add(&p->action, &hdev->pend_le_reports); + hci_pend_le_list_add(p, &hdev->pend_le_reports); break; default: break; @@ -5169,7 +5169,7 @@ static int set_device_flags(struct sock *sk, struct hci_dev *hdev, void *data, goto unlock; } - params->flags = current_flags; + WRITE_ONCE(params->flags, current_flags); status = MGMT_STATUS_SUCCESS; /* Update passive scan if HCI_CONN_FLAG_DEVICE_PRIVACY @@ -7285,7 +7285,7 @@ static void get_conn_info_complete(struct hci_dev *hdev, void *data, int err) bt_dev_dbg(hdev, "err %d", err); - memcpy(&rp.addr, &cp->addr.bdaddr, sizeof(rp.addr)); + memcpy(&rp.addr, &cp->addr, sizeof(rp.addr)); status = mgmt_status(err); if (status == MGMT_STATUS_SUCCESS) { @@ -7580,7 +7580,7 @@ static int hci_conn_params_set(struct hci_dev *hdev, bdaddr_t *addr, if (params->auto_connect == auto_connect) return 0; - list_del_init(¶ms->action); + hci_pend_le_list_del_init(params); switch (auto_connect) { case HCI_AUTO_CONN_DISABLED: @@ -7589,18 +7589,18 @@ static int hci_conn_params_set(struct hci_dev *hdev, bdaddr_t *addr, * connect to device, keep connecting. */ if (params->explicit_connect) - list_add(¶ms->action, &hdev->pend_le_conns); + hci_pend_le_list_add(params, &hdev->pend_le_conns); break; case HCI_AUTO_CONN_REPORT: if (params->explicit_connect) - list_add(¶ms->action, &hdev->pend_le_conns); + hci_pend_le_list_add(params, &hdev->pend_le_conns); else - list_add(¶ms->action, &hdev->pend_le_reports); + hci_pend_le_list_add(params, &hdev->pend_le_reports); break; case HCI_AUTO_CONN_DIRECT: case HCI_AUTO_CONN_ALWAYS: if (!is_connected(hdev, addr, addr_type)) - list_add(¶ms->action, &hdev->pend_le_conns); + hci_pend_le_list_add(params, &hdev->pend_le_conns); break; } @@ -7823,9 +7823,7 @@ static int remove_device(struct sock *sk, struct hci_dev *hdev, goto unlock; } - list_del(¶ms->action); - list_del(¶ms->list); - kfree(params); + hci_conn_params_free(params); device_removed(sk, hdev, &cp->addr.bdaddr, cp->addr.type); } else { @@ -7856,9 +7854,7 @@ static int remove_device(struct sock *sk, struct hci_dev *hdev, p->auto_connect = HCI_AUTO_CONN_EXPLICIT; continue; } - list_del(&p->action); - list_del(&p->list); - kfree(p); + hci_conn_params_free(p); } bt_dev_dbg(hdev, "All LE connection parameters were removed"); diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index cd1a27ac555d..7762604ddfc0 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -126,8 +126,11 @@ static struct sco_conn *sco_conn_add(struct hci_conn *hcon) struct hci_dev *hdev = hcon->hdev; struct sco_conn *conn = hcon->sco_data; - if (conn) + if (conn) { + if (!conn->hcon) + conn->hcon = hcon; return conn; + } conn = kzalloc(sizeof(struct sco_conn), GFP_KERNEL); if (!conn) @@ -268,21 +271,21 @@ static int sco_connect(struct sock *sk) goto unlock; } - hci_dev_unlock(hdev); - hci_dev_put(hdev); - conn = sco_conn_add(hcon); if (!conn) { hci_conn_drop(hcon); - return -ENOMEM; + err = -ENOMEM; + goto unlock; } - err = sco_chan_add(conn, sk, NULL); - if (err) - return err; - lock_sock(sk); + err = sco_chan_add(conn, sk, NULL); + if (err) { + release_sock(sk); + goto unlock; + } + /* Update source addr of the socket */ bacpy(&sco_pi(sk)->src, &hcon->src); @@ -296,8 +299,6 @@ static int sco_connect(struct sock *sk) release_sock(sk); - return err; - unlock: hci_dev_unlock(hdev); hci_dev_put(hdev); diff --git a/net/can/bcm.c b/net/can/bcm.c index 9ba35685b043..9168114fc87f 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -1526,6 +1526,12 @@ static int bcm_release(struct socket *sock) lock_sock(sk); +#if IS_ENABLED(CONFIG_PROC_FS) + /* remove procfs entry */ + if (net->can.bcmproc_dir && bo->bcm_proc_read) + remove_proc_entry(bo->procname, net->can.bcmproc_dir); +#endif /* CONFIG_PROC_FS */ + list_for_each_entry_safe(op, next, &bo->tx_ops, list) bcm_remove_op(op); @@ -1561,12 +1567,6 @@ static int bcm_release(struct socket *sock) list_for_each_entry_safe(op, next, &bo->rx_ops, list) bcm_remove_op(op); -#if IS_ENABLED(CONFIG_PROC_FS) - /* remove procfs entry */ - if (net->can.bcmproc_dir && bo->bcm_proc_read) - remove_proc_entry(bo->procname, net->can.bcmproc_dir); -#endif /* CONFIG_PROC_FS */ - /* remove device reference */ if (bo->bound) { bo->bound = 0; diff --git a/net/can/raw.c b/net/can/raw.c index 15c79b079184..2302e4882967 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -84,6 +84,7 @@ struct raw_sock { struct sock sk; int bound; int ifindex; + struct net_device *dev; struct list_head notifier; int loopback; int recv_own_msgs; @@ -277,7 +278,7 @@ static void raw_notify(struct raw_sock *ro, unsigned long msg, if (!net_eq(dev_net(dev), sock_net(sk))) return; - if (ro->ifindex != dev->ifindex) + if (ro->dev != dev) return; switch (msg) { @@ -292,6 +293,7 @@ static void raw_notify(struct raw_sock *ro, unsigned long msg, ro->ifindex = 0; ro->bound = 0; + ro->dev = NULL; ro->count = 0; release_sock(sk); @@ -337,6 +339,7 @@ static int raw_init(struct sock *sk) ro->bound = 0; ro->ifindex = 0; + ro->dev = NULL; /* set default filter to single entry dfilter */ ro->dfilter.can_id = 0; @@ -385,19 +388,13 @@ static int raw_release(struct socket *sock) lock_sock(sk); + rtnl_lock(); /* remove current filters & unregister */ if (ro->bound) { - if (ro->ifindex) { - struct net_device *dev; - - dev = dev_get_by_index(sock_net(sk), ro->ifindex); - if (dev) { - raw_disable_allfilters(dev_net(dev), dev, sk); - dev_put(dev); - } - } else { + if (ro->dev) + raw_disable_allfilters(dev_net(ro->dev), ro->dev, sk); + else raw_disable_allfilters(sock_net(sk), NULL, sk); - } } if (ro->count > 1) @@ -405,8 +402,10 @@ static int raw_release(struct socket *sock) ro->ifindex = 0; ro->bound = 0; + ro->dev = NULL; ro->count = 0; free_percpu(ro->uniq); + rtnl_unlock(); sock_orphan(sk); sock->sk = NULL; @@ -422,6 +421,7 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len) struct sockaddr_can *addr = (struct sockaddr_can *)uaddr; struct sock *sk = sock->sk; struct raw_sock *ro = raw_sk(sk); + struct net_device *dev = NULL; int ifindex; int err = 0; int notify_enetdown = 0; @@ -431,14 +431,13 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len) if (addr->can_family != AF_CAN) return -EINVAL; + rtnl_lock(); lock_sock(sk); if (ro->bound && addr->can_ifindex == ro->ifindex) goto out; if (addr->can_ifindex) { - struct net_device *dev; - dev = dev_get_by_index(sock_net(sk), addr->can_ifindex); if (!dev) { err = -ENODEV; @@ -467,26 +466,20 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len) if (!err) { if (ro->bound) { /* unregister old filters */ - if (ro->ifindex) { - struct net_device *dev; - - dev = dev_get_by_index(sock_net(sk), - ro->ifindex); - if (dev) { - raw_disable_allfilters(dev_net(dev), - dev, sk); - dev_put(dev); - } - } else { + if (ro->dev) + raw_disable_allfilters(dev_net(ro->dev), + ro->dev, sk); + else raw_disable_allfilters(sock_net(sk), NULL, sk); - } } ro->ifindex = ifindex; ro->bound = 1; + ro->dev = dev; } out: release_sock(sk); + rtnl_unlock(); if (notify_enetdown) { sk->sk_err = ENETDOWN; @@ -553,9 +546,9 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, rtnl_lock(); lock_sock(sk); - if (ro->bound && ro->ifindex) { - dev = dev_get_by_index(sock_net(sk), ro->ifindex); - if (!dev) { + dev = ro->dev; + if (ro->bound && dev) { + if (dev->reg_state != NETREG_REGISTERED) { if (count > 1) kfree(filter); err = -ENODEV; @@ -596,7 +589,6 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, ro->count = count; out_fil: - dev_put(dev); release_sock(sk); rtnl_unlock(); @@ -614,9 +606,9 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, rtnl_lock(); lock_sock(sk); - if (ro->bound && ro->ifindex) { - dev = dev_get_by_index(sock_net(sk), ro->ifindex); - if (!dev) { + dev = ro->dev; + if (ro->bound && dev) { + if (dev->reg_state != NETREG_REGISTERED) { err = -ENODEV; goto out_err; } @@ -640,7 +632,6 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, ro->err_mask = err_mask; out_err: - dev_put(dev); release_sock(sk); rtnl_unlock(); diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index ba06ed42e428..2be2d4922557 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -1132,7 +1132,7 @@ static int esp_init_authenc(struct xfrm_state *x, err = crypto_aead_setkey(aead, key, keylen); free_key: - kfree(key); + kfree_sensitive(key); error: return err; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 0cc19cfbb673..aeebe8816689 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -1019,7 +1019,7 @@ static void reqsk_timer_handler(struct timer_list *t) icsk = inet_csk(sk_listener); net = sock_net(sk_listener); - max_syn_ack_retries = icsk->icsk_syn_retries ? : + max_syn_ack_retries = READ_ONCE(icsk->icsk_syn_retries) ? : READ_ONCE(net->ipv4.sysctl_tcp_synack_retries); /* Normally all the openreqs are young and become mature * (i.e. converted to established socket) for first timeout. diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index e7391bf310a7..0819d6001b9a 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -650,20 +650,8 @@ bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk) spin_lock(lock); if (osk) { WARN_ON_ONCE(sk->sk_hash != osk->sk_hash); - ret = sk_hashed(osk); - if (ret) { - /* Before deleting the node, we insert a new one to make - * sure that the look-up-sk process would not miss either - * of them and that at least one node would exist in ehash - * table all the time. Otherwise there's a tiny chance - * that lookup process could find nothing in ehash table. - */ - __sk_nulls_add_node_tail_rcu(sk, list); - sk_nulls_del_node_init_rcu(osk); - } - goto unlock; - } - if (found_dup_sk) { + ret = sk_nulls_del_node_init_rcu(osk); + } else if (found_dup_sk) { *found_dup_sk = inet_ehash_lookup_by_sk(sk, list); if (*found_dup_sk) ret = false; @@ -672,7 +660,6 @@ bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk) if (ret) __sk_nulls_add_node_rcu(sk, list); -unlock: spin_unlock(lock); return ret; diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 40052414c7c7..2c1b245dba8e 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -88,10 +88,10 @@ void inet_twsk_put(struct inet_timewait_sock *tw) } EXPORT_SYMBOL_GPL(inet_twsk_put); -static void inet_twsk_add_node_tail_rcu(struct inet_timewait_sock *tw, - struct hlist_nulls_head *list) +static void inet_twsk_add_node_rcu(struct inet_timewait_sock *tw, + struct hlist_nulls_head *list) { - hlist_nulls_add_tail_rcu(&tw->tw_node, list); + hlist_nulls_add_head_rcu(&tw->tw_node, list); } static void inet_twsk_add_bind_node(struct inet_timewait_sock *tw, @@ -144,7 +144,7 @@ void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, spin_lock(lock); - inet_twsk_add_node_tail_rcu(tw, &ehead->chain); + inet_twsk_add_node_rcu(tw, &ehead->chain); /* Step 3: Remove SK from hash chain */ if (__sk_nulls_del_node_init_rcu(sk)) diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 81a1cce1a7d1..22a26d1d29a0 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -548,7 +548,8 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) goto err_free_skb; if (skb->len > dev->mtu + dev->hard_header_len) { - pskb_trim(skb, dev->mtu + dev->hard_header_len); + if (pskb_trim(skb, dev->mtu + dev->hard_header_len)) + goto err_free_skb; truncate = true; } @@ -689,7 +690,8 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb, goto free_skb; if (skb->len > dev->mtu + dev->hard_header_len) { - pskb_trim(skb, dev->mtu + dev->hard_header_len); + if (pskb_trim(skb, dev->mtu + dev->hard_header_len)) + goto free_skb; truncate = true; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index e03e08745308..8ed52e1e3c99 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3291,7 +3291,7 @@ int tcp_sock_set_syncnt(struct sock *sk, int val) return -EINVAL; lock_sock(sk); - inet_csk(sk)->icsk_syn_retries = val; + WRITE_ONCE(inet_csk(sk)->icsk_syn_retries, val); release_sock(sk); return 0; } @@ -3300,7 +3300,7 @@ EXPORT_SYMBOL(tcp_sock_set_syncnt); void tcp_sock_set_user_timeout(struct sock *sk, u32 val) { lock_sock(sk); - inet_csk(sk)->icsk_user_timeout = val; + WRITE_ONCE(inet_csk(sk)->icsk_user_timeout, val); release_sock(sk); } EXPORT_SYMBOL(tcp_sock_set_user_timeout); @@ -3312,7 +3312,8 @@ int tcp_sock_set_keepidle_locked(struct sock *sk, int val) if (val < 1 || val > MAX_TCP_KEEPIDLE) return -EINVAL; - tp->keepalive_time = val * HZ; + /* Paired with WRITE_ONCE() in keepalive_time_when() */ + WRITE_ONCE(tp->keepalive_time, val * HZ); if (sock_flag(sk, SOCK_KEEPOPEN) && !((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) { u32 elapsed = keepalive_time_elapsed(tp); @@ -3344,7 +3345,7 @@ int tcp_sock_set_keepintvl(struct sock *sk, int val) return -EINVAL; lock_sock(sk); - tcp_sk(sk)->keepalive_intvl = val * HZ; + WRITE_ONCE(tcp_sk(sk)->keepalive_intvl, val * HZ); release_sock(sk); return 0; } @@ -3356,7 +3357,8 @@ int tcp_sock_set_keepcnt(struct sock *sk, int val) return -EINVAL; lock_sock(sk); - tcp_sk(sk)->keepalive_probes = val; + /* Paired with READ_ONCE() in keepalive_probes() */ + WRITE_ONCE(tcp_sk(sk)->keepalive_probes, val); release_sock(sk); return 0; } @@ -3558,19 +3560,19 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, if (val < 1 || val > MAX_TCP_KEEPINTVL) err = -EINVAL; else - tp->keepalive_intvl = val * HZ; + WRITE_ONCE(tp->keepalive_intvl, val * HZ); break; case TCP_KEEPCNT: if (val < 1 || val > MAX_TCP_KEEPCNT) err = -EINVAL; else - tp->keepalive_probes = val; + WRITE_ONCE(tp->keepalive_probes, val); break; case TCP_SYNCNT: if (val < 1 || val > MAX_TCP_SYNCNT) err = -EINVAL; else - icsk->icsk_syn_retries = val; + WRITE_ONCE(icsk->icsk_syn_retries, val); break; case TCP_SAVE_SYN: @@ -3583,18 +3585,18 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, case TCP_LINGER2: if (val < 0) - tp->linger2 = -1; + WRITE_ONCE(tp->linger2, -1); else if (val > TCP_FIN_TIMEOUT_MAX / HZ) - tp->linger2 = TCP_FIN_TIMEOUT_MAX; + WRITE_ONCE(tp->linger2, TCP_FIN_TIMEOUT_MAX); else - tp->linger2 = val * HZ; + WRITE_ONCE(tp->linger2, val * HZ); break; case TCP_DEFER_ACCEPT: /* Translate value in seconds to number of retransmits */ - icsk->icsk_accept_queue.rskq_defer_accept = - secs_to_retrans(val, TCP_TIMEOUT_INIT / HZ, - TCP_RTO_MAX / HZ); + WRITE_ONCE(icsk->icsk_accept_queue.rskq_defer_accept, + secs_to_retrans(val, TCP_TIMEOUT_INIT / HZ, + TCP_RTO_MAX / HZ)); break; case TCP_WINDOW_CLAMP: @@ -3618,7 +3620,7 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, if (val < 0) err = -EINVAL; else - icsk->icsk_user_timeout = val; + WRITE_ONCE(icsk->icsk_user_timeout, val); break; case TCP_FASTOPEN: @@ -3656,13 +3658,13 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, if (!tp->repair) err = -EPERM; else - tp->tsoffset = val - tcp_time_stamp_raw(); + WRITE_ONCE(tp->tsoffset, val - tcp_time_stamp_raw()); break; case TCP_REPAIR_WINDOW: err = tcp_repair_set_window(tp, optval, optlen); break; case TCP_NOTSENT_LOWAT: - tp->notsent_lowat = val; + WRITE_ONCE(tp->notsent_lowat, val); sk->sk_write_space(sk); break; case TCP_INQ: @@ -3674,7 +3676,7 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, case TCP_TX_DELAY: if (val) tcp_enable_tx_delay(); - tp->tcp_tx_delay = val; + WRITE_ONCE(tp->tcp_tx_delay, val); break; default: err = -ENOPROTOOPT; @@ -3991,17 +3993,18 @@ int do_tcp_getsockopt(struct sock *sk, int level, val = keepalive_probes(tp); break; case TCP_SYNCNT: - val = icsk->icsk_syn_retries ? : + val = READ_ONCE(icsk->icsk_syn_retries) ? : READ_ONCE(net->ipv4.sysctl_tcp_syn_retries); break; case TCP_LINGER2: - val = tp->linger2; + val = READ_ONCE(tp->linger2); if (val >= 0) val = (val ? : READ_ONCE(net->ipv4.sysctl_tcp_fin_timeout)) / HZ; break; case TCP_DEFER_ACCEPT: - val = retrans_to_secs(icsk->icsk_accept_queue.rskq_defer_accept, - TCP_TIMEOUT_INIT / HZ, TCP_RTO_MAX / HZ); + val = READ_ONCE(icsk->icsk_accept_queue.rskq_defer_accept); + val = retrans_to_secs(val, TCP_TIMEOUT_INIT / HZ, + TCP_RTO_MAX / HZ); break; case TCP_WINDOW_CLAMP: val = tp->window_clamp; @@ -4138,11 +4141,11 @@ int do_tcp_getsockopt(struct sock *sk, int level, break; case TCP_USER_TIMEOUT: - val = icsk->icsk_user_timeout; + val = READ_ONCE(icsk->icsk_user_timeout); break; case TCP_FASTOPEN: - val = icsk->icsk_accept_queue.fastopenq.max_qlen; + val = READ_ONCE(icsk->icsk_accept_queue.fastopenq.max_qlen); break; case TCP_FASTOPEN_CONNECT: @@ -4154,14 +4157,14 @@ int do_tcp_getsockopt(struct sock *sk, int level, break; case TCP_TX_DELAY: - val = tp->tcp_tx_delay; + val = READ_ONCE(tp->tcp_tx_delay); break; case TCP_TIMESTAMP: - val = tcp_time_stamp_raw() + tp->tsoffset; + val = tcp_time_stamp_raw() + READ_ONCE(tp->tsoffset); break; case TCP_NOTSENT_LOWAT: - val = tp->notsent_lowat; + val = READ_ONCE(tp->notsent_lowat); break; case TCP_INQ: val = tp->recvmsg_inq; diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 45cc7f1ca296..85e4953f1182 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -296,6 +296,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk, static bool tcp_fastopen_queue_check(struct sock *sk) { struct fastopen_queue *fastopenq; + int max_qlen; /* Make sure the listener has enabled fastopen, and we don't * exceed the max # of pending TFO requests allowed before trying @@ -308,10 +309,11 @@ static bool tcp_fastopen_queue_check(struct sock *sk) * temporarily vs a server not supporting Fast Open at all. */ fastopenq = &inet_csk(sk)->icsk_accept_queue.fastopenq; - if (fastopenq->max_qlen == 0) + max_qlen = READ_ONCE(fastopenq->max_qlen); + if (max_qlen == 0) return false; - if (fastopenq->qlen >= fastopenq->max_qlen) { + if (fastopenq->qlen >= max_qlen) { struct request_sock *req1; spin_lock(&fastopenq->lock); req1 = fastopenq->rskq_rst_head; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index fd365de4d5ff..069642014636 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -307,8 +307,9 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) inet->inet_daddr, inet->inet_sport, usin->sin_port)); - tp->tsoffset = secure_tcp_ts_off(net, inet->inet_saddr, - inet->inet_daddr); + WRITE_ONCE(tp->tsoffset, + secure_tcp_ts_off(net, inet->inet_saddr, + inet->inet_daddr)); } inet->inet_id = get_random_u16(); @@ -988,11 +989,12 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, tcp_time_stamp_raw() + tcp_rsk(req)->ts_off, - req->ts_recent, + READ_ONCE(req->ts_recent), 0, tcp_md5_do_lookup(sk, l3index, addr, AF_INET), inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0, - ip_hdr(skb)->tos, tcp_rsk(req)->txhash); + ip_hdr(skb)->tos, + READ_ONCE(tcp_rsk(req)->txhash)); } /* diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 04fc328727e6..c8f2aa003387 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -528,7 +528,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newicsk->icsk_ack.lrcvtime = tcp_jiffies32; newtp->lsndtime = tcp_jiffies32; - newsk->sk_txhash = treq->txhash; + newsk->sk_txhash = READ_ONCE(treq->txhash); newtp->total_retrans = req->num_retrans; tcp_init_xmit_timers(newsk); @@ -555,7 +555,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->max_window = newtp->snd_wnd; if (newtp->rx_opt.tstamp_ok) { - newtp->rx_opt.ts_recent = req->ts_recent; + newtp->rx_opt.ts_recent = READ_ONCE(req->ts_recent); newtp->rx_opt.ts_recent_stamp = ktime_get_seconds(); newtp->tcp_header_len = sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED; } else { @@ -619,7 +619,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, tcp_parse_options(sock_net(sk), skb, &tmp_opt, 0, NULL); if (tmp_opt.saw_tstamp) { - tmp_opt.ts_recent = req->ts_recent; + tmp_opt.ts_recent = READ_ONCE(req->ts_recent); if (tmp_opt.rcv_tsecr) tmp_opt.rcv_tsecr -= tcp_rsk(req)->ts_off; /* We do not store true stamp, but it is not required, @@ -758,8 +758,11 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, /* In sequence, PAWS is OK. */ + /* TODO: We probably should defer ts_recent change once + * we take ownership of @req. + */ if (tmp_opt.saw_tstamp && !after(TCP_SKB_CB(skb)->seq, tcp_rsk(req)->rcv_nxt)) - req->ts_recent = tmp_opt.rcv_tsval; + WRITE_ONCE(req->ts_recent, tmp_opt.rcv_tsval); if (TCP_SKB_CB(skb)->seq == tcp_rsk(req)->rcv_isn) { /* Truncate SYN, it is out of window starting diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 2cb39b6dad02..51d8638d4b4c 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -878,7 +878,7 @@ static unsigned int tcp_synack_options(const struct sock *sk, if (likely(ireq->tstamp_ok)) { opts->options |= OPTION_TS; opts->tsval = tcp_skb_timestamp(skb) + tcp_rsk(req)->ts_off; - opts->tsecr = req->ts_recent; + opts->tsecr = READ_ONCE(req->ts_recent); remaining -= TCPOLEN_TSTAMP_ALIGNED; } if (likely(ireq->sack_ok)) { @@ -3660,7 +3660,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, rcu_read_lock(); md5 = tcp_rsk(req)->af_specific->req_md5_lookup(sk, req_to_sk(req)); #endif - skb_set_hash(skb, tcp_rsk(req)->txhash, PKT_HASH_TYPE_L4); + skb_set_hash(skb, READ_ONCE(tcp_rsk(req)->txhash), PKT_HASH_TYPE_L4); /* bpf program will be interested in the tcp_flags */ TCP_SKB_CB(skb)->tcp_flags = TCPHDR_SYN | TCPHDR_ACK; tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, md5, @@ -4210,7 +4210,7 @@ int tcp_rtx_synack(const struct sock *sk, struct request_sock *req) /* Paired with WRITE_ONCE() in sock_setsockopt() */ if (READ_ONCE(sk->sk_txrehash) == SOCK_TXREHASH_ENABLED) - tcp_rsk(req)->txhash = net_tx_rndhash(); + WRITE_ONCE(tcp_rsk(req)->txhash, net_tx_rndhash()); res = af_ops->send_synack(sk, NULL, &fl, req, NULL, TCP_SYNACK_NORMAL, NULL); if (!res) { diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 75aa4de5b731..f402946da344 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -274,13 +274,20 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, __sum16 check; __be16 newlen; - if (skb_shinfo(gso_skb)->gso_type & SKB_GSO_FRAGLIST) - return __udp_gso_segment_list(gso_skb, features, is_ipv6); - mss = skb_shinfo(gso_skb)->gso_size; if (gso_skb->len <= sizeof(*uh) + mss) return ERR_PTR(-EINVAL); + if (skb_gso_ok(gso_skb, features | NETIF_F_GSO_ROBUST)) { + /* Packet is from an untrusted source, reset gso_segs. */ + skb_shinfo(gso_skb)->gso_segs = DIV_ROUND_UP(gso_skb->len - sizeof(*uh), + mss); + return NULL; + } + + if (skb_shinfo(gso_skb)->gso_type & SKB_GSO_FRAGLIST) + return __udp_gso_segment_list(gso_skb, features, is_ipv6); + skb_pull(gso_skb, sizeof(*uh)); /* clear destructor to avoid skb_segment assigning it to tail */ @@ -388,8 +395,7 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, if (!pskb_may_pull(skb, sizeof(struct udphdr))) goto out; - if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4 && - !skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) + if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) return __udp_gso_segment(skb, features, false); mss = skb_shinfo(skb)->gso_size; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index da80974ad23a..070d87abf7c0 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -955,7 +955,8 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, goto tx_err; if (skb->len > dev->mtu + dev->hard_header_len) { - pskb_trim(skb, dev->mtu + dev->hard_header_len); + if (pskb_trim(skb, dev->mtu + dev->hard_header_len)) + goto tx_err; truncate = true; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 40dd92a2f480..4714eb695913 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1126,10 +1126,10 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, tcp_time_stamp_raw() + tcp_rsk(req)->ts_off, - req->ts_recent, sk->sk_bound_dev_if, + READ_ONCE(req->ts_recent), sk->sk_bound_dev_if, tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr, l3index), ipv6_get_dsfield(ipv6_hdr(skb)), 0, sk->sk_priority, - tcp_rsk(req)->txhash); + READ_ONCE(tcp_rsk(req)->txhash)); } diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index ad3b8726873e..09fa7a42cb93 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -43,8 +43,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, if (!pskb_may_pull(skb, sizeof(struct udphdr))) goto out; - if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4 && - !skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) + if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) return __udp_gso_segment(skb, features, true); mss = skb_shinfo(skb)->gso_size; diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 57c35c960b2c..9b06c380866b 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -402,7 +402,7 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen) memcpy(laddr.mac, addr->sllc_mac, IFHWADDRLEN); laddr.lsap = addr->sllc_sap; rc = -EADDRINUSE; /* mac + sap clash. */ - ask = llc_lookup_established(sap, &daddr, &laddr); + ask = llc_lookup_established(sap, &daddr, &laddr, &init_net); if (ask) { sock_put(ask); goto out_put; diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c index 912aa9bd5e29..d037009ee10f 100644 --- a/net/llc/llc_conn.c +++ b/net/llc/llc_conn.c @@ -453,11 +453,13 @@ static int llc_exec_conn_trans_actions(struct sock *sk, static inline bool llc_estab_match(const struct llc_sap *sap, const struct llc_addr *daddr, const struct llc_addr *laddr, - const struct sock *sk) + const struct sock *sk, + const struct net *net) { struct llc_sock *llc = llc_sk(sk); - return llc->laddr.lsap == laddr->lsap && + return net_eq(sock_net(sk), net) && + llc->laddr.lsap == laddr->lsap && llc->daddr.lsap == daddr->lsap && ether_addr_equal(llc->laddr.mac, laddr->mac) && ether_addr_equal(llc->daddr.mac, daddr->mac); @@ -468,6 +470,7 @@ static inline bool llc_estab_match(const struct llc_sap *sap, * @sap: SAP * @daddr: address of remote LLC (MAC + SAP) * @laddr: address of local LLC (MAC + SAP) + * @net: netns to look up a socket in * * Search connection list of the SAP and finds connection using the remote * mac, remote sap, local mac, and local sap. Returns pointer for @@ -476,7 +479,8 @@ static inline bool llc_estab_match(const struct llc_sap *sap, */ static struct sock *__llc_lookup_established(struct llc_sap *sap, struct llc_addr *daddr, - struct llc_addr *laddr) + struct llc_addr *laddr, + const struct net *net) { struct sock *rc; struct hlist_nulls_node *node; @@ -486,12 +490,12 @@ static struct sock *__llc_lookup_established(struct llc_sap *sap, rcu_read_lock(); again: sk_nulls_for_each_rcu(rc, node, laddr_hb) { - if (llc_estab_match(sap, daddr, laddr, rc)) { + if (llc_estab_match(sap, daddr, laddr, rc, net)) { /* Extra checks required by SLAB_TYPESAFE_BY_RCU */ if (unlikely(!refcount_inc_not_zero(&rc->sk_refcnt))) goto again; if (unlikely(llc_sk(rc)->sap != sap || - !llc_estab_match(sap, daddr, laddr, rc))) { + !llc_estab_match(sap, daddr, laddr, rc, net))) { sock_put(rc); continue; } @@ -513,29 +517,33 @@ found: struct sock *llc_lookup_established(struct llc_sap *sap, struct llc_addr *daddr, - struct llc_addr *laddr) + struct llc_addr *laddr, + const struct net *net) { struct sock *sk; local_bh_disable(); - sk = __llc_lookup_established(sap, daddr, laddr); + sk = __llc_lookup_established(sap, daddr, laddr, net); local_bh_enable(); return sk; } static inline bool llc_listener_match(const struct llc_sap *sap, const struct llc_addr *laddr, - const struct sock *sk) + const struct sock *sk, + const struct net *net) { struct llc_sock *llc = llc_sk(sk); - return sk->sk_type == SOCK_STREAM && sk->sk_state == TCP_LISTEN && + return net_eq(sock_net(sk), net) && + sk->sk_type == SOCK_STREAM && sk->sk_state == TCP_LISTEN && llc->laddr.lsap == laddr->lsap && ether_addr_equal(llc->laddr.mac, laddr->mac); } static struct sock *__llc_lookup_listener(struct llc_sap *sap, - struct llc_addr *laddr) + struct llc_addr *laddr, + const struct net *net) { struct sock *rc; struct hlist_nulls_node *node; @@ -545,12 +553,12 @@ static struct sock *__llc_lookup_listener(struct llc_sap *sap, rcu_read_lock(); again: sk_nulls_for_each_rcu(rc, node, laddr_hb) { - if (llc_listener_match(sap, laddr, rc)) { + if (llc_listener_match(sap, laddr, rc, net)) { /* Extra checks required by SLAB_TYPESAFE_BY_RCU */ if (unlikely(!refcount_inc_not_zero(&rc->sk_refcnt))) goto again; if (unlikely(llc_sk(rc)->sap != sap || - !llc_listener_match(sap, laddr, rc))) { + !llc_listener_match(sap, laddr, rc, net))) { sock_put(rc); continue; } @@ -574,6 +582,7 @@ found: * llc_lookup_listener - Finds listener for local MAC + SAP * @sap: SAP * @laddr: address of local LLC (MAC + SAP) + * @net: netns to look up a socket in * * Search connection list of the SAP and finds connection listening on * local mac, and local sap. Returns pointer for parent socket found, @@ -581,24 +590,26 @@ found: * Caller has to make sure local_bh is disabled. */ static struct sock *llc_lookup_listener(struct llc_sap *sap, - struct llc_addr *laddr) + struct llc_addr *laddr, + const struct net *net) { + struct sock *rc = __llc_lookup_listener(sap, laddr, net); static struct llc_addr null_addr; - struct sock *rc = __llc_lookup_listener(sap, laddr); if (!rc) - rc = __llc_lookup_listener(sap, &null_addr); + rc = __llc_lookup_listener(sap, &null_addr, net); return rc; } static struct sock *__llc_lookup(struct llc_sap *sap, struct llc_addr *daddr, - struct llc_addr *laddr) + struct llc_addr *laddr, + const struct net *net) { - struct sock *sk = __llc_lookup_established(sap, daddr, laddr); + struct sock *sk = __llc_lookup_established(sap, daddr, laddr, net); - return sk ? : llc_lookup_listener(sap, laddr); + return sk ? : llc_lookup_listener(sap, laddr, net); } /** @@ -776,7 +787,7 @@ void llc_conn_handler(struct llc_sap *sap, struct sk_buff *skb) llc_pdu_decode_da(skb, daddr.mac); llc_pdu_decode_dsap(skb, &daddr.lsap); - sk = __llc_lookup(sap, &saddr, &daddr); + sk = __llc_lookup(sap, &saddr, &daddr, dev_net(skb->dev)); if (!sk) goto drop; diff --git a/net/llc/llc_if.c b/net/llc/llc_if.c index dde9bf08a593..58a5f419adc6 100644 --- a/net/llc/llc_if.c +++ b/net/llc/llc_if.c @@ -92,7 +92,7 @@ int llc_establish_connection(struct sock *sk, const u8 *lmac, u8 *dmac, u8 dsap) daddr.lsap = dsap; memcpy(daddr.mac, dmac, sizeof(daddr.mac)); memcpy(laddr.mac, lmac, sizeof(laddr.mac)); - existing = llc_lookup_established(llc->sap, &daddr, &laddr); + existing = llc_lookup_established(llc->sap, &daddr, &laddr, sock_net(sk)); if (existing) { if (existing->sk_state == TCP_ESTABLISHED) { sk = existing; diff --git a/net/llc/llc_input.c b/net/llc/llc_input.c index c309b72a5877..7cac441862e2 100644 --- a/net/llc/llc_input.c +++ b/net/llc/llc_input.c @@ -163,9 +163,6 @@ int llc_rcv(struct sk_buff *skb, struct net_device *dev, void (*sta_handler)(struct sk_buff *skb); void (*sap_handler)(struct llc_sap *sap, struct sk_buff *skb); - if (!net_eq(dev_net(dev), &init_net)) - goto drop; - /* * When the interface is in promisc. mode, drop all the crap that it * receives, do not try to analyse it. diff --git a/net/llc/llc_sap.c b/net/llc/llc_sap.c index 6805ce43a055..116c0e479183 100644 --- a/net/llc/llc_sap.c +++ b/net/llc/llc_sap.c @@ -294,25 +294,29 @@ static void llc_sap_rcv(struct llc_sap *sap, struct sk_buff *skb, static inline bool llc_dgram_match(const struct llc_sap *sap, const struct llc_addr *laddr, - const struct sock *sk) + const struct sock *sk, + const struct net *net) { struct llc_sock *llc = llc_sk(sk); return sk->sk_type == SOCK_DGRAM && - llc->laddr.lsap == laddr->lsap && - ether_addr_equal(llc->laddr.mac, laddr->mac); + net_eq(sock_net(sk), net) && + llc->laddr.lsap == laddr->lsap && + ether_addr_equal(llc->laddr.mac, laddr->mac); } /** * llc_lookup_dgram - Finds dgram socket for the local sap/mac * @sap: SAP * @laddr: address of local LLC (MAC + SAP) + * @net: netns to look up a socket in * * Search socket list of the SAP and finds connection using the local * mac, and local sap. Returns pointer for socket found, %NULL otherwise. */ static struct sock *llc_lookup_dgram(struct llc_sap *sap, - const struct llc_addr *laddr) + const struct llc_addr *laddr, + const struct net *net) { struct sock *rc; struct hlist_nulls_node *node; @@ -322,12 +326,12 @@ static struct sock *llc_lookup_dgram(struct llc_sap *sap, rcu_read_lock_bh(); again: sk_nulls_for_each_rcu(rc, node, laddr_hb) { - if (llc_dgram_match(sap, laddr, rc)) { + if (llc_dgram_match(sap, laddr, rc, net)) { /* Extra checks required by SLAB_TYPESAFE_BY_RCU */ if (unlikely(!refcount_inc_not_zero(&rc->sk_refcnt))) goto again; if (unlikely(llc_sk(rc)->sap != sap || - !llc_dgram_match(sap, laddr, rc))) { + !llc_dgram_match(sap, laddr, rc, net))) { sock_put(rc); continue; } @@ -429,7 +433,7 @@ void llc_sap_handler(struct llc_sap *sap, struct sk_buff *skb) llc_sap_mcast(sap, &laddr, skb); kfree_skb(skb); } else { - struct sock *sk = llc_lookup_dgram(sap, &laddr); + struct sock *sk = llc_lookup_dgram(sap, &laddr, dev_net(skb->dev)); if (sk) { llc_sap_rcv(sap, skb, sk); sock_put(sk); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 237f739da3ca..b9a4d3fd1d34 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -3685,8 +3685,6 @@ int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain) if (err < 0) return err; } - - cond_resched(); } return 0; @@ -3710,6 +3708,8 @@ static int nft_table_validate(struct net *net, const struct nft_table *table) err = nft_chain_validate(&ctx, chain); if (err < 0) return err; + + cond_resched(); } return 0; @@ -4087,6 +4087,8 @@ static int nf_tables_delrule(struct sk_buff *skb, const struct nfnl_info *info, list_for_each_entry(chain, &table->chains, list) { if (!nft_is_active_next(net, chain)) continue; + if (nft_chain_is_bound(chain)) + continue; ctx.chain = chain; err = nft_delrule_by_chain(&ctx); @@ -10517,6 +10519,9 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, if (!tb[NFTA_VERDICT_CODE]) return -EINVAL; + + /* zero padding hole for memcmp */ + memset(data, 0, sizeof(*data)); data->verdict.code = ntohl(nla_get_be32(tb[NFTA_VERDICT_CODE])); switch (data->verdict.code) { @@ -10799,6 +10804,9 @@ static void __nft_release_table(struct net *net, struct nft_table *table) ctx.family = table->family; ctx.table = table; list_for_each_entry(chain, &table->chains, list) { + if (nft_chain_is_bound(chain)) + continue; + ctx.chain = chain; list_for_each_entry_safe(rule, nr, &chain->rules, list) { list_del(&rule->list); diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index db526cb7a485..49915a2a58eb 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1929,7 +1929,11 @@ static void nft_pipapo_remove(const struct net *net, const struct nft_set *set, int i, start, rules_fx; match_start = data; - match_end = (const u8 *)nft_set_ext_key_end(&e->ext)->data; + + if (nft_set_ext_exists(&e->ext, NFT_SET_EXT_KEY_END)) + match_end = (const u8 *)nft_set_ext_key_end(&e->ext)->data; + else + match_end = data; start = first_rule; rules_fx = rules_f0; diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 466c26df853a..382c7a71f81f 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -406,56 +406,6 @@ static int cls_bpf_prog_from_efd(struct nlattr **tb, struct cls_bpf_prog *prog, return 0; } -static int cls_bpf_set_parms(struct net *net, struct tcf_proto *tp, - struct cls_bpf_prog *prog, unsigned long base, - struct nlattr **tb, struct nlattr *est, u32 flags, - struct netlink_ext_ack *extack) -{ - bool is_bpf, is_ebpf, have_exts = false; - u32 gen_flags = 0; - int ret; - - is_bpf = tb[TCA_BPF_OPS_LEN] && tb[TCA_BPF_OPS]; - is_ebpf = tb[TCA_BPF_FD]; - if ((!is_bpf && !is_ebpf) || (is_bpf && is_ebpf)) - return -EINVAL; - - ret = tcf_exts_validate(net, tp, tb, est, &prog->exts, flags, - extack); - if (ret < 0) - return ret; - - if (tb[TCA_BPF_FLAGS]) { - u32 bpf_flags = nla_get_u32(tb[TCA_BPF_FLAGS]); - - if (bpf_flags & ~TCA_BPF_FLAG_ACT_DIRECT) - return -EINVAL; - - have_exts = bpf_flags & TCA_BPF_FLAG_ACT_DIRECT; - } - if (tb[TCA_BPF_FLAGS_GEN]) { - gen_flags = nla_get_u32(tb[TCA_BPF_FLAGS_GEN]); - if (gen_flags & ~CLS_BPF_SUPPORTED_GEN_FLAGS || - !tc_flags_valid(gen_flags)) - return -EINVAL; - } - - prog->exts_integrated = have_exts; - prog->gen_flags = gen_flags; - - ret = is_bpf ? cls_bpf_prog_from_ops(tb, prog) : - cls_bpf_prog_from_efd(tb, prog, gen_flags, tp); - if (ret < 0) - return ret; - - if (tb[TCA_BPF_CLASSID]) { - prog->res.classid = nla_get_u32(tb[TCA_BPF_CLASSID]); - tcf_bind_filter(tp, &prog->res, base); - } - - return 0; -} - static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, @@ -463,9 +413,12 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, struct netlink_ext_ack *extack) { struct cls_bpf_head *head = rtnl_dereference(tp->root); + bool is_bpf, is_ebpf, have_exts = false; struct cls_bpf_prog *oldprog = *arg; struct nlattr *tb[TCA_BPF_MAX + 1]; + bool bound_to_filter = false; struct cls_bpf_prog *prog; + u32 gen_flags = 0; int ret; if (tca[TCA_OPTIONS] == NULL) @@ -504,11 +457,51 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, goto errout; prog->handle = handle; - ret = cls_bpf_set_parms(net, tp, prog, base, tb, tca[TCA_RATE], flags, - extack); + is_bpf = tb[TCA_BPF_OPS_LEN] && tb[TCA_BPF_OPS]; + is_ebpf = tb[TCA_BPF_FD]; + if ((!is_bpf && !is_ebpf) || (is_bpf && is_ebpf)) { + ret = -EINVAL; + goto errout_idr; + } + + ret = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &prog->exts, + flags, extack); + if (ret < 0) + goto errout_idr; + + if (tb[TCA_BPF_FLAGS]) { + u32 bpf_flags = nla_get_u32(tb[TCA_BPF_FLAGS]); + + if (bpf_flags & ~TCA_BPF_FLAG_ACT_DIRECT) { + ret = -EINVAL; + goto errout_idr; + } + + have_exts = bpf_flags & TCA_BPF_FLAG_ACT_DIRECT; + } + if (tb[TCA_BPF_FLAGS_GEN]) { + gen_flags = nla_get_u32(tb[TCA_BPF_FLAGS_GEN]); + if (gen_flags & ~CLS_BPF_SUPPORTED_GEN_FLAGS || + !tc_flags_valid(gen_flags)) { + ret = -EINVAL; + goto errout_idr; + } + } + + prog->exts_integrated = have_exts; + prog->gen_flags = gen_flags; + + ret = is_bpf ? cls_bpf_prog_from_ops(tb, prog) : + cls_bpf_prog_from_efd(tb, prog, gen_flags, tp); if (ret < 0) goto errout_idr; + if (tb[TCA_BPF_CLASSID]) { + prog->res.classid = nla_get_u32(tb[TCA_BPF_CLASSID]); + tcf_bind_filter(tp, &prog->res, base); + bound_to_filter = true; + } + ret = cls_bpf_offload(tp, prog, oldprog, extack); if (ret) goto errout_parms; @@ -530,6 +523,8 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, return 0; errout_parms: + if (bound_to_filter) + tcf_unbind_filter(tp, &prog->res); cls_bpf_free_parms(prog); errout_idr: if (!oldprog) diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index f2b0bc4142fe..8da9d039d964 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -2173,53 +2173,6 @@ static bool fl_needs_tc_skb_ext(const struct fl_flow_key *mask) return mask->meta.l2_miss; } -static int fl_set_parms(struct net *net, struct tcf_proto *tp, - struct cls_fl_filter *f, struct fl_flow_mask *mask, - unsigned long base, struct nlattr **tb, - struct nlattr *est, - struct fl_flow_tmplt *tmplt, - u32 flags, u32 fl_flags, - struct netlink_ext_ack *extack) -{ - int err; - - err = tcf_exts_validate_ex(net, tp, tb, est, &f->exts, flags, - fl_flags, extack); - if (err < 0) - return err; - - if (tb[TCA_FLOWER_CLASSID]) { - f->res.classid = nla_get_u32(tb[TCA_FLOWER_CLASSID]); - if (flags & TCA_ACT_FLAGS_NO_RTNL) - rtnl_lock(); - tcf_bind_filter(tp, &f->res, base); - if (flags & TCA_ACT_FLAGS_NO_RTNL) - rtnl_unlock(); - } - - err = fl_set_key(net, tb, &f->key, &mask->key, extack); - if (err) - return err; - - fl_mask_update_range(mask); - fl_set_masked_key(&f->mkey, &f->key, mask); - - if (!fl_mask_fits_tmplt(tmplt, mask)) { - NL_SET_ERR_MSG_MOD(extack, "Mask does not fit the template"); - return -EINVAL; - } - - /* Enable tc skb extension if filter matches on data extracted from - * this extension. - */ - if (fl_needs_tc_skb_ext(&mask->key)) { - f->needs_tc_skb_ext = 1; - tc_skb_ext_tc_enable(); - } - - return 0; -} - static int fl_ht_insert_unique(struct cls_fl_filter *fnew, struct cls_fl_filter *fold, bool *in_ht) @@ -2251,6 +2204,7 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, struct cls_fl_head *head = fl_head_dereference(tp); bool rtnl_held = !(flags & TCA_ACT_FLAGS_NO_RTNL); struct cls_fl_filter *fold = *arg; + bool bound_to_filter = false; struct cls_fl_filter *fnew; struct fl_flow_mask *mask; struct nlattr **tb; @@ -2335,15 +2289,46 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, if (err < 0) goto errout_idr; - err = fl_set_parms(net, tp, fnew, mask, base, tb, tca[TCA_RATE], - tp->chain->tmplt_priv, flags, fnew->flags, - extack); - if (err) + err = tcf_exts_validate_ex(net, tp, tb, tca[TCA_RATE], + &fnew->exts, flags, fnew->flags, + extack); + if (err < 0) goto errout_idr; + if (tb[TCA_FLOWER_CLASSID]) { + fnew->res.classid = nla_get_u32(tb[TCA_FLOWER_CLASSID]); + if (flags & TCA_ACT_FLAGS_NO_RTNL) + rtnl_lock(); + tcf_bind_filter(tp, &fnew->res, base); + if (flags & TCA_ACT_FLAGS_NO_RTNL) + rtnl_unlock(); + bound_to_filter = true; + } + + err = fl_set_key(net, tb, &fnew->key, &mask->key, extack); + if (err) + goto unbind_filter; + + fl_mask_update_range(mask); + fl_set_masked_key(&fnew->mkey, &fnew->key, mask); + + if (!fl_mask_fits_tmplt(tp->chain->tmplt_priv, mask)) { + NL_SET_ERR_MSG_MOD(extack, "Mask does not fit the template"); + err = -EINVAL; + goto unbind_filter; + } + + /* Enable tc skb extension if filter matches on data extracted from + * this extension. + */ + if (fl_needs_tc_skb_ext(&mask->key)) { + fnew->needs_tc_skb_ext = 1; + tc_skb_ext_tc_enable(); + } + err = fl_check_assign_mask(head, fnew, fold, mask); if (err) - goto errout_idr; + goto unbind_filter; err = fl_ht_insert_unique(fnew, fold, &in_ht); if (err) @@ -2434,6 +2419,16 @@ errout_hw: fnew->mask->filter_ht_params); errout_mask: fl_mask_put(head, fnew->mask); + +unbind_filter: + if (bound_to_filter) { + if (flags & TCA_ACT_FLAGS_NO_RTNL) + rtnl_lock(); + tcf_unbind_filter(tp, &fnew->res); + if (flags & TCA_ACT_FLAGS_NO_RTNL) + rtnl_unlock(); + } + errout_idr: if (!fold) idr_remove(&head->handle_idr, fnew->handle); diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c index fa3bbd187eb9..c4ed11df6254 100644 --- a/net/sched/cls_matchall.c +++ b/net/sched/cls_matchall.c @@ -159,26 +159,6 @@ static const struct nla_policy mall_policy[TCA_MATCHALL_MAX + 1] = { [TCA_MATCHALL_FLAGS] = { .type = NLA_U32 }, }; -static int mall_set_parms(struct net *net, struct tcf_proto *tp, - struct cls_mall_head *head, - unsigned long base, struct nlattr **tb, - struct nlattr *est, u32 flags, u32 fl_flags, - struct netlink_ext_ack *extack) -{ - int err; - - err = tcf_exts_validate_ex(net, tp, tb, est, &head->exts, flags, - fl_flags, extack); - if (err < 0) - return err; - - if (tb[TCA_MATCHALL_CLASSID]) { - head->res.classid = nla_get_u32(tb[TCA_MATCHALL_CLASSID]); - tcf_bind_filter(tp, &head->res, base); - } - return 0; -} - static int mall_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, @@ -187,6 +167,7 @@ static int mall_change(struct net *net, struct sk_buff *in_skb, { struct cls_mall_head *head = rtnl_dereference(tp->root); struct nlattr *tb[TCA_MATCHALL_MAX + 1]; + bool bound_to_filter = false; struct cls_mall_head *new; u32 userflags = 0; int err; @@ -226,11 +207,17 @@ static int mall_change(struct net *net, struct sk_buff *in_skb, goto err_alloc_percpu; } - err = mall_set_parms(net, tp, new, base, tb, tca[TCA_RATE], - flags, new->flags, extack); - if (err) + err = tcf_exts_validate_ex(net, tp, tb, tca[TCA_RATE], + &new->exts, flags, new->flags, extack); + if (err < 0) goto err_set_parms; + if (tb[TCA_MATCHALL_CLASSID]) { + new->res.classid = nla_get_u32(tb[TCA_MATCHALL_CLASSID]); + tcf_bind_filter(tp, &new->res, base); + bound_to_filter = true; + } + if (!tc_skip_hw(new->flags)) { err = mall_replace_hw_filter(tp, new, (unsigned long)new, extack); @@ -246,6 +233,8 @@ static int mall_change(struct net *net, struct sk_buff *in_skb, return 0; err_replace_hw_filter: + if (bound_to_filter) + tcf_unbind_filter(tp, &new->res); err_set_parms: free_percpu(new->pf); err_alloc_percpu: diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index d15d50de7980..5abf31e432ca 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -712,8 +712,23 @@ static const struct nla_policy u32_policy[TCA_U32_MAX + 1] = { [TCA_U32_FLAGS] = { .type = NLA_U32 }, }; +static void u32_unbind_filter(struct tcf_proto *tp, struct tc_u_knode *n, + struct nlattr **tb) +{ + if (tb[TCA_U32_CLASSID]) + tcf_unbind_filter(tp, &n->res); +} + +static void u32_bind_filter(struct tcf_proto *tp, struct tc_u_knode *n, + unsigned long base, struct nlattr **tb) +{ + if (tb[TCA_U32_CLASSID]) { + n->res.classid = nla_get_u32(tb[TCA_U32_CLASSID]); + tcf_bind_filter(tp, &n->res, base); + } +} + static int u32_set_parms(struct net *net, struct tcf_proto *tp, - unsigned long base, struct tc_u_knode *n, struct nlattr **tb, struct nlattr *est, u32 flags, u32 fl_flags, struct netlink_ext_ack *extack) @@ -760,10 +775,6 @@ static int u32_set_parms(struct net *net, struct tcf_proto *tp, if (ht_old) ht_old->refcnt--; } - if (tb[TCA_U32_CLASSID]) { - n->res.classid = nla_get_u32(tb[TCA_U32_CLASSID]); - tcf_bind_filter(tp, &n->res, base); - } if (ifindex >= 0) n->ifindex = ifindex; @@ -903,17 +914,27 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, if (!new) return -ENOMEM; - err = u32_set_parms(net, tp, base, new, tb, - tca[TCA_RATE], flags, new->flags, - extack); + err = u32_set_parms(net, tp, new, tb, tca[TCA_RATE], + flags, new->flags, extack); if (err) { __u32_destroy_key(new); return err; } + u32_bind_filter(tp, new, base, tb); + err = u32_replace_hw_knode(tp, new, flags, extack); if (err) { + u32_unbind_filter(tp, new, tb); + + if (tb[TCA_U32_LINK]) { + struct tc_u_hnode *ht_old; + + ht_old = rtnl_dereference(n->ht_down); + if (ht_old) + ht_old->refcnt++; + } __u32_destroy_key(new); return err; } @@ -1074,15 +1095,18 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, } #endif - err = u32_set_parms(net, tp, base, n, tb, tca[TCA_RATE], + err = u32_set_parms(net, tp, n, tb, tca[TCA_RATE], flags, n->flags, extack); + + u32_bind_filter(tp, n, base, tb); + if (err == 0) { struct tc_u_knode __rcu **ins; struct tc_u_knode *pins; err = u32_replace_hw_knode(tp, n, flags, extack); if (err) - goto errhw; + goto errunbind; if (!tc_in_hw(n->flags)) n->flags |= TCA_CLS_FLAGS_NOT_IN_HW; @@ -1100,7 +1124,9 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, return 0; } -errhw: +errunbind: + u32_unbind_filter(tp, n, tb); + #ifdef CONFIG_CLS_U32_MARK free_percpu(n->pcpu_success); #endif diff --git a/tools/testing/selftests/bpf/progs/async_stack_depth.c b/tools/testing/selftests/bpf/progs/async_stack_depth.c index 477ba950bb43..3517c0e01206 100644 --- a/tools/testing/selftests/bpf/progs/async_stack_depth.c +++ b/tools/testing/selftests/bpf/progs/async_stack_depth.c @@ -22,9 +22,16 @@ static int timer_cb(void *map, int *key, struct bpf_timer *timer) return buf[69]; } +__attribute__((noinline)) +static int bad_timer_cb(void *map, int *key, struct bpf_timer *timer) +{ + volatile char buf[300] = {}; + return buf[255] + timer_cb(NULL, NULL, NULL); +} + SEC("tc") -__failure __msg("combined stack size of 2 calls") -int prog(struct __sk_buff *ctx) +__failure __msg("combined stack size of 2 calls is 576. Too large") +int pseudo_call_check(struct __sk_buff *ctx) { struct hmap_elem *elem; volatile char buf[256] = {}; @@ -37,4 +44,18 @@ int prog(struct __sk_buff *ctx) return bpf_timer_set_callback(&elem->timer, timer_cb) + buf[0]; } +SEC("tc") +__failure __msg("combined stack size of 2 calls is 608. Too large") +int async_call_root_check(struct __sk_buff *ctx) +{ + struct hmap_elem *elem; + volatile char buf[256] = {}; + + elem = bpf_map_lookup_elem(&hmap, &(int){0}); + if (!elem) + return 0; + + return bpf_timer_set_callback(&elem->timer, bad_timer_cb) + buf[0]; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/tc-testing/config b/tools/testing/selftests/tc-testing/config index 6e73b09c20c8..71706197ba0f 100644 --- a/tools/testing/selftests/tc-testing/config +++ b/tools/testing/selftests/tc-testing/config @@ -5,6 +5,8 @@ CONFIG_NF_CONNTRACK=m CONFIG_NF_CONNTRACK_MARK=y CONFIG_NF_CONNTRACK_ZONES=y CONFIG_NF_CONNTRACK_LABELS=y +CONFIG_NF_CONNTRACK_PROCFS=y +CONFIG_NF_FLOW_TABLE=m CONFIG_NF_NAT=m CONFIG_NETFILTER_XT_TARGET_LOG=m diff --git a/tools/testing/selftests/tc-testing/settings b/tools/testing/selftests/tc-testing/settings new file mode 100644 index 000000000000..e2206265f67c --- /dev/null +++ b/tools/testing/selftests/tc-testing/settings @@ -0,0 +1 @@ +timeout=900 |