diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2026-03-05 11:00:46 -0800 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2026-03-05 11:00:46 -0800 |
| commit | abacaf559950eec0d99d37ff6b92049409af5943 (patch) | |
| tree | 35cb46179fc961ff60205f261c97213bea3321c0 | |
| parent | 18ecff396c9edb9add34f612d9fb99bb34833cc0 (diff) | |
| parent | cf440e5b40649d1ffbc6c4e33fef3223c7482897 (diff) | |
Merge tag 'net-7.0-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Jakub Kicinski:
"Including fixes from CAN, netfilter and wireless.
Current release - new code bugs:
- sched: cake: fixup cake_mq rate adjustment for diffserv config
- wifi: fix missing ieee80211_eml_params member initialization
Previous releases - regressions:
- tcp: give up on stronger sk_rcvbuf checks (for now)
Previous releases - always broken:
- net: fix rcu_tasks stall in threaded busypoll
- sched:
- fq: clear q->band_pkt_count[] in fq_reset()
- only allow act_ct to bind to clsact/ingress qdiscs and shared
blocks
- bridge: check relevant per-VLAN options in VLAN range grouping
- xsk: fix fragment node deletion to prevent buffer leak
Misc:
- spring cleanup of inactive maintainers"
* tag 'net-7.0-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (138 commits)
xdp: produce a warning when calculated tailroom is negative
net: enetc: use truesize as XDP RxQ info frag_size
libeth, idpf: use truesize as XDP RxQ info frag_size
i40e: use xdp.frame_sz as XDP RxQ info frag_size
i40e: fix registering XDP RxQ info
ice: change XDP RxQ frag_size from DMA write length to xdp.frame_sz
ice: fix rxq info registering in mbuf packets
xsk: introduce helper to determine rxq->frag_size
xdp: use modulo operation to calculate XDP frag tailroom
selftests/tc-testing: Add tests exercising act_ife metalist replace behaviour
net/sched: act_ife: Fix metalist update behavior
selftests: net: add test for IPv4 route with loopback IPv6 nexthop
net: ipv6: fix panic when IPv4 route references loopback IPv6 nexthop
net: vxlan: fix nd_tbl NULL dereference when IPv6 is disabled
net: bridge: fix nd_tbl NULL dereference when IPv6 is disabled
MAINTAINERS: remove Thomas Falcon from IBM ibmvnic
MAINTAINERS: remove Claudiu Manoil and Alexandre Belloni from Ocelot switch
MAINTAINERS: replace Taras Chornyi with Elad Nachman for Marvell Prestera
MAINTAINERS: remove Jonathan Lemon from OpenCompute PTP
MAINTAINERS: replace Clark Wang with Frank Li for Freescale FEC
...
159 files changed, 2152 insertions, 836 deletions
@@ -353,6 +353,7 @@ Jarkko Sakkinen <jarkko@kernel.org> <jarkko.sakkinen@opinsys.com> Jason Gunthorpe <jgg@ziepe.ca> <jgg@mellanox.com> Jason Gunthorpe <jgg@ziepe.ca> <jgg@nvidia.com> Jason Gunthorpe <jgg@ziepe.ca> <jgunthorpe@obsidianresearch.com> +Jason Xing <kerneljasonxing@gmail.com> <kernelxing@tencent.com> <javier@osg.samsung.com> <javier.martinez@collabora.co.uk> Javi Merino <javi.merino@kernel.org> <javi.merino@arm.com> Jayachandran C <c.jayachandran@gmail.com> <jayachandranc@netlogicmicro.com> @@ -401,6 +402,7 @@ Jiri Slaby <jirislaby@kernel.org> <xslaby@fi.muni.cz> Jisheng Zhang <jszhang@kernel.org> <jszhang@marvell.com> Jisheng Zhang <jszhang@kernel.org> <Jisheng.Zhang@synaptics.com> Jishnu Prakash <quic_jprakash@quicinc.com> <jprakash@codeaurora.org> +Joe Damato <joe@dama.to> <jdamato@fastly.com> Joel Granados <joel.granados@kernel.org> <j.granados@samsung.com> Johan Hovold <johan@kernel.org> <jhovold@gmail.com> Johan Hovold <johan@kernel.org> <johan@hovoldconsulting.com> @@ -1242,6 +1242,10 @@ N: Veaceslav Falico E: vfalico@gmail.com D: Co-maintainer and co-author of the network bonding driver. +N: Thomas Falcon +E: tlfalcon@linux.ibm.com +D: Initial author of the IBM ibmvnic network driver + N: János Farkas E: chexum@shadow.banki.hu D: romfs, various (mostly networking) fixes @@ -2415,6 +2419,10 @@ S: Am Muehlenweg 38 S: D53424 Remagen S: Germany +N: Jonathan Lemon +E: jonathan.lemon@gmail.com +D: OpenCompute PTP clock driver (ptp_ocp) + N: Colin Leroy E: colin@colino.net W: http://www.geekounet.org/ diff --git a/Documentation/devicetree/bindings/net/can/nxp,sja1000.yaml b/Documentation/devicetree/bindings/net/can/nxp,sja1000.yaml index ec0c2168e4b9..6bcfff970117 100644 --- a/Documentation/devicetree/bindings/net/can/nxp,sja1000.yaml +++ b/Documentation/devicetree/bindings/net/can/nxp,sja1000.yaml @@ -87,6 +87,7 @@ required: allOf: - $ref: can-controller.yaml# + - $ref: /schemas/memory-controllers/mc-peripheral-props.yaml - if: properties: compatible: diff --git a/MAINTAINERS b/MAINTAINERS index b8d1ad952827..7b277d5bf3d1 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -993,10 +993,8 @@ F: Documentation/devicetree/bindings/thermal/amazon,al-thermal.yaml F: drivers/thermal/thermal_mmio.c AMAZON ETHERNET DRIVERS -M: Shay Agroskin <shayagr@amazon.com> M: Arthur Kiyanovski <akiyano@amazon.com> -R: David Arinzon <darinzon@amazon.com> -R: Saeed Bishara <saeedb@amazon.com> +M: David Arinzon <darinzon@amazon.com> L: netdev@vger.kernel.org S: Maintained F: Documentation/networking/device_drivers/ethernet/amazon/ena.rst @@ -4617,7 +4615,6 @@ F: drivers/bluetooth/ BLUETOOTH SUBSYSTEM M: Marcel Holtmann <marcel@holtmann.org> -M: Johan Hedberg <johan.hedberg@gmail.com> M: Luiz Augusto von Dentz <luiz.dentz@gmail.com> L: linux-bluetooth@vger.kernel.org S: Supported @@ -10171,8 +10168,8 @@ F: drivers/i2c/busses/i2c-cpm.c FREESCALE IMX / MXC FEC DRIVER M: Wei Fang <wei.fang@nxp.com> +R: Frank Li <frank.li@nxp.com> R: Shenwei Wang <shenwei.wang@nxp.com> -R: Clark Wang <xiaoning.wang@nxp.com> L: imx@lists.linux.dev L: netdev@vger.kernel.org S: Maintained @@ -12216,7 +12213,6 @@ IBM Power SRIOV Virtual NIC Device Driver M: Haren Myneni <haren@linux.ibm.com> M: Rick Lindsley <ricklind@linux.ibm.com> R: Nick Child <nnac123@linux.ibm.com> -R: Thomas Falcon <tlfalcon@linux.ibm.com> L: netdev@vger.kernel.org S: Maintained F: drivers/net/ethernet/ibm/ibmvnic.* @@ -15375,10 +15371,8 @@ F: drivers/crypto/marvell/ F: include/linux/soc/marvell/octeontx2/ MARVELL GIGABIT ETHERNET DRIVERS (skge/sky2) -M: Mirko Lindner <mlindner@marvell.com> -M: Stephen Hemminger <stephen@networkplumber.org> L: netdev@vger.kernel.org -S: Odd fixes +S: Orphan F: drivers/net/ethernet/marvell/sk* MARVELL LIBERTAS WIRELESS DRIVER @@ -15475,7 +15469,6 @@ MARVELL OCTEONTX2 RVU ADMIN FUNCTION DRIVER M: Sunil Goutham <sgoutham@marvell.com> M: Linu Cherian <lcherian@marvell.com> M: Geetha sowjanya <gakula@marvell.com> -M: Jerin Jacob <jerinj@marvell.com> M: hariprasad <hkelam@marvell.com> M: Subbaraya Sundeep <sbhatta@marvell.com> L: netdev@vger.kernel.org @@ -15490,7 +15483,7 @@ S: Supported F: drivers/perf/marvell_pem_pmu.c MARVELL PRESTERA ETHERNET SWITCH DRIVER -M: Taras Chornyi <taras.chornyi@plvision.eu> +M: Elad Nachman <enachman@marvell.com> S: Supported W: https://github.com/Marvell-switching/switchdev-prestera F: drivers/net/ethernet/marvell/prestera/ @@ -16164,7 +16157,6 @@ F: drivers/dma/mediatek/ MEDIATEK ETHERNET DRIVER M: Felix Fietkau <nbd@nbd.name> -M: Sean Wang <sean.wang@mediatek.com> M: Lorenzo Bianconi <lorenzo@kernel.org> L: netdev@vger.kernel.org S: Maintained @@ -16357,8 +16349,6 @@ F: include/soc/mediatek/smi.h MEDIATEK SWITCH DRIVER M: Chester A. Unal <chester.a.unal@arinc9.com> M: Daniel Golle <daniel@makrotopia.org> -M: DENG Qingfang <dqfext@gmail.com> -M: Sean Wang <sean.wang@mediatek.com> L: netdev@vger.kernel.org S: Maintained F: drivers/net/dsa/mt7530-mdio.c @@ -19226,8 +19216,6 @@ F: tools/objtool/ OCELOT ETHERNET SWITCH DRIVER M: Vladimir Oltean <vladimir.oltean@nxp.com> -M: Claudiu Manoil <claudiu.manoil@nxp.com> -M: Alexandre Belloni <alexandre.belloni@bootlin.com> M: UNGLinuxDriver@microchip.com L: netdev@vger.kernel.org S: Supported @@ -19813,7 +19801,6 @@ F: arch/*/boot/dts/ F: include/dt-bindings/ OPENCOMPUTE PTP CLOCK DRIVER -M: Jonathan Lemon <jonathan.lemon@gmail.com> M: Vadim Fedorenko <vadim.fedorenko@linux.dev> L: netdev@vger.kernel.org S: Maintained @@ -21457,9 +21444,8 @@ S: Supported F: drivers/scsi/qedi/ QLOGIC QL4xxx ETHERNET DRIVER -M: Manish Chopra <manishc@marvell.com> L: netdev@vger.kernel.org -S: Maintained +S: Orphan F: drivers/net/ethernet/qlogic/qed/ F: drivers/net/ethernet/qlogic/qede/ F: include/linux/qed/ diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index a1de08ee3815..14ed91391fcc 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -324,7 +324,7 @@ static bool bond_sk_check(struct bonding *bond) } } -bool bond_xdp_check(struct bonding *bond, int mode) +bool __bond_xdp_check(int mode, int xmit_policy) { switch (mode) { case BOND_MODE_ROUNDROBIN: @@ -335,7 +335,7 @@ bool bond_xdp_check(struct bonding *bond, int mode) /* vlan+srcmac is not supported with XDP as in most cases the 802.1q * payload is not in the packet due to hardware offload. */ - if (bond->params.xmit_policy != BOND_XMIT_POLICY_VLAN_SRCMAC) + if (xmit_policy != BOND_XMIT_POLICY_VLAN_SRCMAC) return true; fallthrough; default: @@ -343,6 +343,11 @@ bool bond_xdp_check(struct bonding *bond, int mode) } } +bool bond_xdp_check(struct bonding *bond, int mode) +{ + return __bond_xdp_check(mode, bond->params.xmit_policy); +} + /*---------------------------------- VLAN -----------------------------------*/ /* In the following 2 functions, bond_vlan_rx_add_vid and bond_vlan_rx_kill_vid, diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index dcee384c2f06..7380cc4ee75a 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -1575,6 +1575,8 @@ static int bond_option_fail_over_mac_set(struct bonding *bond, static int bond_option_xmit_hash_policy_set(struct bonding *bond, const struct bond_opt_value *newval) { + if (bond->xdp_prog && !__bond_xdp_check(BOND_MODE(bond), newval->value)) + return -EOPNOTSUPP; netdev_dbg(bond->dev, "Setting xmit hash policy to %s (%llu)\n", newval->string, newval->value); bond->params.xmit_policy = newval->value; diff --git a/drivers/net/can/dummy_can.c b/drivers/net/can/dummy_can.c index 41953655e3d3..cd23de488edc 100644 --- a/drivers/net/can/dummy_can.c +++ b/drivers/net/can/dummy_can.c @@ -241,6 +241,7 @@ static int __init dummy_can_init(void) dev->netdev_ops = &dummy_can_netdev_ops; dev->ethtool_ops = &dummy_can_ethtool_ops; + dev->flags |= IFF_ECHO; /* enable echo handling */ priv = netdev_priv(dev); priv->can.bittiming_const = &dummy_can_bittiming_const; priv->can.bitrate_max = 20 * MEGA /* BPS */; diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c index fa97adf25b73..bb7782582f40 100644 --- a/drivers/net/can/spi/mcp251x.c +++ b/drivers/net/can/spi/mcp251x.c @@ -1214,6 +1214,7 @@ static int mcp251x_open(struct net_device *net) { struct mcp251x_priv *priv = netdev_priv(net); struct spi_device *spi = priv->spi; + bool release_irq = false; unsigned long flags = 0; int ret; @@ -1257,12 +1258,24 @@ static int mcp251x_open(struct net_device *net) return 0; out_free_irq: - free_irq(spi->irq, priv); + /* The IRQ handler might be running, and if so it will be waiting + * for the lock. But free_irq() must wait for the handler to finish + * so calling it here would deadlock. + * + * Setting priv->force_quit will let the handler exit right away + * without any access to the hardware. This make it safe to call + * free_irq() after the lock is released. + */ + priv->force_quit = 1; + release_irq = true; + mcp251x_hw_sleep(spi); out_close: mcp251x_power_enable(priv->transceiver, 0); close_candev(net); mutex_unlock(&priv->mcp_lock); + if (release_irq) + free_irq(spi->irq, priv); return ret; } diff --git a/drivers/net/can/usb/ems_usb.c b/drivers/net/can/usb/ems_usb.c index 4c219a5b139b..9b25dda7c183 100644 --- a/drivers/net/can/usb/ems_usb.c +++ b/drivers/net/can/usb/ems_usb.c @@ -445,6 +445,11 @@ static void ems_usb_read_bulk_callback(struct urb *urb) start = CPC_HEADER_SIZE; while (msg_count) { + if (start + CPC_MSG_HEADER_LEN > urb->actual_length) { + netdev_err(netdev, "format error\n"); + break; + } + msg = (struct ems_cpc_msg *)&ibuf[start]; switch (msg->type) { @@ -474,7 +479,7 @@ static void ems_usb_read_bulk_callback(struct urb *urb) start += CPC_MSG_HEADER_LEN + msg->length; msg_count--; - if (start > urb->transfer_buffer_length) { + if (start > urb->actual_length) { netdev_err(netdev, "format error\n"); break; } diff --git a/drivers/net/can/usb/esd_usb.c b/drivers/net/can/usb/esd_usb.c index 2892a68f510a..d257440fa01f 100644 --- a/drivers/net/can/usb/esd_usb.c +++ b/drivers/net/can/usb/esd_usb.c @@ -272,6 +272,9 @@ struct esd_usb { struct usb_anchor rx_submitted; + unsigned int rx_pipe; + unsigned int tx_pipe; + int net_count; u32 version; int rxinitdone; @@ -537,7 +540,7 @@ static void esd_usb_read_bulk_callback(struct urb *urb) } resubmit_urb: - usb_fill_bulk_urb(urb, dev->udev, usb_rcvbulkpipe(dev->udev, 1), + usb_fill_bulk_urb(urb, dev->udev, dev->rx_pipe, urb->transfer_buffer, ESD_USB_RX_BUFFER_SIZE, esd_usb_read_bulk_callback, dev); @@ -626,9 +629,7 @@ static int esd_usb_send_msg(struct esd_usb *dev, union esd_usb_msg *msg) { int actual_length; - return usb_bulk_msg(dev->udev, - usb_sndbulkpipe(dev->udev, 2), - msg, + return usb_bulk_msg(dev->udev, dev->tx_pipe, msg, msg->hdr.len * sizeof(u32), /* convert to # of bytes */ &actual_length, 1000); @@ -639,12 +640,8 @@ static int esd_usb_wait_msg(struct esd_usb *dev, { int actual_length; - return usb_bulk_msg(dev->udev, - usb_rcvbulkpipe(dev->udev, 1), - msg, - sizeof(*msg), - &actual_length, - 1000); + return usb_bulk_msg(dev->udev, dev->rx_pipe, msg, + sizeof(*msg), &actual_length, 1000); } static int esd_usb_setup_rx_urbs(struct esd_usb *dev) @@ -677,8 +674,7 @@ static int esd_usb_setup_rx_urbs(struct esd_usb *dev) urb->transfer_dma = buf_dma; - usb_fill_bulk_urb(urb, dev->udev, - usb_rcvbulkpipe(dev->udev, 1), + usb_fill_bulk_urb(urb, dev->udev, dev->rx_pipe, buf, ESD_USB_RX_BUFFER_SIZE, esd_usb_read_bulk_callback, dev); urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP; @@ -903,7 +899,7 @@ static netdev_tx_t esd_usb_start_xmit(struct sk_buff *skb, /* hnd must not be 0 - MSB is stripped in txdone handling */ msg->tx.hnd = BIT(31) | i; /* returned in TX done message */ - usb_fill_bulk_urb(urb, dev->udev, usb_sndbulkpipe(dev->udev, 2), buf, + usb_fill_bulk_urb(urb, dev->udev, dev->tx_pipe, buf, msg->hdr.len * sizeof(u32), /* convert to # of bytes */ esd_usb_write_bulk_callback, context); @@ -1298,10 +1294,16 @@ done: static int esd_usb_probe(struct usb_interface *intf, const struct usb_device_id *id) { + struct usb_endpoint_descriptor *ep_in, *ep_out; struct esd_usb *dev; union esd_usb_msg *msg; int i, err; + err = usb_find_common_endpoints(intf->cur_altsetting, &ep_in, &ep_out, + NULL, NULL); + if (err) + return err; + dev = kzalloc_obj(*dev); if (!dev) { err = -ENOMEM; @@ -1309,6 +1311,8 @@ static int esd_usb_probe(struct usb_interface *intf, } dev->udev = interface_to_usbdev(intf); + dev->rx_pipe = usb_rcvbulkpipe(dev->udev, ep_in->bEndpointAddress); + dev->tx_pipe = usb_sndbulkpipe(dev->udev, ep_out->bEndpointAddress); init_usb_anchor(&dev->rx_submitted); diff --git a/drivers/net/can/usb/etas_es58x/es58x_core.c b/drivers/net/can/usb/etas_es58x/es58x_core.c index 2d248deb69dc..b259f6109808 100644 --- a/drivers/net/can/usb/etas_es58x/es58x_core.c +++ b/drivers/net/can/usb/etas_es58x/es58x_core.c @@ -1461,12 +1461,18 @@ static void es58x_read_bulk_callback(struct urb *urb) } resubmit_urb: + usb_anchor_urb(urb, &es58x_dev->rx_urbs); ret = usb_submit_urb(urb, GFP_ATOMIC); + if (!ret) + return; + + usb_unanchor_urb(urb); + if (ret == -ENODEV) { for (i = 0; i < es58x_dev->num_can_ch; i++) if (es58x_dev->netdev[i]) netif_device_detach(es58x_dev->netdev[i]); - } else if (ret) + } else dev_err_ratelimited(dev, "Failed resubmitting read bulk urb: %pe\n", ERR_PTR(ret)); diff --git a/drivers/net/can/usb/f81604.c b/drivers/net/can/usb/f81604.c index 76578063ac82..f12318268e46 100644 --- a/drivers/net/can/usb/f81604.c +++ b/drivers/net/can/usb/f81604.c @@ -413,6 +413,7 @@ static void f81604_read_bulk_callback(struct urb *urb) { struct f81604_can_frame *frame = urb->transfer_buffer; struct net_device *netdev = urb->context; + struct f81604_port_priv *priv = netdev_priv(netdev); int ret; if (!netif_device_present(netdev)) @@ -445,10 +446,15 @@ static void f81604_read_bulk_callback(struct urb *urb) f81604_process_rx_packet(netdev, frame); resubmit_urb: + usb_anchor_urb(urb, &priv->urbs_anchor); ret = usb_submit_urb(urb, GFP_ATOMIC); + if (!ret) + return; + usb_unanchor_urb(urb); + if (ret == -ENODEV) netif_device_detach(netdev); - else if (ret) + else netdev_err(netdev, "%s: failed to resubmit read bulk urb: %pe\n", __func__, ERR_PTR(ret)); @@ -620,6 +626,12 @@ static void f81604_read_int_callback(struct urb *urb) netdev_info(netdev, "%s: Int URB aborted: %pe\n", __func__, ERR_PTR(urb->status)); + if (urb->actual_length < sizeof(*data)) { + netdev_warn(netdev, "%s: short int URB: %u < %zu\n", + __func__, urb->actual_length, sizeof(*data)); + goto resubmit_urb; + } + switch (urb->status) { case 0: /* success */ break; @@ -646,10 +658,15 @@ static void f81604_read_int_callback(struct urb *urb) f81604_handle_tx(priv, data); resubmit_urb: + usb_anchor_urb(urb, &priv->urbs_anchor); ret = usb_submit_urb(urb, GFP_ATOMIC); + if (!ret) + return; + usb_unanchor_urb(urb); + if (ret == -ENODEV) netif_device_detach(netdev); - else if (ret) + else netdev_err(netdev, "%s: failed to resubmit int urb: %pe\n", __func__, ERR_PTR(ret)); } @@ -874,9 +891,27 @@ static void f81604_write_bulk_callback(struct urb *urb) if (!netif_device_present(netdev)) return; - if (urb->status) - netdev_info(netdev, "%s: Tx URB error: %pe\n", __func__, - ERR_PTR(urb->status)); + if (!urb->status) + return; + + switch (urb->status) { + case -ENOENT: + case -ECONNRESET: + case -ESHUTDOWN: + return; + default: + break; + } + + if (net_ratelimit()) + netdev_err(netdev, "%s: Tx URB error: %pe\n", __func__, + ERR_PTR(urb->status)); + + can_free_echo_skb(netdev, 0, NULL); + netdev->stats.tx_dropped++; + netdev->stats.tx_errors++; + + netif_wake_queue(netdev); } static void f81604_clear_reg_work(struct work_struct *work) diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c index 9d27d6f0c0b5..ec9a7cbbbc69 100644 --- a/drivers/net/can/usb/gs_usb.c +++ b/drivers/net/can/usb/gs_usb.c @@ -772,9 +772,8 @@ device_detach: } } -static int gs_usb_set_bittiming(struct net_device *netdev) +static int gs_usb_set_bittiming(struct gs_can *dev) { - struct gs_can *dev = netdev_priv(netdev); struct can_bittiming *bt = &dev->can.bittiming; struct gs_device_bittiming dbt = { .prop_seg = cpu_to_le32(bt->prop_seg), @@ -791,9 +790,8 @@ static int gs_usb_set_bittiming(struct net_device *netdev) GFP_KERNEL); } -static int gs_usb_set_data_bittiming(struct net_device *netdev) +static int gs_usb_set_data_bittiming(struct gs_can *dev) { - struct gs_can *dev = netdev_priv(netdev); struct can_bittiming *bt = &dev->can.fd.data_bittiming; struct gs_device_bittiming dbt = { .prop_seg = cpu_to_le32(bt->prop_seg), @@ -1057,6 +1055,20 @@ static int gs_can_open(struct net_device *netdev) if (dev->feature & GS_CAN_FEATURE_HW_TIMESTAMP) flags |= GS_CAN_MODE_HW_TIMESTAMP; + rc = gs_usb_set_bittiming(dev); + if (rc) { + netdev_err(netdev, "failed to set bittiming: %pe\n", ERR_PTR(rc)); + goto out_usb_kill_anchored_urbs; + } + + if (ctrlmode & CAN_CTRLMODE_FD) { + rc = gs_usb_set_data_bittiming(dev); + if (rc) { + netdev_err(netdev, "failed to set data bittiming: %pe\n", ERR_PTR(rc)); + goto out_usb_kill_anchored_urbs; + } + } + /* finally start device */ dev->can.state = CAN_STATE_ERROR_ACTIVE; dm.flags = cpu_to_le32(flags); @@ -1370,7 +1382,6 @@ static struct gs_can *gs_make_candev(unsigned int channel, dev->can.state = CAN_STATE_STOPPED; dev->can.clock.freq = le32_to_cpu(bt_const.fclk_can); dev->can.bittiming_const = &dev->bt_const; - dev->can.do_set_bittiming = gs_usb_set_bittiming; dev->can.ctrlmode_supported = CAN_CTRLMODE_CC_LEN8_DLC; @@ -1394,7 +1405,6 @@ static struct gs_can *gs_make_candev(unsigned int channel, * GS_CAN_FEATURE_BT_CONST_EXT is set. */ dev->can.fd.data_bittiming_const = &dev->bt_const; - dev->can.fd.do_set_data_bittiming = gs_usb_set_data_bittiming; } if (feature & GS_CAN_FEATURE_TERMINATION) { diff --git a/drivers/net/can/usb/ucan.c b/drivers/net/can/usb/ucan.c index c79508b1c43e..0ea0ac75e42f 100644 --- a/drivers/net/can/usb/ucan.c +++ b/drivers/net/can/usb/ucan.c @@ -748,7 +748,7 @@ static void ucan_read_bulk_callback(struct urb *urb) len = le16_to_cpu(m->len); /* check sanity (length of content) */ - if (urb->actual_length - pos < len) { + if ((len == 0) || (urb->actual_length - pos < len)) { netdev_warn(up->netdev, "invalid message (short; no data; l:%d)\n", urb->actual_length); diff --git a/drivers/net/dsa/realtek/rtl8365mb.c b/drivers/net/dsa/realtek/rtl8365mb.c index c575e164368c..f938a3f701cc 100644 --- a/drivers/net/dsa/realtek/rtl8365mb.c +++ b/drivers/net/dsa/realtek/rtl8365mb.c @@ -769,7 +769,7 @@ static int rtl8365mb_phy_ocp_write(struct realtek_priv *priv, int phy, out: rtl83xx_unlock(priv); - return 0; + return ret; } static int rtl8365mb_phy_read(struct realtek_priv *priv, int phy, int regnum) diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-common.h b/drivers/net/ethernet/amd/xgbe/xgbe-common.h index 711f295eb777..80c2c27ac9dc 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-common.h +++ b/drivers/net/ethernet/amd/xgbe/xgbe-common.h @@ -431,7 +431,7 @@ #define MAC_SSIR_SSINC_INDEX 16 #define MAC_SSIR_SSINC_WIDTH 8 #define MAC_TCR_SS_INDEX 29 -#define MAC_TCR_SS_WIDTH 2 +#define MAC_TCR_SS_WIDTH 3 #define MAC_TCR_TE_INDEX 0 #define MAC_TCR_TE_WIDTH 1 #define MAC_TCR_VNE_INDEX 24 diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index 62bb4b8a68e1..8b79d88480db 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -1120,7 +1120,6 @@ int xgbe_powerdown(struct net_device *netdev, unsigned int caller) { struct xgbe_prv_data *pdata = netdev_priv(netdev); struct xgbe_hw_if *hw_if = &pdata->hw_if; - unsigned long flags; DBGPR("-->xgbe_powerdown\n"); @@ -1131,8 +1130,6 @@ int xgbe_powerdown(struct net_device *netdev, unsigned int caller) return -EINVAL; } - spin_lock_irqsave(&pdata->lock, flags); - if (caller == XGMAC_DRIVER_CONTEXT) netif_device_detach(netdev); @@ -1148,8 +1145,6 @@ int xgbe_powerdown(struct net_device *netdev, unsigned int caller) pdata->power_down = 1; - spin_unlock_irqrestore(&pdata->lock, flags); - DBGPR("<--xgbe_powerdown\n"); return 0; @@ -1159,7 +1154,6 @@ int xgbe_powerup(struct net_device *netdev, unsigned int caller) { struct xgbe_prv_data *pdata = netdev_priv(netdev); struct xgbe_hw_if *hw_if = &pdata->hw_if; - unsigned long flags; DBGPR("-->xgbe_powerup\n"); @@ -1170,8 +1164,6 @@ int xgbe_powerup(struct net_device *netdev, unsigned int caller) return -EINVAL; } - spin_lock_irqsave(&pdata->lock, flags); - pdata->power_down = 0; xgbe_napi_enable(pdata, 0); @@ -1186,8 +1178,6 @@ int xgbe_powerup(struct net_device *netdev, unsigned int caller) xgbe_start_timers(pdata); - spin_unlock_irqrestore(&pdata->lock, flags); - DBGPR("<--xgbe_powerup\n"); return 0; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-main.c b/drivers/net/ethernet/amd/xgbe/xgbe-main.c index d1f0419edb23..7d45ea22a02e 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-main.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-main.c @@ -76,7 +76,6 @@ struct xgbe_prv_data *xgbe_alloc_pdata(struct device *dev) pdata->netdev = netdev; pdata->dev = dev; - spin_lock_init(&pdata->lock); spin_lock_init(&pdata->xpcs_lock); mutex_init(&pdata->rss_mutex); spin_lock_init(&pdata->tstamp_lock); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h index 1269b8ce9249..e1d7d7150e16 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe.h +++ b/drivers/net/ethernet/amd/xgbe/xgbe.h @@ -1004,9 +1004,6 @@ struct xgbe_prv_data { unsigned int pp3; unsigned int pp4; - /* Overall device lock */ - spinlock_t lock; - /* XPCS indirect addressing lock */ spinlock_t xpcs_lock; unsigned int xpcs_window_def_reg; diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c index fc0e0f36186e..52c1cb9cb7e0 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c @@ -1533,7 +1533,7 @@ static irqreturn_t dpaa2_switch_irq0_handler_thread(int irq_num, void *arg) if_id = (status & 0xFFFF0000) >> 16; if (if_id >= ethsw->sw_attr.num_ifs) { dev_err(dev, "Invalid if_id %d in IRQ status\n", if_id); - goto out; + goto out_clear; } port_priv = ethsw->ports[if_id]; @@ -1553,6 +1553,7 @@ static irqreturn_t dpaa2_switch_irq0_handler_thread(int irq_num, void *arg) dpaa2_switch_port_connect_mac(port_priv); } +out_clear: err = dpsw_clear_irq_status(ethsw->mc_io, 0, ethsw->dpsw_handle, DPSW_IRQ_INDEX_IF, status); if (err) diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 70768392912c..a146ceaf2ed6 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -3467,7 +3467,7 @@ static int enetc_int_vector_init(struct enetc_ndev_priv *priv, int i, priv->rx_ring[i] = bdr; err = __xdp_rxq_info_reg(&bdr->xdp.rxq, priv->ndev, i, 0, - ENETC_RXB_DMA_SIZE_XDP); + ENETC_RXB_TRUESIZE); if (err) goto free_vector; diff --git a/drivers/net/ethernet/intel/e1000e/defines.h b/drivers/net/ethernet/intel/e1000e/defines.h index ba331899d186..d4a1041e456d 100644 --- a/drivers/net/ethernet/intel/e1000e/defines.h +++ b/drivers/net/ethernet/intel/e1000e/defines.h @@ -33,6 +33,7 @@ /* Extended Device Control */ #define E1000_CTRL_EXT_LPCD 0x00000004 /* LCD Power Cycle Done */ +#define E1000_CTRL_EXT_DPG_EN 0x00000008 /* Dynamic Power Gating Enable */ #define E1000_CTRL_EXT_SDP3_DATA 0x00000080 /* Value of SW Definable Pin 3 */ #define E1000_CTRL_EXT_FORCE_SMBUS 0x00000800 /* Force SMBus mode */ #define E1000_CTRL_EXT_EE_RST 0x00002000 /* Reinitialize from EEPROM */ diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h index aa08f397988e..63ebe00376f5 100644 --- a/drivers/net/ethernet/intel/e1000e/e1000.h +++ b/drivers/net/ethernet/intel/e1000e/e1000.h @@ -117,7 +117,8 @@ enum e1000_boards { board_pch_cnp, board_pch_tgp, board_pch_adp, - board_pch_mtp + board_pch_mtp, + board_pch_ptp }; struct e1000_ps_page { @@ -527,6 +528,7 @@ extern const struct e1000_info e1000_pch_cnp_info; extern const struct e1000_info e1000_pch_tgp_info; extern const struct e1000_info e1000_pch_adp_info; extern const struct e1000_info e1000_pch_mtp_info; +extern const struct e1000_info e1000_pch_ptp_info; extern const struct e1000_info e1000_es2_info; void e1000e_ptp_init(struct e1000_adapter *adapter); diff --git a/drivers/net/ethernet/intel/e1000e/hw.h b/drivers/net/ethernet/intel/e1000e/hw.h index fc8ed38aa095..c7ac599e5a7a 100644 --- a/drivers/net/ethernet/intel/e1000e/hw.h +++ b/drivers/net/ethernet/intel/e1000e/hw.h @@ -118,8 +118,6 @@ struct e1000_hw; #define E1000_DEV_ID_PCH_ARL_I219_V24 0x57A1 #define E1000_DEV_ID_PCH_PTP_I219_LM25 0x57B3 #define E1000_DEV_ID_PCH_PTP_I219_V25 0x57B4 -#define E1000_DEV_ID_PCH_PTP_I219_LM26 0x57B5 -#define E1000_DEV_ID_PCH_PTP_I219_V26 0x57B6 #define E1000_DEV_ID_PCH_PTP_I219_LM27 0x57B7 #define E1000_DEV_ID_PCH_PTP_I219_V27 0x57B8 #define E1000_DEV_ID_PCH_NVL_I219_LM29 0x57B9 diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index 0ff8688ac3b8..dea208db1be5 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -528,7 +528,7 @@ static s32 e1000_init_phy_params_pchlan(struct e1000_hw *hw) phy->id = e1000_phy_unknown; - if (hw->mac.type == e1000_pch_mtp) { + if (hw->mac.type == e1000_pch_mtp || hw->mac.type == e1000_pch_ptp) { phy->retry_count = 2; e1000e_enable_phy_retry(hw); } @@ -4932,6 +4932,15 @@ static s32 e1000_reset_hw_ich8lan(struct e1000_hw *hw) reg |= E1000_KABGTXD_BGSQLBIAS; ew32(KABGTXD, reg); + /* The hardware reset value of the DPG_EN bit is 1. + * Clear DPG_EN to prevent unexpected autonomous power gating. + */ + if (hw->mac.type >= e1000_pch_ptp) { + reg = er32(CTRL_EXT); + reg &= ~E1000_CTRL_EXT_DPG_EN; + ew32(CTRL_EXT, reg); + } + return 0; } @@ -6208,3 +6217,23 @@ const struct e1000_info e1000_pch_mtp_info = { .phy_ops = &ich8_phy_ops, .nvm_ops = &spt_nvm_ops, }; + +const struct e1000_info e1000_pch_ptp_info = { + .mac = e1000_pch_ptp, + .flags = FLAG_IS_ICH + | FLAG_HAS_WOL + | FLAG_HAS_HW_TIMESTAMP + | FLAG_HAS_CTRLEXT_ON_LOAD + | FLAG_HAS_AMT + | FLAG_HAS_FLASH + | FLAG_HAS_JUMBO_FRAMES + | FLAG_APME_IN_WUC, + .flags2 = FLAG2_HAS_PHY_STATS + | FLAG2_HAS_EEE, + .pba = 26, + .max_hw_frame_size = 9022, + .get_variants = e1000_get_variants_ich8lan, + .mac_ops = &ich8_mac_ops, + .phy_ops = &ich8_phy_ops, + .nvm_ops = &spt_nvm_ops, +}; diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index fd4b117ed20f..35dab1e3132f 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -55,6 +55,7 @@ static const struct e1000_info *e1000_info_tbl[] = { [board_pch_tgp] = &e1000_pch_tgp_info, [board_pch_adp] = &e1000_pch_adp_info, [board_pch_mtp] = &e1000_pch_mtp_info, + [board_pch_ptp] = &e1000_pch_ptp_info, }; struct e1000_reg_info { @@ -7922,14 +7923,12 @@ static const struct pci_device_id e1000_pci_tbl[] = { { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_V21), board_pch_mtp }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ARL_I219_LM24), board_pch_mtp }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ARL_I219_V24), board_pch_mtp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_LM25), board_pch_mtp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_V25), board_pch_mtp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_LM26), board_pch_mtp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_V26), board_pch_mtp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_LM27), board_pch_mtp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_V27), board_pch_mtp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_NVL_I219_LM29), board_pch_mtp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_NVL_I219_V29), board_pch_mtp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_LM25), board_pch_ptp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_V25), board_pch_ptp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_LM27), board_pch_ptp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_V27), board_pch_ptp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_NVL_I219_LM29), board_pch_ptp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_NVL_I219_V29), board_pch_ptp }, { 0, 0, 0, 0, 0, 0, 0 } /* terminate list */ }; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 7b9e147d7365..926d001b2150 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -3569,6 +3569,7 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) u16 pf_q = vsi->base_queue + ring->queue_index; struct i40e_hw *hw = &vsi->back->hw; struct i40e_hmc_obj_rxq rx_ctx; + u32 xdp_frame_sz; int err = 0; bool ok; @@ -3578,49 +3579,47 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) memset(&rx_ctx, 0, sizeof(rx_ctx)); ring->rx_buf_len = vsi->rx_buf_len; + xdp_frame_sz = i40e_rx_pg_size(ring) / 2; /* XDP RX-queue info only needed for RX rings exposed to XDP */ if (ring->vsi->type != I40E_VSI_MAIN) goto skip; - if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) { - err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, - ring->queue_index, - ring->q_vector->napi.napi_id, - ring->rx_buf_len); - if (err) - return err; - } - ring->xsk_pool = i40e_xsk_pool(ring); if (ring->xsk_pool) { - xdp_rxq_info_unreg(&ring->xdp_rxq); + xdp_frame_sz = xsk_pool_get_rx_frag_step(ring->xsk_pool); ring->rx_buf_len = xsk_pool_get_rx_frame_size(ring->xsk_pool); err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, ring->queue_index, ring->q_vector->napi.napi_id, - ring->rx_buf_len); + xdp_frame_sz); if (err) return err; err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, MEM_TYPE_XSK_BUFF_POOL, NULL); if (err) - return err; + goto unreg_xdp; dev_info(&vsi->back->pdev->dev, "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n", ring->queue_index); } else { + err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, + ring->queue_index, + ring->q_vector->napi.napi_id, + xdp_frame_sz); + if (err) + return err; err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, MEM_TYPE_PAGE_SHARED, NULL); if (err) - return err; + goto unreg_xdp; } skip: - xdp_init_buff(&ring->xdp, i40e_rx_pg_size(ring) / 2, &ring->xdp_rxq); + xdp_init_buff(&ring->xdp, xdp_frame_sz, &ring->xdp_rxq); rx_ctx.dbuff = DIV_ROUND_UP(ring->rx_buf_len, BIT_ULL(I40E_RXQ_CTX_DBUFF_SHIFT)); @@ -3654,7 +3653,8 @@ skip: dev_info(&vsi->back->pdev->dev, "Failed to clear LAN Rx queue context on Rx ring %d (pf_q %d), error: %d\n", ring->queue_index, pf_q, err); - return -ENOMEM; + err = -ENOMEM; + goto unreg_xdp; } /* set the context in the HMC */ @@ -3663,7 +3663,8 @@ skip: dev_info(&vsi->back->pdev->dev, "Failed to set LAN Rx queue context on Rx ring %d (pf_q %d), error: %d\n", ring->queue_index, pf_q, err); - return -ENOMEM; + err = -ENOMEM; + goto unreg_xdp; } /* configure Rx buffer alignment */ @@ -3671,7 +3672,8 @@ skip: if (I40E_2K_TOO_SMALL_WITH_PADDING) { dev_info(&vsi->back->pdev->dev, "2k Rx buffer is too small to fit standard MTU and skb_shared_info\n"); - return -EOPNOTSUPP; + err = -EOPNOTSUPP; + goto unreg_xdp; } clear_ring_build_skb_enabled(ring); } else { @@ -3701,6 +3703,11 @@ skip: } return 0; +unreg_xdp: + if (ring->vsi->type == I40E_VSI_MAIN) + xdp_rxq_info_unreg(&ring->xdp_rxq); + + return err; } /** diff --git a/drivers/net/ethernet/intel/i40e/i40e_trace.h b/drivers/net/ethernet/intel/i40e/i40e_trace.h index 759f3d1c4c8f..dde0ccd789ed 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_trace.h +++ b/drivers/net/ethernet/intel/i40e/i40e_trace.h @@ -88,7 +88,7 @@ TRACE_EVENT(i40e_napi_poll, __entry->rx_clean_complete = rx_clean_complete; __entry->tx_clean_complete = tx_clean_complete; __entry->irq_num = q->irq_num; - __entry->curr_cpu = get_cpu(); + __entry->curr_cpu = smp_processor_id(); __assign_str(qname); __assign_str(dev_name); __assign_bitmask(irq_affinity, cpumask_bits(&q->affinity_mask), diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 34db7d8866b0..894f2d06d39d 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -1470,6 +1470,9 @@ void i40e_clean_rx_ring(struct i40e_ring *rx_ring) if (!rx_ring->rx_bi) return; + if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq)) + xdp_rxq_info_unreg(&rx_ring->xdp_rxq); + if (rx_ring->xsk_pool) { i40e_xsk_clean_rx_ring(rx_ring); goto skip_free; @@ -1527,8 +1530,6 @@ skip_free: void i40e_free_rx_resources(struct i40e_ring *rx_ring) { i40e_clean_rx_ring(rx_ring); - if (rx_ring->vsi->type == I40E_VSI_MAIN) - xdp_rxq_info_unreg(&rx_ring->xdp_rxq); rx_ring->xdp_prog = NULL; kfree(rx_ring->rx_bi); rx_ring->rx_bi = NULL; diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index bceaf4b1b85d..86c1964f42e1 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -2793,7 +2793,22 @@ static void iavf_init_config_adapter(struct iavf_adapter *adapter) netdev->watchdog_timeo = 5 * HZ; netdev->min_mtu = ETH_MIN_MTU; - netdev->max_mtu = LIBIE_MAX_MTU; + + /* PF/VF API: vf_res->max_mtu is max frame size (not MTU). + * Convert to MTU. + */ + if (!adapter->vf_res->max_mtu) { + netdev->max_mtu = LIBIE_MAX_MTU; + } else if (adapter->vf_res->max_mtu < LIBETH_RX_LL_LEN + ETH_MIN_MTU || + adapter->vf_res->max_mtu > + LIBETH_RX_LL_LEN + LIBIE_MAX_MTU) { + netdev_warn_once(adapter->netdev, + "invalid max frame size %d from PF, using default MTU %d", + adapter->vf_res->max_mtu, LIBIE_MAX_MTU); + netdev->max_mtu = LIBIE_MAX_MTU; + } else { + netdev->max_mtu = adapter->vf_res->max_mtu - LIBETH_RX_LL_LEN; + } if (!is_valid_ether_addr(adapter->hw.mac.addr)) { dev_info(&pdev->dev, "Invalid MAC address %pM, using random\n", diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index def7efa15447..2b2b22af42be 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -987,6 +987,7 @@ int ice_schedule_reset(struct ice_pf *pf, enum ice_reset_req reset); void ice_print_link_msg(struct ice_vsi *vsi, bool isup); int ice_plug_aux_dev(struct ice_pf *pf); void ice_unplug_aux_dev(struct ice_pf *pf); +void ice_rdma_finalize_setup(struct ice_pf *pf); int ice_init_rdma(struct ice_pf *pf); void ice_deinit_rdma(struct ice_pf *pf); bool ice_is_wol_supported(struct ice_hw *hw); diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index eb77dfa934aa..1667f686ff75 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -124,6 +124,8 @@ static int ice_vsi_alloc_q_vector(struct ice_vsi *vsi, u16 v_idx) if (vsi->type == ICE_VSI_VF) { ice_calc_vf_reg_idx(vsi->vf, q_vector); goto out; + } else if (vsi->type == ICE_VSI_LB) { + goto skip_alloc; } else if (vsi->type == ICE_VSI_CTRL && vsi->vf) { struct ice_vsi *ctrl_vsi = ice_get_vf_ctrl_vsi(pf, vsi); @@ -659,33 +661,22 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) { struct device *dev = ice_pf_to_dev(ring->vsi->back); u32 num_bufs = ICE_DESC_UNUSED(ring); - u32 rx_buf_len; int err; - if (ring->vsi->type == ICE_VSI_PF || ring->vsi->type == ICE_VSI_SF) { - if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) { - err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, - ring->q_index, - ring->q_vector->napi.napi_id, - ring->rx_buf_len); - if (err) - return err; - } - + if (ring->vsi->type == ICE_VSI_PF || ring->vsi->type == ICE_VSI_SF || + ring->vsi->type == ICE_VSI_LB) { ice_rx_xsk_pool(ring); err = ice_realloc_rx_xdp_bufs(ring, ring->xsk_pool); if (err) return err; if (ring->xsk_pool) { - xdp_rxq_info_unreg(&ring->xdp_rxq); - - rx_buf_len = - xsk_pool_get_rx_frame_size(ring->xsk_pool); + u32 frag_size = + xsk_pool_get_rx_frag_step(ring->xsk_pool); err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, ring->q_index, ring->q_vector->napi.napi_id, - rx_buf_len); + frag_size); if (err) return err; err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, @@ -702,14 +693,13 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) if (err) return err; - if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) { - err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, - ring->q_index, - ring->q_vector->napi.napi_id, - ring->rx_buf_len); - if (err) - goto err_destroy_fq; - } + err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, + ring->q_index, + ring->q_vector->napi.napi_id, + ring->truesize); + if (err) + goto err_destroy_fq; + xdp_rxq_info_attach_page_pool(&ring->xdp_rxq, ring->pp); } diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 6cd63190f55d..ce11fea122d0 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -1816,6 +1816,7 @@ static bool ice_should_retry_sq_send_cmd(u16 opcode) case ice_aqc_opc_lldp_stop: case ice_aqc_opc_lldp_start: case ice_aqc_opc_lldp_filter_ctrl: + case ice_aqc_opc_sff_eeprom: return true; } @@ -1841,6 +1842,7 @@ ice_sq_send_cmd_retry(struct ice_hw *hw, struct ice_ctl_q_info *cq, { struct libie_aq_desc desc_cpy; bool is_cmd_for_retry; + u8 *buf_cpy = NULL; u8 idx = 0; u16 opcode; int status; @@ -1850,8 +1852,11 @@ ice_sq_send_cmd_retry(struct ice_hw *hw, struct ice_ctl_q_info *cq, memset(&desc_cpy, 0, sizeof(desc_cpy)); if (is_cmd_for_retry) { - /* All retryable cmds are direct, without buf. */ - WARN_ON(buf); + if (buf) { + buf_cpy = kmemdup(buf, buf_size, GFP_KERNEL); + if (!buf_cpy) + return -ENOMEM; + } memcpy(&desc_cpy, desc, sizeof(desc_cpy)); } @@ -1863,12 +1868,14 @@ ice_sq_send_cmd_retry(struct ice_hw *hw, struct ice_ctl_q_info *cq, hw->adminq.sq_last_status != LIBIE_AQ_RC_EBUSY) break; + if (buf_cpy) + memcpy(buf, buf_cpy, buf_size); memcpy(desc, &desc_cpy, sizeof(desc_cpy)); - msleep(ICE_SQ_SEND_DELAY_TIME_MS); } while (++idx < ICE_SQ_SEND_MAX_EXECUTE); + kfree(buf_cpy); return status; } @@ -6391,7 +6398,7 @@ int ice_lldp_fltr_add_remove(struct ice_hw *hw, struct ice_vsi *vsi, bool add) struct ice_aqc_lldp_filter_ctrl *cmd; struct libie_aq_desc desc; - if (vsi->type != ICE_VSI_PF || !ice_fw_supports_lldp_fltr_ctrl(hw)) + if (!ice_fw_supports_lldp_fltr_ctrl(hw)) return -EOPNOTSUPP; cmd = libie_aq_raw(&desc); diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 0ea64b330614..301947d53ede 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -1289,6 +1289,10 @@ static u64 ice_loopback_test(struct net_device *netdev) test_vsi->netdev = netdev; tx_ring = test_vsi->tx_rings[0]; rx_ring = test_vsi->rx_rings[0]; + /* Dummy q_vector and napi. Fill the minimum required for + * ice_rxq_pp_create(). + */ + rx_ring->q_vector->napi.dev = netdev; if (ice_lbtest_prepare_rings(test_vsi)) { ret = 2; @@ -3328,7 +3332,7 @@ process_rx: rx_rings = kzalloc_objs(*rx_rings, vsi->num_rxq); if (!rx_rings) { err = -ENOMEM; - goto done; + goto free_xdp; } ice_for_each_rxq(vsi, i) { @@ -3338,6 +3342,7 @@ process_rx: rx_rings[i].cached_phctime = pf->ptp.cached_phc_time; rx_rings[i].desc = NULL; rx_rings[i].xdp_buf = NULL; + rx_rings[i].xdp_rxq = (struct xdp_rxq_info){ }; /* this is to allow wr32 to have something to write to * during early allocation of Rx buffers @@ -3355,7 +3360,7 @@ rx_unwind: } kfree(rx_rings); err = -ENOMEM; - goto free_tx; + goto free_xdp; } } @@ -3407,6 +3412,13 @@ process_link: } goto done; +free_xdp: + if (xdp_rings) { + ice_for_each_xdp_txq(vsi, i) + ice_free_tx_ring(&xdp_rings[i]); + kfree(xdp_rings); + } + free_tx: /* error cleanup if the Rx allocations failed after getting Tx */ if (tx_rings) { @@ -4505,7 +4517,7 @@ ice_get_module_eeprom(struct net_device *netdev, u8 addr = ICE_I2C_EEPROM_DEV_ADDR; struct ice_hw *hw = &pf->hw; bool is_sfp = false; - unsigned int i, j; + unsigned int i; u16 offset = 0; u8 page = 0; int status; @@ -4547,26 +4559,19 @@ ice_get_module_eeprom(struct net_device *netdev, if (page == 0 || !(data[0x2] & 0x4)) { u32 copy_len; - /* If i2c bus is busy due to slow page change or - * link management access, call can fail. This is normal. - * So we retry this a few times. - */ - for (j = 0; j < 4; j++) { - status = ice_aq_sff_eeprom(hw, 0, addr, offset, page, - !is_sfp, value, - SFF_READ_BLOCK_SIZE, - 0, NULL); - netdev_dbg(netdev, "SFF %02X %02X %02X %X = %02X%02X%02X%02X.%02X%02X%02X%02X (%X)\n", - addr, offset, page, is_sfp, - value[0], value[1], value[2], value[3], - value[4], value[5], value[6], value[7], - status); - if (status) { - usleep_range(1500, 2500); - memset(value, 0, SFF_READ_BLOCK_SIZE); - continue; - } - break; + status = ice_aq_sff_eeprom(hw, 0, addr, offset, page, + !is_sfp, value, + SFF_READ_BLOCK_SIZE, + 0, NULL); + netdev_dbg(netdev, "SFF %02X %02X %02X %X = %02X%02X%02X%02X.%02X%02X%02X%02X (%pe)\n", + addr, offset, page, is_sfp, + value[0], value[1], value[2], value[3], + value[4], value[5], value[6], value[7], + ERR_PTR(status)); + if (status) { + netdev_err(netdev, "%s: error reading module EEPROM: status %pe\n", + __func__, ERR_PTR(status)); + return status; } /* Make sure we have enough room for the new block */ diff --git a/drivers/net/ethernet/intel/ice/ice_idc.c b/drivers/net/ethernet/intel/ice/ice_idc.c index 3572b0e1d49f..102d63c3018b 100644 --- a/drivers/net/ethernet/intel/ice/ice_idc.c +++ b/drivers/net/ethernet/intel/ice/ice_idc.c @@ -361,6 +361,39 @@ void ice_unplug_aux_dev(struct ice_pf *pf) } /** + * ice_rdma_finalize_setup - Complete RDMA setup after VSI is ready + * @pf: ptr to ice_pf + * + * Sets VSI-dependent information and plugs aux device. + * Must be called after ice_init_rdma(), ice_vsi_rebuild(), and + * ice_dcb_rebuild() complete. + */ +void ice_rdma_finalize_setup(struct ice_pf *pf) +{ + struct device *dev = ice_pf_to_dev(pf); + struct iidc_rdma_priv_dev_info *privd; + int ret; + + if (!ice_is_rdma_ena(pf) || !pf->cdev_info) + return; + + privd = pf->cdev_info->iidc_priv; + if (!privd || !pf->vsi || !pf->vsi[0] || !pf->vsi[0]->netdev) + return; + + /* Assign VSI info now that VSI is valid */ + privd->netdev = pf->vsi[0]->netdev; + privd->vport_id = pf->vsi[0]->vsi_num; + + /* Update QoS info after DCB has been rebuilt */ + ice_setup_dcb_qos_info(pf, &privd->qos_info); + + ret = ice_plug_aux_dev(pf); + if (ret) + dev_warn(dev, "Failed to plug RDMA aux device: %d\n", ret); +} + +/** * ice_init_rdma - initializes PF for RDMA use * @pf: ptr to ice_pf */ @@ -398,22 +431,14 @@ int ice_init_rdma(struct ice_pf *pf) } cdev->iidc_priv = privd; - privd->netdev = pf->vsi[0]->netdev; privd->hw_addr = (u8 __iomem *)pf->hw.hw_addr; cdev->pdev = pf->pdev; - privd->vport_id = pf->vsi[0]->vsi_num; pf->cdev_info->rdma_protocol |= IIDC_RDMA_PROTOCOL_ROCEV2; - ice_setup_dcb_qos_info(pf, &privd->qos_info); - ret = ice_plug_aux_dev(pf); - if (ret) - goto err_plug_aux_dev; + return 0; -err_plug_aux_dev: - pf->cdev_info->adev = NULL; - xa_erase(&ice_aux_id, pf->aux_idx); err_alloc_xa: kfree(privd); err_privd_alloc: @@ -432,7 +457,6 @@ void ice_deinit_rdma(struct ice_pf *pf) if (!ice_is_rdma_ena(pf)) return; - ice_unplug_aux_dev(pf); xa_erase(&ice_aux_id, pf->aux_idx); kfree(pf->cdev_info->iidc_priv); kfree(pf->cdev_info); diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index f91f8b672b02..689c6025ea82 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -107,10 +107,6 @@ static int ice_vsi_alloc_arrays(struct ice_vsi *vsi) if (!vsi->rxq_map) goto err_rxq_map; - /* There is no need to allocate q_vectors for a loopback VSI. */ - if (vsi->type == ICE_VSI_LB) - return 0; - /* allocate memory for q_vector pointers */ vsi->q_vectors = devm_kcalloc(dev, vsi->num_q_vectors, sizeof(*vsi->q_vectors), GFP_KERNEL); @@ -241,6 +237,8 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi) case ICE_VSI_LB: vsi->alloc_txq = 1; vsi->alloc_rxq = 1; + /* A dummy q_vector, no actual IRQ. */ + vsi->num_q_vectors = 1; break; default: dev_warn(ice_pf_to_dev(pf), "Unknown VSI type %d\n", vsi_type); @@ -2426,14 +2424,21 @@ static int ice_vsi_cfg_def(struct ice_vsi *vsi) } break; case ICE_VSI_LB: - ret = ice_vsi_alloc_rings(vsi); + ret = ice_vsi_alloc_q_vectors(vsi); if (ret) goto unroll_vsi_init; + ret = ice_vsi_alloc_rings(vsi); + if (ret) + goto unroll_alloc_q_vector; + ret = ice_vsi_alloc_ring_stats(vsi); if (ret) goto unroll_vector_base; + /* Simply map the dummy q_vector to the only rx_ring */ + vsi->rx_rings[0]->q_vector = vsi->q_vectors[0]; + break; default: /* clean up the resources and exit */ diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index ebf48feffb30..e7308e381e2f 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -5138,6 +5138,9 @@ int ice_load(struct ice_pf *pf) if (err) goto err_init_rdma; + /* Finalize RDMA: VSI already created, assign info and plug device */ + ice_rdma_finalize_setup(pf); + ice_service_task_restart(pf); clear_bit(ICE_DOWN, pf->state); @@ -5169,6 +5172,7 @@ void ice_unload(struct ice_pf *pf) devl_assert_locked(priv_to_devlink(pf)); + ice_unplug_aux_dev(pf); ice_deinit_rdma(pf); ice_deinit_features(pf); ice_tc_indir_block_unregister(vsi); @@ -5595,6 +5599,7 @@ static int ice_suspend(struct device *dev) */ disabled = ice_service_task_stop(pf); + ice_unplug_aux_dev(pf); ice_deinit_rdma(pf); /* Already suspended?, then there is nothing to do */ @@ -7859,7 +7864,7 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) ice_health_clear(pf); - ice_plug_aux_dev(pf); + ice_rdma_finalize_setup(pf); if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG)) ice_lag_rebuild(pf); diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index a5bbce68f76c..a2cd4cf37734 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -560,7 +560,9 @@ void ice_clean_rx_ring(struct ice_rx_ring *rx_ring) i = 0; } - if (rx_ring->vsi->type == ICE_VSI_PF && + if ((rx_ring->vsi->type == ICE_VSI_PF || + rx_ring->vsi->type == ICE_VSI_SF || + rx_ring->vsi->type == ICE_VSI_LB) && xdp_rxq_info_is_reg(&rx_ring->xdp_rxq)) { xdp_rxq_info_detach_mem_model(&rx_ring->xdp_rxq); xdp_rxq_info_unreg(&rx_ring->xdp_rxq); diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index c673094663a3..0643017541c3 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -899,6 +899,9 @@ void ice_xsk_clean_rx_ring(struct ice_rx_ring *rx_ring) u16 ntc = rx_ring->next_to_clean; u16 ntu = rx_ring->next_to_use; + if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq)) + xdp_rxq_info_unreg(&rx_ring->xdp_rxq); + while (ntc != ntu) { struct xdp_buff *xdp = *ice_xdp_buf(rx_ring, ntc); diff --git a/drivers/net/ethernet/intel/idpf/idpf_ethtool.c b/drivers/net/ethernet/intel/idpf/idpf_ethtool.c index 40e08a71d2d3..bb99d9e7c65d 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_ethtool.c +++ b/drivers/net/ethernet/intel/idpf/idpf_ethtool.c @@ -307,9 +307,6 @@ static int idpf_del_flow_steer(struct net_device *netdev, vport_config = vport->adapter->vport_config[np->vport_idx]; user_config = &vport_config->user_config; - if (!idpf_sideband_action_ena(vport, fsp)) - return -EOPNOTSUPP; - rule = kzalloc_flex(*rule, rule_info, 1); if (!rule) return -ENOMEM; diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c index de3df705a7e6..cf966fe6c759 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_lib.c +++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c @@ -1318,6 +1318,7 @@ static struct idpf_vport *idpf_vport_alloc(struct idpf_adapter *adapter, free_rss_key: kfree(rss_data->rss_key); + rss_data->rss_key = NULL; free_qreg_chunks: idpf_vport_deinit_queue_reg_chunks(adapter->vport_config[idx]); free_vector_idxs: diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c index 05a162094d10..252259993022 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c @@ -1314,6 +1314,9 @@ static void idpf_txq_group_rel(struct idpf_q_vec_rsrc *rsrc) struct idpf_txq_group *txq_grp = &rsrc->txq_grps[i]; for (unsigned int j = 0; j < txq_grp->num_txq; j++) { + if (!txq_grp->txqs[j]) + continue; + if (idpf_queue_has(FLOW_SCH_EN, txq_grp->txqs[j])) { kfree(txq_grp->txqs[j]->refillq); txq_grp->txqs[j]->refillq = NULL; @@ -1339,6 +1342,9 @@ static void idpf_txq_group_rel(struct idpf_q_vec_rsrc *rsrc) */ static void idpf_rxq_sw_queue_rel(struct idpf_rxq_group *rx_qgrp) { + if (!rx_qgrp->splitq.bufq_sets) + return; + for (unsigned int i = 0; i < rx_qgrp->splitq.num_bufq_sets; i++) { struct idpf_bufq_set *bufq_set = &rx_qgrp->splitq.bufq_sets[i]; @@ -2336,7 +2342,7 @@ void idpf_wait_for_sw_marker_completion(const struct idpf_tx_queue *txq) do { struct idpf_splitq_4b_tx_compl_desc *tx_desc; - struct idpf_tx_queue *target; + struct idpf_tx_queue *target = NULL; u32 ctype_gen, id; tx_desc = flow ? &complq->comp[ntc].common : @@ -2356,14 +2362,14 @@ void idpf_wait_for_sw_marker_completion(const struct idpf_tx_queue *txq) target = complq->txq_grp->txqs[id]; idpf_queue_clear(SW_MARKER, target); - if (target == txq) - break; next: if (unlikely(++ntc == complq->desc_count)) { ntc = 0; gen_flag = !gen_flag; } + if (target == txq) + break; } while (time_before(jiffies, timeout)); idpf_queue_assign(GEN_CHK, complq, gen_flag); @@ -4059,7 +4065,7 @@ static int idpf_vport_intr_req_irq(struct idpf_vport *vport, continue; name = kasprintf(GFP_KERNEL, "%s-%s-%s-%d", drv_name, if_name, - vec_name, vidx); + vec_name, vector); err = request_irq(irq_num, idpf_vport_intr_clean_queues, 0, name, q_vector); diff --git a/drivers/net/ethernet/intel/idpf/xdp.c b/drivers/net/ethernet/intel/idpf/xdp.c index 6ac9c6624c2a..cbccd4546768 100644 --- a/drivers/net/ethernet/intel/idpf/xdp.c +++ b/drivers/net/ethernet/intel/idpf/xdp.c @@ -47,12 +47,16 @@ static int __idpf_xdp_rxq_info_init(struct idpf_rx_queue *rxq, void *arg) { const struct idpf_vport *vport = rxq->q_vector->vport; const struct idpf_q_vec_rsrc *rsrc; + u32 frag_size = 0; bool split; int err; + if (idpf_queue_has(XSK, rxq)) + frag_size = rxq->bufq_sets[0].bufq.truesize; + err = __xdp_rxq_info_reg(&rxq->xdp_rxq, vport->netdev, rxq->idx, rxq->q_vector->napi.napi_id, - rxq->rx_buf_size); + frag_size); if (err) return err; diff --git a/drivers/net/ethernet/intel/idpf/xsk.c b/drivers/net/ethernet/intel/idpf/xsk.c index 676cbd80774d..d95d3efdfd36 100644 --- a/drivers/net/ethernet/intel/idpf/xsk.c +++ b/drivers/net/ethernet/intel/idpf/xsk.c @@ -403,6 +403,7 @@ int idpf_xskfq_init(struct idpf_buf_queue *bufq) bufq->pending = fq.pending; bufq->thresh = fq.thresh; bufq->rx_buf_size = fq.buf_len; + bufq->truesize = fq.truesize; if (!idpf_xskfq_refill(bufq)) netdev_err(bufq->pool->netdev, diff --git a/drivers/net/ethernet/intel/igb/igb_xsk.c b/drivers/net/ethernet/intel/igb/igb_xsk.c index 30ce5fbb5b77..ce4a7b58cad2 100644 --- a/drivers/net/ethernet/intel/igb/igb_xsk.c +++ b/drivers/net/ethernet/intel/igb/igb_xsk.c @@ -524,6 +524,16 @@ bool igb_xmit_zc(struct igb_ring *tx_ring, struct xsk_buff_pool *xsk_pool) return nb_pkts < budget; } +static u32 igb_sw_irq_prep(struct igb_q_vector *q_vector) +{ + u32 eics = 0; + + if (!napi_if_scheduled_mark_missed(&q_vector->napi)) + eics = q_vector->eims_value; + + return eics; +} + int igb_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags) { struct igb_adapter *adapter = netdev_priv(dev); @@ -542,20 +552,32 @@ int igb_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags) ring = adapter->tx_ring[qid]; - if (test_bit(IGB_RING_FLAG_TX_DISABLED, &ring->flags)) - return -ENETDOWN; - if (!READ_ONCE(ring->xsk_pool)) return -EINVAL; - if (!napi_if_scheduled_mark_missed(&ring->q_vector->napi)) { + if (flags & XDP_WAKEUP_TX) { + if (test_bit(IGB_RING_FLAG_TX_DISABLED, &ring->flags)) + return -ENETDOWN; + + eics |= igb_sw_irq_prep(ring->q_vector); + } + + if (flags & XDP_WAKEUP_RX) { + /* If IGB_FLAG_QUEUE_PAIRS is active, the q_vector + * and NAPI is shared between RX and TX. + * If NAPI is already running it would be marked as missed + * from the TX path, making this RX call a NOP + */ + ring = adapter->rx_ring[qid]; + eics |= igb_sw_irq_prep(ring->q_vector); + } + + if (eics) { /* Cause software interrupt */ - if (adapter->flags & IGB_FLAG_HAS_MSIX) { - eics |= ring->q_vector->eims_value; + if (adapter->flags & IGB_FLAG_HAS_MSIX) wr32(E1000_EICS, eics); - } else { + else wr32(E1000_ICS, E1000_ICS_RXDMT0); - } } return 0; diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 27e5c2109138..b2e8d0c0f827 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -6906,28 +6906,29 @@ static int igc_xdp_xmit(struct net_device *dev, int num_frames, return nxmit; } -static void igc_trigger_rxtxq_interrupt(struct igc_adapter *adapter, - struct igc_q_vector *q_vector) +static u32 igc_sw_irq_prep(struct igc_q_vector *q_vector) { - struct igc_hw *hw = &adapter->hw; u32 eics = 0; - eics |= q_vector->eims_value; - wr32(IGC_EICS, eics); + if (!napi_if_scheduled_mark_missed(&q_vector->napi)) + eics = q_vector->eims_value; + + return eics; } int igc_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags) { struct igc_adapter *adapter = netdev_priv(dev); - struct igc_q_vector *q_vector; + struct igc_hw *hw = &adapter->hw; struct igc_ring *ring; + u32 eics = 0; if (test_bit(__IGC_DOWN, &adapter->state)) return -ENETDOWN; if (!igc_xdp_is_enabled(adapter)) return -ENXIO; - + /* Check if queue_id is valid. Tx and Rx queue numbers are always same */ if (queue_id >= adapter->num_rx_queues) return -EINVAL; @@ -6936,9 +6937,22 @@ int igc_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags) if (!ring->xsk_pool) return -ENXIO; - q_vector = adapter->q_vector[queue_id]; - if (!napi_if_scheduled_mark_missed(&q_vector->napi)) - igc_trigger_rxtxq_interrupt(adapter, q_vector); + if (flags & XDP_WAKEUP_RX) + eics |= igc_sw_irq_prep(ring->q_vector); + + if (flags & XDP_WAKEUP_TX) { + /* If IGC_FLAG_QUEUE_PAIRS is active, the q_vector + * and NAPI is shared between RX and TX. + * If NAPI is already running it would be marked as missed + * from the RX path, making this TX call a NOP + */ + ring = adapter->tx_ring[queue_id]; + eics |= igc_sw_irq_prep(ring->q_vector); + } + + if (eics) + /* Cause software interrupt */ + wr32(IGC_EICS, eics); return 0; } diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c index 7aae83c108fd..44ee19386766 100644 --- a/drivers/net/ethernet/intel/igc/igc_ptp.c +++ b/drivers/net/ethernet/intel/igc/igc_ptp.c @@ -550,7 +550,8 @@ static void igc_ptp_free_tx_buffer(struct igc_adapter *adapter, tstamp->buffer_type = 0; /* Trigger txrx interrupt for transmit completion */ - igc_xsk_wakeup(adapter->netdev, tstamp->xsk_queue_index, 0); + igc_xsk_wakeup(adapter->netdev, tstamp->xsk_queue_index, + XDP_WAKEUP_TX); return; } diff --git a/drivers/net/ethernet/intel/ixgbevf/vf.c b/drivers/net/ethernet/intel/ixgbevf/vf.c index 74d320879513..b67b580f7f1c 100644 --- a/drivers/net/ethernet/intel/ixgbevf/vf.c +++ b/drivers/net/ethernet/intel/ixgbevf/vf.c @@ -852,7 +852,8 @@ static s32 ixgbevf_check_mac_link_vf(struct ixgbe_hw *hw, if (!mac->get_link_status) goto out; - if (hw->mac.type == ixgbe_mac_e610_vf) { + if (hw->mac.type == ixgbe_mac_e610_vf && + hw->api_version >= ixgbe_mbox_api_16) { ret_val = ixgbevf_get_pf_link_state(hw, speed, link_up); if (ret_val) goto out; diff --git a/drivers/net/ethernet/intel/libeth/xsk.c b/drivers/net/ethernet/intel/libeth/xsk.c index 846e902e31b6..4882951d5c9c 100644 --- a/drivers/net/ethernet/intel/libeth/xsk.c +++ b/drivers/net/ethernet/intel/libeth/xsk.c @@ -167,6 +167,7 @@ int libeth_xskfq_create(struct libeth_xskfq *fq) fq->pending = fq->count; fq->thresh = libeth_xdp_queue_threshold(fq->count); fq->buf_len = xsk_pool_get_rx_frame_size(fq->pool); + fq->truesize = xsk_pool_get_rx_frag_step(fq->pool); return 0; } diff --git a/drivers/net/ethernet/intel/libie/fwlog.c b/drivers/net/ethernet/intel/libie/fwlog.c index 79020d990859..4d0c8370386b 100644 --- a/drivers/net/ethernet/intel/libie/fwlog.c +++ b/drivers/net/ethernet/intel/libie/fwlog.c @@ -1049,6 +1049,10 @@ void libie_fwlog_deinit(struct libie_fwlog *fwlog) { int status; + /* if FW logging isn't supported it means no configuration was done */ + if (!libie_fwlog_supported(fwlog)) + return; + /* make sure FW logging is disabled to not put the FW in a weird state * for the next driver load */ diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c index ec55eb2a6c04..028dd55604ea 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c @@ -554,28 +554,43 @@ static void octep_clean_irqs(struct octep_device *oct) } /** - * octep_enable_ioq_irq() - Enable MSI-x interrupt of a Tx/Rx queue. + * octep_update_pkt() - Update IQ/OQ IN/OUT_CNT registers. * * @iq: Octeon Tx queue data structure. * @oq: Octeon Rx queue data structure. */ -static void octep_enable_ioq_irq(struct octep_iq *iq, struct octep_oq *oq) +static void octep_update_pkt(struct octep_iq *iq, struct octep_oq *oq) { - u32 pkts_pend = oq->pkts_pending; + u32 pkts_pend = READ_ONCE(oq->pkts_pending); + u32 last_pkt_count = READ_ONCE(oq->last_pkt_count); + u32 pkts_processed = READ_ONCE(iq->pkts_processed); + u32 pkt_in_done = READ_ONCE(iq->pkt_in_done); netdev_dbg(iq->netdev, "enabling intr for Q-%u\n", iq->q_no); - if (iq->pkts_processed) { - writel(iq->pkts_processed, iq->inst_cnt_reg); - iq->pkt_in_done -= iq->pkts_processed; - iq->pkts_processed = 0; + if (pkts_processed) { + writel(pkts_processed, iq->inst_cnt_reg); + readl(iq->inst_cnt_reg); + WRITE_ONCE(iq->pkt_in_done, (pkt_in_done - pkts_processed)); + WRITE_ONCE(iq->pkts_processed, 0); } - if (oq->last_pkt_count - pkts_pend) { - writel(oq->last_pkt_count - pkts_pend, oq->pkts_sent_reg); - oq->last_pkt_count = pkts_pend; + if (last_pkt_count - pkts_pend) { + writel(last_pkt_count - pkts_pend, oq->pkts_sent_reg); + readl(oq->pkts_sent_reg); + WRITE_ONCE(oq->last_pkt_count, pkts_pend); } /* Flush the previous wrties before writing to RESEND bit */ - wmb(); + smp_wmb(); +} + +/** + * octep_enable_ioq_irq() - Enable MSI-x interrupt of a Tx/Rx queue. + * + * @iq: Octeon Tx queue data structure. + * @oq: Octeon Rx queue data structure. + */ +static void octep_enable_ioq_irq(struct octep_iq *iq, struct octep_oq *oq) +{ writeq(1UL << OCTEP_OQ_INTR_RESEND_BIT, oq->pkts_sent_reg); writeq(1UL << OCTEP_IQ_INTR_RESEND_BIT, iq->inst_cnt_reg); } @@ -601,7 +616,8 @@ static int octep_napi_poll(struct napi_struct *napi, int budget) if (tx_pending || rx_done >= budget) return budget; - napi_complete(napi); + octep_update_pkt(ioq_vector->iq, ioq_vector->oq); + napi_complete_done(napi, rx_done); octep_enable_ioq_irq(ioq_vector->iq, ioq_vector->oq); return rx_done; } diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c b/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c index f2a7c6a76c74..74de19166488 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c @@ -324,10 +324,16 @@ static int octep_oq_check_hw_for_pkts(struct octep_device *oct, struct octep_oq *oq) { u32 pkt_count, new_pkts; + u32 last_pkt_count, pkts_pending; pkt_count = readl(oq->pkts_sent_reg); - new_pkts = pkt_count - oq->last_pkt_count; + last_pkt_count = READ_ONCE(oq->last_pkt_count); + new_pkts = pkt_count - last_pkt_count; + if (pkt_count < last_pkt_count) { + dev_err(oq->dev, "OQ-%u pkt_count(%u) < oq->last_pkt_count(%u)\n", + oq->q_no, pkt_count, last_pkt_count); + } /* Clear the hardware packets counter register if the rx queue is * being processed continuously with-in a single interrupt and * reached half its max value. @@ -338,8 +344,9 @@ static int octep_oq_check_hw_for_pkts(struct octep_device *oct, pkt_count = readl(oq->pkts_sent_reg); new_pkts += pkt_count; } - oq->last_pkt_count = pkt_count; - oq->pkts_pending += new_pkts; + WRITE_ONCE(oq->last_pkt_count, pkt_count); + pkts_pending = READ_ONCE(oq->pkts_pending); + WRITE_ONCE(oq->pkts_pending, (pkts_pending + new_pkts)); return new_pkts; } @@ -414,7 +421,7 @@ static int __octep_oq_process_rx(struct octep_device *oct, u16 rx_ol_flags; u32 read_idx; - read_idx = oq->host_read_idx; + read_idx = READ_ONCE(oq->host_read_idx); rx_bytes = 0; desc_used = 0; for (pkt = 0; pkt < pkts_to_process; pkt++) { @@ -499,7 +506,7 @@ static int __octep_oq_process_rx(struct octep_device *oct, napi_gro_receive(oq->napi, skb); } - oq->host_read_idx = read_idx; + WRITE_ONCE(oq->host_read_idx, read_idx); oq->refill_count += desc_used; oq->stats->packets += pkt; oq->stats->bytes += rx_bytes; @@ -522,22 +529,26 @@ int octep_oq_process_rx(struct octep_oq *oq, int budget) { u32 pkts_available, pkts_processed, total_pkts_processed; struct octep_device *oct = oq->octep_dev; + u32 pkts_pending; pkts_available = 0; pkts_processed = 0; total_pkts_processed = 0; while (total_pkts_processed < budget) { /* update pending count only when current one exhausted */ - if (oq->pkts_pending == 0) + pkts_pending = READ_ONCE(oq->pkts_pending); + if (pkts_pending == 0) octep_oq_check_hw_for_pkts(oct, oq); + pkts_pending = READ_ONCE(oq->pkts_pending); pkts_available = min(budget - total_pkts_processed, - oq->pkts_pending); + pkts_pending); if (!pkts_available) break; pkts_processed = __octep_oq_process_rx(oct, oq, pkts_available); - oq->pkts_pending -= pkts_processed; + pkts_pending = READ_ONCE(oq->pkts_pending); + WRITE_ONCE(oq->pkts_pending, (pkts_pending - pkts_processed)); total_pkts_processed += pkts_processed; } diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c index 562fe945b422..7f1b93cffb98 100644 --- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c +++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c @@ -286,28 +286,45 @@ static void octep_vf_clean_irqs(struct octep_vf_device *oct) } /** - * octep_vf_enable_ioq_irq() - Enable MSI-x interrupt of a Tx/Rx queue. + * octep_vf_update_pkt() - Update IQ/OQ IN/OUT_CNT registers. * * @iq: Octeon Tx queue data structure. * @oq: Octeon Rx queue data structure. */ -static void octep_vf_enable_ioq_irq(struct octep_vf_iq *iq, struct octep_vf_oq *oq) + +static void octep_vf_update_pkt(struct octep_vf_iq *iq, struct octep_vf_oq *oq) { - u32 pkts_pend = oq->pkts_pending; + u32 pkts_pend = READ_ONCE(oq->pkts_pending); + u32 last_pkt_count = READ_ONCE(oq->last_pkt_count); + u32 pkts_processed = READ_ONCE(iq->pkts_processed); + u32 pkt_in_done = READ_ONCE(iq->pkt_in_done); netdev_dbg(iq->netdev, "enabling intr for Q-%u\n", iq->q_no); - if (iq->pkts_processed) { - writel(iq->pkts_processed, iq->inst_cnt_reg); - iq->pkt_in_done -= iq->pkts_processed; - iq->pkts_processed = 0; + if (pkts_processed) { + writel(pkts_processed, iq->inst_cnt_reg); + readl(iq->inst_cnt_reg); + WRITE_ONCE(iq->pkt_in_done, (pkt_in_done - pkts_processed)); + WRITE_ONCE(iq->pkts_processed, 0); } - if (oq->last_pkt_count - pkts_pend) { - writel(oq->last_pkt_count - pkts_pend, oq->pkts_sent_reg); - oq->last_pkt_count = pkts_pend; + if (last_pkt_count - pkts_pend) { + writel(last_pkt_count - pkts_pend, oq->pkts_sent_reg); + readl(oq->pkts_sent_reg); + WRITE_ONCE(oq->last_pkt_count, pkts_pend); } /* Flush the previous wrties before writing to RESEND bit */ smp_wmb(); +} + +/** + * octep_vf_enable_ioq_irq() - Enable MSI-x interrupt of a Tx/Rx queue. + * + * @iq: Octeon Tx queue data structure. + * @oq: Octeon Rx queue data structure. + */ +static void octep_vf_enable_ioq_irq(struct octep_vf_iq *iq, + struct octep_vf_oq *oq) +{ writeq(1UL << OCTEP_VF_OQ_INTR_RESEND_BIT, oq->pkts_sent_reg); writeq(1UL << OCTEP_VF_IQ_INTR_RESEND_BIT, iq->inst_cnt_reg); } @@ -333,6 +350,7 @@ static int octep_vf_napi_poll(struct napi_struct *napi, int budget) if (tx_pending || rx_done >= budget) return budget; + octep_vf_update_pkt(ioq_vector->iq, ioq_vector->oq); if (likely(napi_complete_done(napi, rx_done))) octep_vf_enable_ioq_irq(ioq_vector->iq, ioq_vector->oq); diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.c b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.c index 6f865dbbba6c..b579d5b545c4 100644 --- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.c +++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.c @@ -325,9 +325,16 @@ static int octep_vf_oq_check_hw_for_pkts(struct octep_vf_device *oct, struct octep_vf_oq *oq) { u32 pkt_count, new_pkts; + u32 last_pkt_count, pkts_pending; pkt_count = readl(oq->pkts_sent_reg); - new_pkts = pkt_count - oq->last_pkt_count; + last_pkt_count = READ_ONCE(oq->last_pkt_count); + new_pkts = pkt_count - last_pkt_count; + + if (pkt_count < last_pkt_count) { + dev_err(oq->dev, "OQ-%u pkt_count(%u) < oq->last_pkt_count(%u)\n", + oq->q_no, pkt_count, last_pkt_count); + } /* Clear the hardware packets counter register if the rx queue is * being processed continuously with-in a single interrupt and @@ -339,8 +346,9 @@ static int octep_vf_oq_check_hw_for_pkts(struct octep_vf_device *oct, pkt_count = readl(oq->pkts_sent_reg); new_pkts += pkt_count; } - oq->last_pkt_count = pkt_count; - oq->pkts_pending += new_pkts; + WRITE_ONCE(oq->last_pkt_count, pkt_count); + pkts_pending = READ_ONCE(oq->pkts_pending); + WRITE_ONCE(oq->pkts_pending, (pkts_pending + new_pkts)); return new_pkts; } @@ -369,7 +377,7 @@ static int __octep_vf_oq_process_rx(struct octep_vf_device *oct, struct sk_buff *skb; u32 read_idx; - read_idx = oq->host_read_idx; + read_idx = READ_ONCE(oq->host_read_idx); rx_bytes = 0; desc_used = 0; for (pkt = 0; pkt < pkts_to_process; pkt++) { @@ -463,7 +471,7 @@ static int __octep_vf_oq_process_rx(struct octep_vf_device *oct, napi_gro_receive(oq->napi, skb); } - oq->host_read_idx = read_idx; + WRITE_ONCE(oq->host_read_idx, read_idx); oq->refill_count += desc_used; oq->stats->packets += pkt; oq->stats->bytes += rx_bytes; @@ -486,22 +494,26 @@ int octep_vf_oq_process_rx(struct octep_vf_oq *oq, int budget) { u32 pkts_available, pkts_processed, total_pkts_processed; struct octep_vf_device *oct = oq->octep_vf_dev; + u32 pkts_pending; pkts_available = 0; pkts_processed = 0; total_pkts_processed = 0; while (total_pkts_processed < budget) { /* update pending count only when current one exhausted */ - if (oq->pkts_pending == 0) + pkts_pending = READ_ONCE(oq->pkts_pending); + if (pkts_pending == 0) octep_vf_oq_check_hw_for_pkts(oct, oq); + pkts_pending = READ_ONCE(oq->pkts_pending); pkts_available = min(budget - total_pkts_processed, - oq->pkts_pending); + pkts_pending); if (!pkts_available) break; pkts_processed = __octep_vf_oq_process_rx(oct, oq, pkts_available); - oq->pkts_pending -= pkts_processed; + pkts_pending = READ_ONCE(oq->pkts_pending); + WRITE_ONCE(oq->pkts_pending, (pkts_pending - pkts_processed)); total_pkts_processed += pkts_processed; } diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index e5e2ffa9c542..ddc321a02fda 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -3748,12 +3748,21 @@ static int mtk_xdp_setup(struct net_device *dev, struct bpf_prog *prog, mtk_stop(dev); old_prog = rcu_replace_pointer(eth->prog, prog, lockdep_rtnl_is_held()); + + if (netif_running(dev) && need_update) { + int err; + + err = mtk_open(dev); + if (err) { + rcu_assign_pointer(eth->prog, old_prog); + + return err; + } + } + if (old_prog) bpf_prog_put(old_prog); - if (netif_running(dev) && need_update) - return mtk_open(dev); - return 0; } diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 933e9d681ded..9017e806ecda 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -1770,8 +1770,14 @@ static void mana_poll_tx_cq(struct mana_cq *cq) ndev = txq->ndev; apc = netdev_priv(ndev); + /* Limit CQEs polled to 4 wraparounds of the CQ to ensure the + * doorbell can be rung in time for the hardware's requirement + * of at least one doorbell ring every 8 wraparounds. + */ comp_read = mana_gd_poll_cq(cq->gdma_cq, completions, - CQE_POLLING_BUFFER); + min((cq->gdma_cq->queue_size / + COMP_ENTRY_SIZE) * 4, + CQE_POLLING_BUFFER)); if (comp_read < 1) return; @@ -2156,7 +2162,14 @@ static void mana_poll_rx_cq(struct mana_cq *cq) struct mana_rxq *rxq = cq->rxq; int comp_read, i; - comp_read = mana_gd_poll_cq(cq->gdma_cq, comp, CQE_POLLING_BUFFER); + /* Limit CQEs polled to 4 wraparounds of the CQ to ensure the + * doorbell can be rung in time for the hardware's requirement + * of at least one doorbell ring every 8 wraparounds. + */ + comp_read = mana_gd_poll_cq(cq->gdma_cq, comp, + min((cq->gdma_cq->queue_size / + COMP_ENTRY_SIZE) * 4, + CQE_POLLING_BUFFER)); WARN_ON_ONCE(comp_read > CQE_POLLING_BUFFER); rxq->xdp_flush = false; @@ -2201,11 +2214,11 @@ static int mana_cq_handler(void *context, struct gdma_queue *gdma_queue) mana_gd_ring_cq(gdma_queue, SET_ARM_BIT); cq->work_done_since_doorbell = 0; napi_complete_done(&cq->napi, w); - } else if (cq->work_done_since_doorbell > - cq->gdma_cq->queue_size / COMP_ENTRY_SIZE * 4) { + } else if (cq->work_done_since_doorbell >= + (cq->gdma_cq->queue_size / COMP_ENTRY_SIZE) * 4) { /* MANA hardware requires at least one doorbell ring every 8 * wraparounds of CQ even if there is no need to arm the CQ. - * This driver rings the doorbell as soon as we have exceeded + * This driver rings the doorbell as soon as it has processed * 4 wraparounds. */ mana_gd_ring_cq(gdma_queue, 0); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index 51c96a738151..33667a26708c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -323,6 +323,7 @@ struct stmmac_priv { void __iomem *ptpaddr; void __iomem *estaddr; unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; + unsigned int num_double_vlans; int sfty_irq; int sfty_ce_irq; int sfty_ue_irq; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index e00aa42a1961..6827c99bde8c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -156,6 +156,7 @@ static void stmmac_tx_timer_arm(struct stmmac_priv *priv, u32 queue); static void stmmac_flush_tx_descriptors(struct stmmac_priv *priv, int queue); static void stmmac_set_dma_operation_mode(struct stmmac_priv *priv, u32 txmode, u32 rxmode, u32 chan); +static int stmmac_vlan_restore(struct stmmac_priv *priv); #ifdef CONFIG_DEBUG_FS static const struct net_device_ops stmmac_netdev_ops; @@ -4107,6 +4108,8 @@ static int __stmmac_open(struct net_device *dev, phylink_start(priv->phylink); + stmmac_vlan_restore(priv); + ret = stmmac_request_irq(dev); if (ret) goto irq_error; @@ -6766,6 +6769,9 @@ static int stmmac_vlan_update(struct stmmac_priv *priv, bool is_double) hash = 0; } + if (!netif_running(priv->dev)) + return 0; + return stmmac_update_vlan_hash(priv, priv->hw, hash, pmatch, is_double); } @@ -6775,6 +6781,7 @@ static int stmmac_vlan_update(struct stmmac_priv *priv, bool is_double) static int stmmac_vlan_rx_add_vid(struct net_device *ndev, __be16 proto, u16 vid) { struct stmmac_priv *priv = netdev_priv(ndev); + unsigned int num_double_vlans; bool is_double = false; int ret; @@ -6786,7 +6793,8 @@ static int stmmac_vlan_rx_add_vid(struct net_device *ndev, __be16 proto, u16 vid is_double = true; set_bit(vid, priv->active_vlans); - ret = stmmac_vlan_update(priv, is_double); + num_double_vlans = priv->num_double_vlans + is_double; + ret = stmmac_vlan_update(priv, num_double_vlans); if (ret) { clear_bit(vid, priv->active_vlans); goto err_pm_put; @@ -6794,9 +6802,15 @@ static int stmmac_vlan_rx_add_vid(struct net_device *ndev, __be16 proto, u16 vid if (priv->hw->num_vlan) { ret = stmmac_add_hw_vlan_rx_fltr(priv, ndev, priv->hw, proto, vid); - if (ret) + if (ret) { + clear_bit(vid, priv->active_vlans); + stmmac_vlan_update(priv, priv->num_double_vlans); goto err_pm_put; + } } + + priv->num_double_vlans = num_double_vlans; + err_pm_put: pm_runtime_put(priv->device); @@ -6809,6 +6823,7 @@ err_pm_put: static int stmmac_vlan_rx_kill_vid(struct net_device *ndev, __be16 proto, u16 vid) { struct stmmac_priv *priv = netdev_priv(ndev); + unsigned int num_double_vlans; bool is_double = false; int ret; @@ -6820,14 +6835,23 @@ static int stmmac_vlan_rx_kill_vid(struct net_device *ndev, __be16 proto, u16 vi is_double = true; clear_bit(vid, priv->active_vlans); + num_double_vlans = priv->num_double_vlans - is_double; + ret = stmmac_vlan_update(priv, num_double_vlans); + if (ret) { + set_bit(vid, priv->active_vlans); + goto del_vlan_error; + } if (priv->hw->num_vlan) { ret = stmmac_del_hw_vlan_rx_fltr(priv, ndev, priv->hw, proto, vid); - if (ret) + if (ret) { + set_bit(vid, priv->active_vlans); + stmmac_vlan_update(priv, priv->num_double_vlans); goto del_vlan_error; + } } - ret = stmmac_vlan_update(priv, is_double); + priv->num_double_vlans = num_double_vlans; del_vlan_error: pm_runtime_put(priv->device); @@ -6835,6 +6859,23 @@ del_vlan_error: return ret; } +static int stmmac_vlan_restore(struct stmmac_priv *priv) +{ + int ret; + + if (!(priv->dev->features & NETIF_F_VLAN_FEATURES)) + return 0; + + if (priv->hw->num_vlan) + stmmac_restore_hw_vlan_rx_fltr(priv, priv->dev, priv->hw); + + ret = stmmac_vlan_update(priv, priv->num_double_vlans); + if (ret) + netdev_err(priv->dev, "Failed to restore VLANs\n"); + + return ret; +} + static int stmmac_bpf(struct net_device *dev, struct netdev_bpf *bpf) { struct stmmac_priv *priv = netdev_priv(dev); @@ -8259,10 +8300,10 @@ int stmmac_resume(struct device *dev) stmmac_init_coalesce(priv); phylink_rx_clk_stop_block(priv->phylink); stmmac_set_rx_mode(ndev); - - stmmac_restore_hw_vlan_rx_fltr(priv, ndev, priv->hw); phylink_rx_clk_stop_unblock(priv->phylink); + stmmac_vlan_restore(priv); + stmmac_enable_all_queues(priv); stmmac_enable_all_dma_irq(priv); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c index b18404dd5a8b..e24efe3bfedb 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c @@ -76,7 +76,9 @@ static int vlan_add_hw_rx_fltr(struct net_device *dev, } hw->vlan_filter[0] = vid; - vlan_write_single(dev, vid); + + if (netif_running(dev)) + vlan_write_single(dev, vid); return 0; } @@ -97,12 +99,15 @@ static int vlan_add_hw_rx_fltr(struct net_device *dev, return -EPERM; } - ret = vlan_write_filter(dev, hw, index, val); + if (netif_running(dev)) { + ret = vlan_write_filter(dev, hw, index, val); + if (ret) + return ret; + } - if (!ret) - hw->vlan_filter[index] = val; + hw->vlan_filter[index] = val; - return ret; + return 0; } static int vlan_del_hw_rx_fltr(struct net_device *dev, @@ -115,7 +120,9 @@ static int vlan_del_hw_rx_fltr(struct net_device *dev, if (hw->num_vlan == 1) { if ((hw->vlan_filter[0] & VLAN_TAG_VID) == vid) { hw->vlan_filter[0] = 0; - vlan_write_single(dev, 0); + + if (netif_running(dev)) + vlan_write_single(dev, 0); } return 0; } @@ -124,25 +131,23 @@ static int vlan_del_hw_rx_fltr(struct net_device *dev, for (i = 0; i < hw->num_vlan; i++) { if ((hw->vlan_filter[i] & VLAN_TAG_DATA_VEN) && ((hw->vlan_filter[i] & VLAN_TAG_DATA_VID) == vid)) { - ret = vlan_write_filter(dev, hw, i, 0); - if (!ret) - hw->vlan_filter[i] = 0; - else - return ret; + if (netif_running(dev)) { + ret = vlan_write_filter(dev, hw, i, 0); + if (ret) + return ret; + } + + hw->vlan_filter[i] = 0; } } - return ret; + return 0; } static void vlan_restore_hw_rx_fltr(struct net_device *dev, struct mac_device_info *hw) { - void __iomem *ioaddr = hw->pcsr; - u32 value; - u32 hash; - u32 val; int i; /* Single Rx VLAN Filter */ @@ -152,19 +157,8 @@ static void vlan_restore_hw_rx_fltr(struct net_device *dev, } /* Extended Rx VLAN Filter Enable */ - for (i = 0; i < hw->num_vlan; i++) { - if (hw->vlan_filter[i] & VLAN_TAG_DATA_VEN) { - val = hw->vlan_filter[i]; - vlan_write_filter(dev, hw, i, val); - } - } - - hash = readl(ioaddr + VLAN_HASH_TABLE); - if (hash & VLAN_VLHT) { - value = readl(ioaddr + VLAN_TAG); - value |= VLAN_VTHM; - writel(value, ioaddr + VLAN_TAG); - } + for (i = 0; i < hw->num_vlan; i++) + vlan_write_filter(dev, hw, i, hw->vlan_filter[i]); } static void vlan_update_hash(struct mac_device_info *hw, u32 hash, @@ -183,6 +177,10 @@ static void vlan_update_hash(struct mac_device_info *hw, u32 hash, value |= VLAN_EDVLP; value |= VLAN_ESVL; value |= VLAN_DOVLTC; + } else { + value &= ~VLAN_EDVLP; + value &= ~VLAN_ESVL; + value &= ~VLAN_DOVLTC; } writel(value, ioaddr + VLAN_TAG); @@ -193,6 +191,10 @@ static void vlan_update_hash(struct mac_device_info *hw, u32 hash, value |= VLAN_EDVLP; value |= VLAN_ESVL; value |= VLAN_DOVLTC; + } else { + value &= ~VLAN_EDVLP; + value &= ~VLAN_ESVL; + value &= ~VLAN_DOVLTC; } writel(value | perfect_match, ioaddr + VLAN_TAG); diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 5924db6be3fe..967918050433 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -391,7 +391,7 @@ static void am65_cpsw_nuss_ndo_slave_set_rx_mode(struct net_device *ndev) cpsw_ale_set_allmulti(common->ale, ndev->flags & IFF_ALLMULTI, port->port_id); - port_mask = ALE_PORT_HOST; + port_mask = BIT(port->port_id) | ALE_PORT_HOST; /* Clear all mcast from ALE */ cpsw_ale_flush_multicast(common->ale, port_mask, -1); diff --git a/drivers/net/ethernet/ti/cpsw_ale.c b/drivers/net/ethernet/ti/cpsw_ale.c index bb969dd435b4..be7b69319221 100644 --- a/drivers/net/ethernet/ti/cpsw_ale.c +++ b/drivers/net/ethernet/ti/cpsw_ale.c @@ -450,14 +450,13 @@ static void cpsw_ale_flush_mcast(struct cpsw_ale *ale, u32 *ale_entry, ale->port_mask_bits); if ((mask & port_mask) == 0) return; /* ports dont intersect, not interested */ - mask &= ~port_mask; + mask &= (~port_mask | ALE_PORT_HOST); - /* free if only remaining port is host port */ - if (mask) + if (mask == 0x0 || mask == ALE_PORT_HOST) + cpsw_ale_set_entry_type(ale_entry, ALE_TYPE_FREE); + else cpsw_ale_set_port_mask(ale_entry, mask, ale->port_mask_bits); - else - cpsw_ale_set_entry_type(ale_entry, ALE_TYPE_FREE); } int cpsw_ale_flush_multicast(struct cpsw_ale *ale, int port_mask, int vid) diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c index 0939994c932f..42a881bee109 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c @@ -273,6 +273,14 @@ static int prueth_emac_common_start(struct prueth *prueth) if (ret) goto disable_class; + /* Reset link state to force reconfiguration in + * emac_adjust_link(). Without this, if the link was already up + * before restart, emac_adjust_link() won't detect any state + * change and will skip critical configuration like writing + * speed to firmware. + */ + emac->link = 0; + mutex_lock(&emac->ndev->phydev->lock); emac_adjust_link(emac->ndev); mutex_unlock(&emac->ndev->phydev->lock); diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c index 2db116fb1a7c..3c9acd6e49e8 100644 --- a/drivers/net/netconsole.c +++ b/drivers/net/netconsole.c @@ -617,7 +617,7 @@ static ssize_t sysdata_release_enabled_show(struct config_item *item, bool release_enabled; dynamic_netconsole_mutex_lock(); - release_enabled = !!(nt->sysdata_fields & SYSDATA_TASKNAME); + release_enabled = !!(nt->sysdata_fields & SYSDATA_RELEASE); dynamic_netconsole_mutex_unlock(); return sysfs_emit(buf, "%d\n", release_enabled); diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 4af85728ac4f..0c83bbbea2e7 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -10054,6 +10054,7 @@ static const struct usb_device_id rtl8152_table[] = { { USB_DEVICE(VENDOR_ID_DLINK, 0xb301) }, { USB_DEVICE(VENDOR_ID_DELL, 0xb097) }, { USB_DEVICE(VENDOR_ID_ASUS, 0x1976) }, + { USB_DEVICE(VENDOR_ID_TRENDNET, 0xe02b) }, {} }; diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index 05558b6afecd..17c941aac32d 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -2130,6 +2130,11 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb) { struct ipv6hdr *pip6; + /* check if nd_tbl is not initiliazed due to + * ipv6.disable=1 set during boot + */ + if (!ipv6_stub->nd_tbl) + return false; if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) return false; pip6 = ipv6_hdr(skb); diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c index c6b88909b6b7..b253d1e3f405 100644 --- a/drivers/net/wireless/ath/ath12k/mac.c +++ b/drivers/net/wireless/ath/ath12k/mac.c @@ -5430,7 +5430,7 @@ int ath12k_mac_op_get_txpower(struct ieee80211_hw *hw, ar->last_tx_power_update)) goto send_tx_power; - params.pdev_id = ar->pdev->pdev_id; + params.pdev_id = ath12k_mac_get_target_pdev_id(ar); params.vdev_id = arvif->vdev_id; params.stats_id = WMI_REQUEST_PDEV_STAT; ret = ath12k_mac_get_fw_stats(ar, ¶ms); @@ -13452,7 +13452,7 @@ void ath12k_mac_op_sta_statistics(struct ieee80211_hw *hw, /* TODO: Use real NF instead of default one. */ signal = rate_info.rssi_comb; - params.pdev_id = ar->pdev->pdev_id; + params.pdev_id = ath12k_mac_get_target_pdev_id(ar); params.vdev_id = 0; params.stats_id = WMI_REQUEST_VDEV_STAT; @@ -13580,7 +13580,7 @@ void ath12k_mac_op_link_sta_statistics(struct ieee80211_hw *hw, spin_unlock_bh(&ar->ab->dp->dp_lock); if (!signal && ahsta->ahvif->vdev_type == WMI_VDEV_TYPE_STA) { - params.pdev_id = ar->pdev->pdev_id; + params.pdev_id = ath12k_mac_get_target_pdev_id(ar); params.vdev_id = 0; params.stats_id = WMI_REQUEST_VDEV_STAT; diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c index eb7615a289f7..48fee9346de8 100644 --- a/drivers/net/wireless/ath/ath12k/wmi.c +++ b/drivers/net/wireless/ath/ath12k/wmi.c @@ -8241,8 +8241,6 @@ static int ath12k_wmi_tlv_fw_stats_data_parse(struct ath12k_base *ab, struct ath12k_fw_stats *stats = parse->stats; struct ath12k *ar; struct ath12k_link_vif *arvif; - struct ieee80211_sta *sta; - struct ath12k_sta *ahsta; struct ath12k_link_sta *arsta; int i, ret = 0; const void *data = ptr; @@ -8278,21 +8276,19 @@ static int ath12k_wmi_tlv_fw_stats_data_parse(struct ath12k_base *ab, arvif = ath12k_mac_get_arvif(ar, le32_to_cpu(src->vdev_id)); if (arvif) { - sta = ieee80211_find_sta_by_ifaddr(ath12k_ar_to_hw(ar), - arvif->bssid, - NULL); - if (sta) { - ahsta = ath12k_sta_to_ahsta(sta); - arsta = &ahsta->deflink; + spin_lock_bh(&ab->base_lock); + arsta = ath12k_link_sta_find_by_addr(ab, arvif->bssid); + if (arsta) { arsta->rssi_beacon = le32_to_cpu(src->beacon_snr); ath12k_dbg(ab, ATH12K_DBG_WMI, "wmi stats vdev id %d snr %d\n", src->vdev_id, src->beacon_snr); } else { - ath12k_dbg(ab, ATH12K_DBG_WMI, - "not found station bssid %pM for vdev stat\n", - arvif->bssid); + ath12k_warn(ab, + "not found link sta with bssid %pM for vdev stat\n", + arvif->bssid); } + spin_unlock_bh(&ab->base_lock); } data += sizeof(*src); @@ -8363,8 +8359,6 @@ static int ath12k_wmi_tlv_rssi_chain_parse(struct ath12k_base *ab, struct ath12k_fw_stats *stats = parse->stats; struct ath12k_link_vif *arvif; struct ath12k_link_sta *arsta; - struct ieee80211_sta *sta; - struct ath12k_sta *ahsta; struct ath12k *ar; int vdev_id; int j; @@ -8400,19 +8394,15 @@ static int ath12k_wmi_tlv_rssi_chain_parse(struct ath12k_base *ab, "stats bssid %pM vif %p\n", arvif->bssid, arvif->ahvif->vif); - sta = ieee80211_find_sta_by_ifaddr(ath12k_ar_to_hw(ar), - arvif->bssid, - NULL); - if (!sta) { - ath12k_dbg(ab, ATH12K_DBG_WMI, - "not found station of bssid %pM for rssi chain\n", - arvif->bssid); + guard(spinlock_bh)(&ab->base_lock); + arsta = ath12k_link_sta_find_by_addr(ab, arvif->bssid); + if (!arsta) { + ath12k_warn(ab, + "not found link sta with bssid %pM for rssi chain\n", + arvif->bssid); return -EPROTO; } - ahsta = ath12k_sta_to_ahsta(sta); - arsta = &ahsta->deflink; - BUILD_BUG_ON(ARRAY_SIZE(arsta->chain_signal) > ARRAY_SIZE(stats_rssi->rssi_avg_beacon)); diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c index 3304b5971be0..b41ca1410da9 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c @@ -413,6 +413,7 @@ mt76_connac2_mac_write_txwi_80211(struct mt76_dev *dev, __le32 *txwi, u32 val; if (ieee80211_is_action(fc) && + skb->len >= IEEE80211_MIN_ACTION_SIZE + 1 + 1 + 2 && mgmt->u.action.category == WLAN_CATEGORY_BACK && mgmt->u.action.u.addba_req.action_code == WLAN_ACTION_ADDBA_REQ) { u16 capab = le16_to_cpu(mgmt->u.action.u.addba_req.capab); diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mac.c b/drivers/net/wireless/mediatek/mt76/mt7925/mac.c index 871b67101976..0d9435900423 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/mac.c @@ -668,6 +668,7 @@ mt7925_mac_write_txwi_80211(struct mt76_dev *dev, __le32 *txwi, u32 val; if (ieee80211_is_action(fc) && + skb->len >= IEEE80211_MIN_ACTION_SIZE + 1 && mgmt->u.action.category == WLAN_CATEGORY_BACK && mgmt->u.action.u.addba_req.action_code == WLAN_ACTION_ADDBA_REQ) tid = MT_TX_ADDBA; diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c index 2560e2f46e89..d4f3ee943b47 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c @@ -800,6 +800,7 @@ mt7996_mac_write_txwi_80211(struct mt7996_dev *dev, __le32 *txwi, u32 val; if (ieee80211_is_action(fc) && + skb->len >= IEEE80211_MIN_ACTION_SIZE + 1 && mgmt->u.action.category == WLAN_CATEGORY_BACK && mgmt->u.action.u.addba_req.action_code == WLAN_ACTION_ADDBA_REQ) { if (is_mt7990(&dev->mt76)) diff --git a/drivers/net/wireless/rsi/rsi_91x_mac80211.c b/drivers/net/wireless/rsi/rsi_91x_mac80211.c index 8c8e074a3a70..c7ae8031436a 100644 --- a/drivers/net/wireless/rsi/rsi_91x_mac80211.c +++ b/drivers/net/wireless/rsi/rsi_91x_mac80211.c @@ -668,7 +668,7 @@ static int rsi_mac80211_config(struct ieee80211_hw *hw, struct rsi_hw *adapter = hw->priv; struct rsi_common *common = adapter->priv; struct ieee80211_conf *conf = &hw->conf; - int status = -EOPNOTSUPP; + int status = 0; mutex_lock(&common->mutex); diff --git a/drivers/net/wireless/st/cw1200/pm.c b/drivers/net/wireless/st/cw1200/pm.c index 120f0379f81d..84eb15d729c7 100644 --- a/drivers/net/wireless/st/cw1200/pm.c +++ b/drivers/net/wireless/st/cw1200/pm.c @@ -264,12 +264,14 @@ int cw1200_wow_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan) wiphy_err(priv->hw->wiphy, "PM request failed: %d. WoW is disabled.\n", ret); cw1200_wow_resume(hw); + mutex_unlock(&priv->conf_mutex); return -EBUSY; } /* Force resume if event is coming from the device. */ if (atomic_read(&priv->bh_rx)) { cw1200_wow_resume(hw); + mutex_unlock(&priv->conf_mutex); return -EAGAIN; } diff --git a/drivers/net/wireless/ti/wlcore/main.c b/drivers/net/wireless/ti/wlcore/main.c index 17dd417756f2..1c340a4a0930 100644 --- a/drivers/net/wireless/ti/wlcore/main.c +++ b/drivers/net/wireless/ti/wlcore/main.c @@ -1875,6 +1875,8 @@ static int __maybe_unused wl1271_op_resume(struct ieee80211_hw *hw) wl->wow_enabled); WARN_ON(!wl->wow_enabled); + mutex_lock(&wl->mutex); + ret = pm_runtime_force_resume(wl->dev); if (ret < 0) { wl1271_error("ELP wakeup failure!"); @@ -1891,8 +1893,6 @@ static int __maybe_unused wl1271_op_resume(struct ieee80211_hw *hw) run_irq_work = true; spin_unlock_irqrestore(&wl->wl_lock, flags); - mutex_lock(&wl->mutex); - /* test the recovery flag before calling any SDIO functions */ pending_recovery = test_bit(WL1271_FLAG_RECOVERY_IN_PROGRESS, &wl->flags); diff --git a/include/linux/indirect_call_wrapper.h b/include/linux/indirect_call_wrapper.h index 35227d47cfc9..dc272b514a01 100644 --- a/include/linux/indirect_call_wrapper.h +++ b/include/linux/indirect_call_wrapper.h @@ -16,22 +16,26 @@ */ #define INDIRECT_CALL_1(f, f1, ...) \ ({ \ - likely(f == f1) ? f1(__VA_ARGS__) : f(__VA_ARGS__); \ + typeof(f) __f1 = (f); \ + likely(__f1 == f1) ? f1(__VA_ARGS__) : __f1(__VA_ARGS__); \ }) #define INDIRECT_CALL_2(f, f2, f1, ...) \ ({ \ - likely(f == f2) ? f2(__VA_ARGS__) : \ - INDIRECT_CALL_1(f, f1, __VA_ARGS__); \ + typeof(f) __f2 = (f); \ + likely(__f2 == f2) ? f2(__VA_ARGS__) : \ + INDIRECT_CALL_1(__f2, f1, __VA_ARGS__); \ }) #define INDIRECT_CALL_3(f, f3, f2, f1, ...) \ ({ \ - likely(f == f3) ? f3(__VA_ARGS__) : \ - INDIRECT_CALL_2(f, f2, f1, __VA_ARGS__); \ + typeof(f) __f3 = (f); \ + likely(__f3 == f3) ? f3(__VA_ARGS__) : \ + INDIRECT_CALL_2(__f3, f2, f1, __VA_ARGS__); \ }) #define INDIRECT_CALL_4(f, f4, f3, f2, f1, ...) \ ({ \ - likely(f == f4) ? f4(__VA_ARGS__) : \ - INDIRECT_CALL_3(f, f3, f2, f1, __VA_ARGS__); \ + typeof(f) __f4 = (f); \ + likely(__f4 == f4) ? f4(__VA_ARGS__) : \ + INDIRECT_CALL_3(__f4, f3, f2, f1, __VA_ARGS__); \ }) #define INDIRECT_CALLABLE_DECLARE(f) f diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d4e6e00bb90a..67e25f6d15a4 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4711,7 +4711,7 @@ static inline u32 netif_msg_init(int debug_value, int default_msg_enable_bits) static inline void __netif_tx_lock(struct netdev_queue *txq, int cpu) { spin_lock(&txq->_xmit_lock); - /* Pairs with READ_ONCE() in __dev_queue_xmit() */ + /* Pairs with READ_ONCE() in netif_tx_owned() */ WRITE_ONCE(txq->xmit_lock_owner, cpu); } @@ -4729,7 +4729,7 @@ static inline void __netif_tx_release(struct netdev_queue *txq) static inline void __netif_tx_lock_bh(struct netdev_queue *txq) { spin_lock_bh(&txq->_xmit_lock); - /* Pairs with READ_ONCE() in __dev_queue_xmit() */ + /* Pairs with READ_ONCE() in netif_tx_owned() */ WRITE_ONCE(txq->xmit_lock_owner, smp_processor_id()); } @@ -4738,7 +4738,7 @@ static inline bool __netif_tx_trylock(struct netdev_queue *txq) bool ok = spin_trylock(&txq->_xmit_lock); if (likely(ok)) { - /* Pairs with READ_ONCE() in __dev_queue_xmit() */ + /* Pairs with READ_ONCE() in netif_tx_owned() */ WRITE_ONCE(txq->xmit_lock_owner, smp_processor_id()); } return ok; @@ -4746,14 +4746,14 @@ static inline bool __netif_tx_trylock(struct netdev_queue *txq) static inline void __netif_tx_unlock(struct netdev_queue *txq) { - /* Pairs with READ_ONCE() in __dev_queue_xmit() */ + /* Pairs with READ_ONCE() in netif_tx_owned() */ WRITE_ONCE(txq->xmit_lock_owner, -1); spin_unlock(&txq->_xmit_lock); } static inline void __netif_tx_unlock_bh(struct netdev_queue *txq) { - /* Pairs with READ_ONCE() in __dev_queue_xmit() */ + /* Pairs with READ_ONCE() in netif_tx_owned() */ WRITE_ONCE(txq->xmit_lock_owner, -1); spin_unlock_bh(&txq->_xmit_lock); } @@ -4846,6 +4846,23 @@ static inline void netif_tx_disable(struct net_device *dev) local_bh_enable(); } +#ifndef CONFIG_PREEMPT_RT +static inline bool netif_tx_owned(struct netdev_queue *txq, unsigned int cpu) +{ + /* Other cpus might concurrently change txq->xmit_lock_owner + * to -1 or to their cpu id, but not to our id. + */ + return READ_ONCE(txq->xmit_lock_owner) == cpu; +} + +#else +static inline bool netif_tx_owned(struct netdev_queue *txq, unsigned int cpu) +{ + return rt_mutex_owner(&txq->_xmit_lock.lock) == current; +} + +#endif + static inline void netif_addr_lock(struct net_device *dev) { unsigned char nest_level = 0; diff --git a/include/linux/usb/r8152.h b/include/linux/usb/r8152.h index 2ca60828f28b..1502b2a355f9 100644 --- a/include/linux/usb/r8152.h +++ b/include/linux/usb/r8152.h @@ -32,6 +32,7 @@ #define VENDOR_ID_DLINK 0x2001 #define VENDOR_ID_DELL 0x413c #define VENDOR_ID_ASUS 0x0b05 +#define VENDOR_ID_TRENDNET 0x20f4 #if IS_REACHABLE(CONFIG_USB_RTL8152) extern u8 rtl8152_get_version(struct usb_interface *intf); diff --git a/include/net/act_api.h b/include/net/act_api.h index e1e8f0f7dacb..d11b79107930 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -70,6 +70,7 @@ struct tc_action { #define TCA_ACT_FLAGS_REPLACE (1U << (TCA_ACT_FLAGS_USER_BITS + 2)) #define TCA_ACT_FLAGS_NO_RTNL (1U << (TCA_ACT_FLAGS_USER_BITS + 3)) #define TCA_ACT_FLAGS_AT_INGRESS (1U << (TCA_ACT_FLAGS_USER_BITS + 4)) +#define TCA_ACT_FLAGS_AT_INGRESS_OR_CLSACT (1U << (TCA_ACT_FLAGS_USER_BITS + 5)) /* Update lastuse only if needed, to avoid dirtying a cache line. * We use a temp variable to avoid fetching jiffies twice. diff --git a/include/net/bonding.h b/include/net/bonding.h index 4ad5521e7731..395c6e281c5f 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -699,6 +699,7 @@ void bond_debug_register(struct bonding *bond); void bond_debug_unregister(struct bonding *bond); void bond_debug_reregister(struct bonding *bond); const char *bond_mode_name(int mode); +bool __bond_xdp_check(int mode, int xmit_policy); bool bond_xdp_check(struct bonding *bond, int mode); void bond_setup(struct net_device *bond_dev); unsigned int bond_get_num_tx_queues(void); diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h index 282e29237d93..c16de5b7963f 100644 --- a/include/net/inet6_hashtables.h +++ b/include/net/inet6_hashtables.h @@ -175,7 +175,7 @@ static inline bool inet6_match(const struct net *net, const struct sock *sk, { if (!net_eq(sock_net(sk), net) || sk->sk_family != AF_INET6 || - sk->sk_portpair != ports || + READ_ONCE(sk->sk_portpair) != ports || !ipv6_addr_equal(&sk->sk_v6_daddr, saddr) || !ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr)) return false; diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index ac05a52d9e13..5a979dcab538 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -345,7 +345,7 @@ static inline bool inet_match(const struct net *net, const struct sock *sk, int dif, int sdif) { if (!net_eq(sock_net(sk), net) || - sk->sk_portpair != ports || + READ_ONCE(sk->sk_portpair) != ports || sk->sk_addrpair != cookie) return false; diff --git a/include/net/ip.h b/include/net/ip.h index 69d5cef46004..7f9abd457e01 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -101,7 +101,7 @@ static inline void ipcm_init_sk(struct ipcm_cookie *ipcm, ipcm->oif = READ_ONCE(inet->sk.sk_bound_dev_if); ipcm->addr = inet->inet_saddr; - ipcm->protocol = inet->inet_num; + ipcm->protocol = READ_ONCE(inet->inet_num); } #define IPCB(skb) ((struct inet_skb_parm*)((skb)->cb)) diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index b4495c38e0a0..318593743b6e 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -559,7 +559,7 @@ static inline u32 fib_multipath_hash_from_keys(const struct net *net, siphash_aligned_key_t hash_key; u32 mp_seed; - mp_seed = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed).mp_seed; + mp_seed = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed.mp_seed); fib_multipath_hash_construct_key(&hash_key, mp_seed); return flow_hash_from_keys_seed(keys, &hash_key); diff --git a/include/net/libeth/xsk.h b/include/net/libeth/xsk.h index 481a7b28e6f2..82b5d21aae87 100644 --- a/include/net/libeth/xsk.h +++ b/include/net/libeth/xsk.h @@ -597,6 +597,7 @@ __libeth_xsk_run_pass(struct libeth_xdp_buff *xdp, * @pending: current number of XSkFQEs to refill * @thresh: threshold below which the queue is refilled * @buf_len: HW-writeable length per each buffer + * @truesize: step between consecutive buffers, 0 if none exists * @nid: ID of the closest NUMA node with memory */ struct libeth_xskfq { @@ -614,6 +615,8 @@ struct libeth_xskfq { u32 thresh; u32 buf_len; + u32 truesize; + int nid; }; diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 426534a711b0..e2d2bfc1f989 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -320,11 +320,13 @@ static inline void *nft_elem_priv_cast(const struct nft_elem_priv *priv) * @NFT_ITER_UNSPEC: unspecified, to catch errors * @NFT_ITER_READ: read-only iteration over set elements * @NFT_ITER_UPDATE: iteration under mutex to update set element state + * @NFT_ITER_UPDATE_CLONE: clone set before iteration under mutex to update element */ enum nft_iter_type { NFT_ITER_UNSPEC, NFT_ITER_READ, NFT_ITER_UPDATE, + NFT_ITER_UPDATE_CLONE, }; struct nft_set; @@ -1861,6 +1863,11 @@ struct nft_trans_gc { struct rcu_head rcu; }; +static inline int nft_trans_gc_space(const struct nft_trans_gc *trans) +{ + return NFT_TRANS_GC_BATCHCOUNT - trans->count; +} + static inline void nft_ctx_update(struct nft_ctx *ctx, const struct nft_trans *trans) { diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index c3a7268b567e..d5d55cb21686 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -778,13 +778,23 @@ static inline bool skb_skip_tc_classify(struct sk_buff *skb) static inline void qdisc_reset_all_tx_gt(struct net_device *dev, unsigned int i) { struct Qdisc *qdisc; + bool nolock; for (; i < dev->num_tx_queues; i++) { qdisc = rtnl_dereference(netdev_get_tx_queue(dev, i)->qdisc); if (qdisc) { + nolock = qdisc->flags & TCQ_F_NOLOCK; + + if (nolock) + spin_lock_bh(&qdisc->seqlock); spin_lock_bh(qdisc_lock(qdisc)); qdisc_reset(qdisc); spin_unlock_bh(qdisc_lock(qdisc)); + if (nolock) { + clear_bit(__QDISC_STATE_MISSED, &qdisc->state); + clear_bit(__QDISC_STATE_DRAINING, &qdisc->state); + spin_unlock_bh(&qdisc->seqlock); + } } } } diff --git a/include/net/secure_seq.h b/include/net/secure_seq.h index cddebafb9f77..6f996229167b 100644 --- a/include/net/secure_seq.h +++ b/include/net/secure_seq.h @@ -5,16 +5,47 @@ #include <linux/types.h> struct net; +extern struct net init_net; + +union tcp_seq_and_ts_off { + struct { + u32 seq; + u32 ts_off; + }; + u64 hash64; +}; u64 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport); u64 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, __be16 dport); -u32 secure_tcp_seq(__be32 saddr, __be32 daddr, - __be16 sport, __be16 dport); -u32 secure_tcp_ts_off(const struct net *net, __be32 saddr, __be32 daddr); -u32 secure_tcpv6_seq(const __be32 *saddr, const __be32 *daddr, - __be16 sport, __be16 dport); -u32 secure_tcpv6_ts_off(const struct net *net, - const __be32 *saddr, const __be32 *daddr); +union tcp_seq_and_ts_off +secure_tcp_seq_and_ts_off(const struct net *net, __be32 saddr, __be32 daddr, + __be16 sport, __be16 dport); + +static inline u32 secure_tcp_seq(__be32 saddr, __be32 daddr, + __be16 sport, __be16 dport) +{ + union tcp_seq_and_ts_off ts; + + ts = secure_tcp_seq_and_ts_off(&init_net, saddr, daddr, + sport, dport); + + return ts.seq; +} + +union tcp_seq_and_ts_off +secure_tcpv6_seq_and_ts_off(const struct net *net, const __be32 *saddr, + const __be32 *daddr, + __be16 sport, __be16 dport); + +static inline u32 secure_tcpv6_seq(const __be32 *saddr, const __be32 *daddr, + __be16 sport, __be16 dport) +{ + union tcp_seq_and_ts_off ts; + + ts = secure_tcpv6_seq_and_ts_off(&init_net, saddr, daddr, + sport, dport); + return ts.seq; +} #endif /* _NET_SECURE_SEQ */ diff --git a/include/net/tc_act/tc_gate.h b/include/net/tc_act/tc_gate.h index b147a3bb1a46..e0fded18e18c 100644 --- a/include/net/tc_act/tc_gate.h +++ b/include/net/tc_act/tc_gate.h @@ -32,6 +32,7 @@ struct tcf_gate_params { s32 tcfg_clockid; size_t num_entries; struct list_head entries; + struct rcu_head rcu; }; #define GATE_ACT_GATE_OPEN BIT(0) @@ -39,7 +40,7 @@ struct tcf_gate_params { struct tcf_gate { struct tc_action common; - struct tcf_gate_params param; + struct tcf_gate_params __rcu *param; u8 current_gate_status; ktime_t current_close_time; u32 current_entry_octets; @@ -51,47 +52,65 @@ struct tcf_gate { #define to_gate(a) ((struct tcf_gate *)a) +static inline struct tcf_gate_params *tcf_gate_params_locked(const struct tc_action *a) +{ + struct tcf_gate *gact = to_gate(a); + + return rcu_dereference_protected(gact->param, + lockdep_is_held(&gact->tcf_lock)); +} + static inline s32 tcf_gate_prio(const struct tc_action *a) { + struct tcf_gate_params *p; s32 tcfg_prio; - tcfg_prio = to_gate(a)->param.tcfg_priority; + p = tcf_gate_params_locked(a); + tcfg_prio = p->tcfg_priority; return tcfg_prio; } static inline u64 tcf_gate_basetime(const struct tc_action *a) { + struct tcf_gate_params *p; u64 tcfg_basetime; - tcfg_basetime = to_gate(a)->param.tcfg_basetime; + p = tcf_gate_params_locked(a); + tcfg_basetime = p->tcfg_basetime; return tcfg_basetime; } static inline u64 tcf_gate_cycletime(const struct tc_action *a) { + struct tcf_gate_params *p; u64 tcfg_cycletime; - tcfg_cycletime = to_gate(a)->param.tcfg_cycletime; + p = tcf_gate_params_locked(a); + tcfg_cycletime = p->tcfg_cycletime; return tcfg_cycletime; } static inline u64 tcf_gate_cycletimeext(const struct tc_action *a) { + struct tcf_gate_params *p; u64 tcfg_cycletimeext; - tcfg_cycletimeext = to_gate(a)->param.tcfg_cycletime_ext; + p = tcf_gate_params_locked(a); + tcfg_cycletimeext = p->tcfg_cycletime_ext; return tcfg_cycletimeext; } static inline u32 tcf_gate_num_entries(const struct tc_action *a) { + struct tcf_gate_params *p; u32 num_entries; - num_entries = to_gate(a)->param.num_entries; + p = tcf_gate_params_locked(a); + num_entries = p->num_entries; return num_entries; } @@ -105,7 +124,7 @@ static inline struct action_gate_entry u32 num_entries; int i = 0; - p = &to_gate(a)->param; + p = tcf_gate_params_locked(a); num_entries = p->num_entries; list_for_each_entry(entry, &p->entries, list) diff --git a/include/net/tc_act/tc_ife.h b/include/net/tc_act/tc_ife.h index c7f24a2da1ca..24d4d5a62b3c 100644 --- a/include/net/tc_act/tc_ife.h +++ b/include/net/tc_act/tc_ife.h @@ -13,15 +13,13 @@ struct tcf_ife_params { u8 eth_src[ETH_ALEN]; u16 eth_type; u16 flags; - + struct list_head metalist; struct rcu_head rcu; }; struct tcf_ife_info { struct tc_action common; struct tcf_ife_params __rcu *params; - /* list of metaids allowed */ - struct list_head metalist; }; #define to_ife(a) ((struct tcf_ife_info *)a) diff --git a/include/net/tcp.h b/include/net/tcp.h index eb8bf63fdafc..978eea2d5df0 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -43,6 +43,7 @@ #include <net/dst.h> #include <net/mptcp.h> #include <net/xfrm.h> +#include <net/secure_seq.h> #include <linux/seq_file.h> #include <linux/memcontrol.h> @@ -2464,8 +2465,9 @@ struct tcp_request_sock_ops { struct flowi *fl, struct request_sock *req, u32 tw_isn); - u32 (*init_seq)(const struct sk_buff *skb); - u32 (*init_ts_off)(const struct net *net, const struct sk_buff *skb); + union tcp_seq_and_ts_off (*init_seq_and_ts_off)( + const struct net *net, + const struct sk_buff *skb); int (*send_synack)(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, struct tcp_fastopen_cookie *foc, diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h index 242e34f771cc..6b9ebae2dc95 100644 --- a/include/net/xdp_sock_drv.h +++ b/include/net/xdp_sock_drv.h @@ -51,6 +51,11 @@ static inline u32 xsk_pool_get_rx_frame_size(struct xsk_buff_pool *pool) return xsk_pool_get_chunk_size(pool) - xsk_pool_get_headroom(pool); } +static inline u32 xsk_pool_get_rx_frag_step(struct xsk_buff_pool *pool) +{ + return pool->unaligned ? 0 : xsk_pool_get_chunk_size(pool); +} + static inline void xsk_pool_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq) { @@ -122,7 +127,7 @@ static inline void xsk_buff_free(struct xdp_buff *xdp) goto out; list_for_each_entry_safe(pos, tmp, xskb_list, list_node) { - list_del(&pos->list_node); + list_del_init(&pos->list_node); xp_free(pos); } @@ -157,7 +162,7 @@ static inline struct xdp_buff *xsk_buff_get_frag(const struct xdp_buff *first) frag = list_first_entry_or_null(&xskb->pool->xskb_list, struct xdp_buff_xsk, list_node); if (frag) { - list_del(&frag->list_node); + list_del_init(&frag->list_node); ret = &frag->xdp; } @@ -168,7 +173,7 @@ static inline void xsk_buff_del_frag(struct xdp_buff *xdp) { struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp); - list_del(&xskb->list_node); + list_del_init(&xskb->list_node); } static inline struct xdp_buff *xsk_buff_get_head(struct xdp_buff *first) @@ -337,6 +342,11 @@ static inline u32 xsk_pool_get_rx_frame_size(struct xsk_buff_pool *pool) return 0; } +static inline u32 xsk_pool_get_rx_frag_step(struct xsk_buff_pool *pool) +{ + return 0; +} + static inline void xsk_pool_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq) { diff --git a/net/atm/lec.c b/net/atm/lec.c index a107375c0629..fb93c6e1c329 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -1260,24 +1260,28 @@ static void lec_arp_clear_vccs(struct lec_arp_table *entry) struct lec_vcc_priv *vpriv = LEC_VCC_PRIV(vcc); struct net_device *dev = (struct net_device *)vcc->proto_data; - vcc->pop = vpriv->old_pop; - if (vpriv->xoff) - netif_wake_queue(dev); - kfree(vpriv); - vcc->user_back = NULL; - vcc->push = entry->old_push; - vcc_release_async(vcc, -EPIPE); + if (vpriv) { + vcc->pop = vpriv->old_pop; + if (vpriv->xoff) + netif_wake_queue(dev); + kfree(vpriv); + vcc->user_back = NULL; + vcc->push = entry->old_push; + vcc_release_async(vcc, -EPIPE); + } entry->vcc = NULL; } if (entry->recv_vcc) { struct atm_vcc *vcc = entry->recv_vcc; struct lec_vcc_priv *vpriv = LEC_VCC_PRIV(vcc); - kfree(vpriv); - vcc->user_back = NULL; + if (vpriv) { + kfree(vpriv); + vcc->user_back = NULL; - entry->recv_vcc->push = entry->old_recv_push; - vcc_release_async(entry->recv_vcc, -EPIPE); + entry->recv_vcc->push = entry->old_recv_push; + vcc_release_async(entry->recv_vcc, -EPIPE); + } entry->recv_vcc = NULL; } } diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c index 2ce4e5bf9292..fdc2abe96d77 100644 --- a/net/batman-adv/bat_v_elp.c +++ b/net/batman-adv/bat_v_elp.c @@ -111,7 +111,15 @@ static bool batadv_v_elp_get_throughput(struct batadv_hardif_neigh_node *neigh, /* unsupported WiFi driver version */ goto default_throughput; - real_netdev = batadv_get_real_netdev(hard_iface->net_dev); + /* only use rtnl_trylock because the elp worker will be cancelled while + * the rntl_lock is held. the cancel_delayed_work_sync() would otherwise + * wait forever when the elp work_item was started and it is then also + * trying to rtnl_lock + */ + if (!rtnl_trylock()) + return false; + real_netdev = __batadv_get_real_netdev(hard_iface->net_dev); + rtnl_unlock(); if (!real_netdev) goto default_throughput; diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index 7b7640f3ffe2..d6732c34aeaf 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -204,7 +204,7 @@ static bool batadv_is_valid_iface(const struct net_device *net_dev) } /** - * batadv_get_real_netdevice() - check if the given netdev struct is a virtual + * __batadv_get_real_netdev() - check if the given netdev struct is a virtual * interface on top of another 'real' interface * @netdev: the device to check * @@ -214,7 +214,7 @@ static bool batadv_is_valid_iface(const struct net_device *net_dev) * Return: the 'real' net device or the original net device and NULL in case * of an error. */ -static struct net_device *batadv_get_real_netdevice(struct net_device *netdev) +struct net_device *__batadv_get_real_netdev(struct net_device *netdev) { struct batadv_hard_iface *hard_iface = NULL; struct net_device *real_netdev = NULL; @@ -267,7 +267,7 @@ struct net_device *batadv_get_real_netdev(struct net_device *net_device) struct net_device *real_netdev; rtnl_lock(); - real_netdev = batadv_get_real_netdevice(net_device); + real_netdev = __batadv_get_real_netdev(net_device); rtnl_unlock(); return real_netdev; @@ -336,7 +336,7 @@ static u32 batadv_wifi_flags_evaluate(struct net_device *net_device) if (batadv_is_cfg80211_netdev(net_device)) wifi_flags |= BATADV_HARDIF_WIFI_CFG80211_DIRECT; - real_netdev = batadv_get_real_netdevice(net_device); + real_netdev = __batadv_get_real_netdev(net_device); if (!real_netdev) return wifi_flags; diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h index 9db8a310961e..9ba8fb2bdceb 100644 --- a/net/batman-adv/hard-interface.h +++ b/net/batman-adv/hard-interface.h @@ -67,6 +67,7 @@ enum batadv_hard_if_bcast { extern struct notifier_block batadv_hard_if_notifier; +struct net_device *__batadv_get_real_netdev(struct net_device *net_device); struct net_device *batadv_get_real_netdev(struct net_device *net_device); bool batadv_is_cfg80211_hardif(struct batadv_hard_iface *hard_iface); bool batadv_is_wifi_hardif(struct batadv_hard_iface *hard_iface); diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index ee01122f466f..f7502e62dd35 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -74,7 +74,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) eth_hdr(skb)->h_proto == htons(ETH_P_RARP)) && br_opt_get(br, BROPT_NEIGH_SUPPRESS_ENABLED)) { br_do_proxy_suppress_arp(skb, br, vid, NULL); - } else if (IS_ENABLED(CONFIG_IPV6) && + } else if (ipv6_mod_enabled() && skb->protocol == htons(ETH_P_IPV6) && br_opt_get(br, BROPT_NEIGH_SUPPRESS_ENABLED) && pskb_may_pull(skb, sizeof(struct ipv6hdr) + diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 1405f1061a54..2cbae0f9ae1f 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -170,7 +170,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb (skb->protocol == htons(ETH_P_ARP) || skb->protocol == htons(ETH_P_RARP))) { br_do_proxy_suppress_arp(skb, br, vid, p); - } else if (IS_ENABLED(CONFIG_IPV6) && + } else if (ipv6_mod_enabled() && skb->protocol == htons(ETH_P_IPV6) && br_opt_get(br, BROPT_NEIGH_SUPPRESS_ENABLED) && pskb_may_pull(skb, sizeof(struct ipv6hdr) + diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index b9b2981c4841..9b55d38ea9ed 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -1345,6 +1345,16 @@ br_multicast_ctx_options_equal(const struct net_bridge_mcast *brmctx1, } static inline bool +br_multicast_port_ctx_options_equal(const struct net_bridge_mcast_port *pmctx1, + const struct net_bridge_mcast_port *pmctx2) +{ + return br_multicast_ngroups_get(pmctx1) == + br_multicast_ngroups_get(pmctx2) && + br_multicast_ngroups_get_max(pmctx1) == + br_multicast_ngroups_get_max(pmctx2); +} + +static inline bool br_multicast_ctx_matches_vlan_snooping(const struct net_bridge_mcast *brmctx) { bool vlan_snooping_enabled; diff --git a/net/bridge/br_vlan_options.c b/net/bridge/br_vlan_options.c index 8fa89b04ee94..5514e1fc8d1f 100644 --- a/net/bridge/br_vlan_options.c +++ b/net/bridge/br_vlan_options.c @@ -43,9 +43,29 @@ bool br_vlan_opts_eq_range(const struct net_bridge_vlan *v_curr, u8 range_mc_rtr = br_vlan_multicast_router(range_end); u8 curr_mc_rtr = br_vlan_multicast_router(v_curr); - return v_curr->state == range_end->state && - __vlan_tun_can_enter_range(v_curr, range_end) && - curr_mc_rtr == range_mc_rtr; + if (v_curr->state != range_end->state) + return false; + + if (!__vlan_tun_can_enter_range(v_curr, range_end)) + return false; + + if (curr_mc_rtr != range_mc_rtr) + return false; + + /* Check user-visible priv_flags that affect output */ + if ((v_curr->priv_flags ^ range_end->priv_flags) & + (BR_VLFLAG_NEIGH_SUPPRESS_ENABLED | BR_VLFLAG_MCAST_ENABLED)) + return false; + +#ifdef CONFIG_BRIDGE_IGMP_SNOOPING + if (!br_vlan_is_master(v_curr) && + !br_multicast_port_ctx_vlan_disabled(&v_curr->port_mcast_ctx) && + !br_multicast_port_ctx_options_equal(&v_curr->port_mcast_ctx, + &range_end->port_mcast_ctx)) + return false; +#endif + + return true; } bool br_vlan_opts_fill(struct sk_buff *skb, const struct net_bridge_vlan *v, diff --git a/net/can/bcm.c b/net/can/bcm.c index b7324e9c955b..fd9fa072881e 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -1176,6 +1176,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, if (!op) return -ENOMEM; + spin_lock_init(&op->bcm_tx_lock); op->can_id = msg_head->can_id; op->nframes = msg_head->nframes; op->cfsiz = CFSIZ(msg_head->flags); diff --git a/net/core/dev.c b/net/core/dev.c index c1a9f7fdcffa..14a83f2035b9 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3987,7 +3987,7 @@ static struct sk_buff *validate_xmit_unreadable_skb(struct sk_buff *skb, if (shinfo->nr_frags > 0) { niov = netmem_to_net_iov(skb_frag_netmem(&shinfo->frags[0])); if (net_is_devmem_iov(niov) && - net_devmem_iov_binding(niov)->dev != dev) + READ_ONCE(net_devmem_iov_binding(niov)->dev) != dev) goto out_free; } @@ -4818,10 +4818,7 @@ int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev) if (dev->flags & IFF_UP) { int cpu = smp_processor_id(); /* ok because BHs are off */ - /* Other cpus might concurrently change txq->xmit_lock_owner - * to -1 or to their cpu id, but not to our id. - */ - if (READ_ONCE(txq->xmit_lock_owner) != cpu) { + if (!netif_tx_owned(txq, cpu)) { bool is_list = false; if (dev_xmit_recursion()) @@ -7794,11 +7791,12 @@ static int napi_thread_wait(struct napi_struct *napi) return -1; } -static void napi_threaded_poll_loop(struct napi_struct *napi, bool busy_poll) +static void napi_threaded_poll_loop(struct napi_struct *napi, + unsigned long *busy_poll_last_qs) { + unsigned long last_qs = busy_poll_last_qs ? *busy_poll_last_qs : jiffies; struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; struct softnet_data *sd; - unsigned long last_qs = jiffies; for (;;) { bool repoll = false; @@ -7827,12 +7825,12 @@ static void napi_threaded_poll_loop(struct napi_struct *napi, bool busy_poll) /* When busy poll is enabled, the old packets are not flushed in * napi_complete_done. So flush them here. */ - if (busy_poll) + if (busy_poll_last_qs) gro_flush_normal(&napi->gro, HZ >= 1000); local_bh_enable(); /* Call cond_resched here to avoid watchdog warnings. */ - if (repoll || busy_poll) { + if (repoll || busy_poll_last_qs) { rcu_softirq_qs_periodic(last_qs); cond_resched(); } @@ -7840,11 +7838,15 @@ static void napi_threaded_poll_loop(struct napi_struct *napi, bool busy_poll) if (!repoll) break; } + + if (busy_poll_last_qs) + *busy_poll_last_qs = last_qs; } static int napi_threaded_poll(void *data) { struct napi_struct *napi = data; + unsigned long last_qs = jiffies; bool want_busy_poll; bool in_busy_poll; unsigned long val; @@ -7862,7 +7864,7 @@ static int napi_threaded_poll(void *data) assign_bit(NAPI_STATE_IN_BUSY_POLL, &napi->state, want_busy_poll); - napi_threaded_poll_loop(napi, want_busy_poll); + napi_threaded_poll_loop(napi, want_busy_poll ? &last_qs : NULL); } return 0; @@ -13175,7 +13177,7 @@ static void run_backlog_napi(unsigned int cpu) { struct softnet_data *sd = per_cpu_ptr(&softnet_data, cpu); - napi_threaded_poll_loop(&sd->backlog, false); + napi_threaded_poll_loop(&sd->backlog, NULL); } static void backlog_napi_setup(unsigned int cpu) diff --git a/net/core/devmem.c b/net/core/devmem.c index 8c9aad776bf4..69d79aee07ef 100644 --- a/net/core/devmem.c +++ b/net/core/devmem.c @@ -396,7 +396,8 @@ struct net_devmem_dmabuf_binding *net_devmem_get_binding(struct sock *sk, * net_device. */ dst_dev = dst_dev_rcu(dst); - if (unlikely(!dst_dev) || unlikely(dst_dev != binding->dev)) { + if (unlikely(!dst_dev) || + unlikely(dst_dev != READ_ONCE(binding->dev))) { err = -ENODEV; goto out_unlock; } @@ -513,7 +514,8 @@ static void mp_dmabuf_devmem_uninstall(void *mp_priv, xa_erase(&binding->bound_rxqs, xa_idx); if (xa_empty(&binding->bound_rxqs)) { mutex_lock(&binding->lock); - binding->dev = NULL; + ASSERT_EXCLUSIVE_WRITER(binding->dev); + WRITE_ONCE(binding->dev, NULL); mutex_unlock(&binding->lock); } break; diff --git a/net/core/filter.c b/net/core/filter.c index 0d5d5a17acb2..a77d23fe2359 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4150,12 +4150,14 @@ static int bpf_xdp_frags_increase_tail(struct xdp_buff *xdp, int offset) struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); skb_frag_t *frag = &sinfo->frags[sinfo->nr_frags - 1]; struct xdp_rxq_info *rxq = xdp->rxq; - unsigned int tailroom; + int tailroom; if (!rxq->frag_size || rxq->frag_size > xdp->frame_sz) return -EOPNOTSUPP; - tailroom = rxq->frag_size - skb_frag_size(frag) - skb_frag_off(frag); + tailroom = rxq->frag_size - skb_frag_size(frag) - + skb_frag_off(frag) % rxq->frag_size; + WARN_ON_ONCE(tailroom < 0); if (unlikely(offset > tailroom)) return -EINVAL; diff --git a/net/core/netpoll.c b/net/core/netpoll.c index a8558a52884f..cd74beffd209 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -132,7 +132,7 @@ static int netif_local_xmit_active(struct net_device *dev) for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); - if (READ_ONCE(txq->xmit_lock_owner) == smp_processor_id()) + if (netif_tx_owned(txq, smp_processor_id())) return 1; } diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c index 9a3965680451..6a6f2cda5aae 100644 --- a/net/core/secure_seq.c +++ b/net/core/secure_seq.c @@ -20,7 +20,6 @@ #include <net/tcp.h> static siphash_aligned_key_t net_secret; -static siphash_aligned_key_t ts_secret; #define EPHEMERAL_PORT_SHUFFLE_PERIOD (10 * HZ) @@ -28,11 +27,6 @@ static __always_inline void net_secret_init(void) { net_get_random_once(&net_secret, sizeof(net_secret)); } - -static __always_inline void ts_secret_init(void) -{ - net_get_random_once(&ts_secret, sizeof(ts_secret)); -} #endif #ifdef CONFIG_INET @@ -53,28 +47,9 @@ static u32 seq_scale(u32 seq) #endif #if IS_ENABLED(CONFIG_IPV6) -u32 secure_tcpv6_ts_off(const struct net *net, - const __be32 *saddr, const __be32 *daddr) -{ - const struct { - struct in6_addr saddr; - struct in6_addr daddr; - } __aligned(SIPHASH_ALIGNMENT) combined = { - .saddr = *(struct in6_addr *)saddr, - .daddr = *(struct in6_addr *)daddr, - }; - - if (READ_ONCE(net->ipv4.sysctl_tcp_timestamps) != 1) - return 0; - - ts_secret_init(); - return siphash(&combined, offsetofend(typeof(combined), daddr), - &ts_secret); -} -EXPORT_IPV6_MOD(secure_tcpv6_ts_off); - -u32 secure_tcpv6_seq(const __be32 *saddr, const __be32 *daddr, - __be16 sport, __be16 dport) +union tcp_seq_and_ts_off +secure_tcpv6_seq_and_ts_off(const struct net *net, const __be32 *saddr, + const __be32 *daddr, __be16 sport, __be16 dport) { const struct { struct in6_addr saddr; @@ -87,14 +62,20 @@ u32 secure_tcpv6_seq(const __be32 *saddr, const __be32 *daddr, .sport = sport, .dport = dport }; - u32 hash; + union tcp_seq_and_ts_off st; net_secret_init(); - hash = siphash(&combined, offsetofend(typeof(combined), dport), - &net_secret); - return seq_scale(hash); + + st.hash64 = siphash(&combined, offsetofend(typeof(combined), dport), + &net_secret); + + if (READ_ONCE(net->ipv4.sysctl_tcp_timestamps) != 1) + st.ts_off = 0; + + st.seq = seq_scale(st.seq); + return st; } -EXPORT_SYMBOL(secure_tcpv6_seq); +EXPORT_SYMBOL(secure_tcpv6_seq_and_ts_off); u64 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, __be16 dport) @@ -118,33 +99,30 @@ EXPORT_SYMBOL(secure_ipv6_port_ephemeral); #endif #ifdef CONFIG_INET -u32 secure_tcp_ts_off(const struct net *net, __be32 saddr, __be32 daddr) -{ - if (READ_ONCE(net->ipv4.sysctl_tcp_timestamps) != 1) - return 0; - - ts_secret_init(); - return siphash_2u32((__force u32)saddr, (__force u32)daddr, - &ts_secret); -} - /* secure_tcp_seq_and_tsoff(a, b, 0, d) == secure_ipv4_port_ephemeral(a, b, d), * but fortunately, `sport' cannot be 0 in any circumstances. If this changes, * it would be easy enough to have the former function use siphash_4u32, passing * the arguments as separate u32. */ -u32 secure_tcp_seq(__be32 saddr, __be32 daddr, - __be16 sport, __be16 dport) +union tcp_seq_and_ts_off +secure_tcp_seq_and_ts_off(const struct net *net, __be32 saddr, __be32 daddr, + __be16 sport, __be16 dport) { - u32 hash; + u32 ports = (__force u32)sport << 16 | (__force u32)dport; + union tcp_seq_and_ts_off st; net_secret_init(); - hash = siphash_3u32((__force u32)saddr, (__force u32)daddr, - (__force u32)sport << 16 | (__force u32)dport, - &net_secret); - return seq_scale(hash); + + st.hash64 = siphash_3u32((__force u32)saddr, (__force u32)daddr, + ports, &net_secret); + + if (READ_ONCE(net->ipv4.sysctl_tcp_timestamps) != 1) + st.ts_off = 0; + + st.seq = seq_scale(st.seq); + return st; } -EXPORT_SYMBOL_GPL(secure_tcp_seq); +EXPORT_SYMBOL_GPL(secure_tcp_seq_and_ts_off); u64 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport) { diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 2e26174c9919..3261793abe83 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -1205,8 +1205,8 @@ void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock) return; psock->saved_data_ready = sk->sk_data_ready; - sk->sk_data_ready = sk_psock_strp_data_ready; - sk->sk_write_space = sk_psock_write_space; + WRITE_ONCE(sk->sk_data_ready, sk_psock_strp_data_ready); + WRITE_ONCE(sk->sk_write_space, sk_psock_write_space); } void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock) @@ -1216,8 +1216,8 @@ void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock) if (!psock->saved_data_ready) return; - sk->sk_data_ready = psock->saved_data_ready; - psock->saved_data_ready = NULL; + WRITE_ONCE(sk->sk_data_ready, psock->saved_data_ready); + WRITE_ONCE(psock->saved_data_ready, NULL); strp_stop(&psock->strp); } @@ -1296,8 +1296,8 @@ void sk_psock_start_verdict(struct sock *sk, struct sk_psock *psock) return; psock->saved_data_ready = sk->sk_data_ready; - sk->sk_data_ready = sk_psock_verdict_data_ready; - sk->sk_write_space = sk_psock_write_space; + WRITE_ONCE(sk->sk_data_ready, sk_psock_verdict_data_ready); + WRITE_ONCE(sk->sk_write_space, sk_psock_write_space); } void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *psock) @@ -1308,6 +1308,6 @@ void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *psock) if (!psock->saved_data_ready) return; - sk->sk_data_ready = psock->saved_data_ready; + WRITE_ONCE(sk->sk_data_ready, psock->saved_data_ready); psock->saved_data_ready = NULL; } diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index b71c22475c51..df922f9f5289 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -748,6 +748,7 @@ config TCP_SIGPOOL config TCP_AO bool "TCP: Authentication Option (RFC5925)" select CRYPTO + select CRYPTO_LIB_UTILS select TCP_SIGPOOL depends on 64BIT && IPV6 != m # seq-number extension needs WRITE_ONCE(u64) help @@ -761,6 +762,7 @@ config TCP_AO config TCP_MD5SIG bool "TCP: MD5 Signature Option support (RFC2385)" select CRYPTO_LIB_MD5 + select CRYPTO_LIB_UTILS help RFC2385 specifies a method of giving MD5 protection to TCP sessions. Its main (only?) use is to protect BGP sessions between core routers diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index fca980772c81..9bfccc283fa6 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -200,7 +200,7 @@ static bool inet_bind2_bucket_addr_match(const struct inet_bind2_bucket *tb2, void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb, struct inet_bind2_bucket *tb2, unsigned short port) { - inet_sk(sk)->inet_num = port; + WRITE_ONCE(inet_sk(sk)->inet_num, port); inet_csk(sk)->icsk_bind_hash = tb; inet_csk(sk)->icsk_bind2_hash = tb2; sk_add_bind_node(sk, &tb2->owners); @@ -224,7 +224,7 @@ static void __inet_put_port(struct sock *sk) spin_lock(&head->lock); tb = inet_csk(sk)->icsk_bind_hash; inet_csk(sk)->icsk_bind_hash = NULL; - inet_sk(sk)->inet_num = 0; + WRITE_ONCE(inet_sk(sk)->inet_num, 0); sk->sk_userlocks &= ~SOCK_CONNECT_BIND; spin_lock(&head2->lock); @@ -352,7 +352,7 @@ static inline int compute_score(struct sock *sk, const struct net *net, { int score = -1; - if (net_eq(sock_net(sk), net) && sk->sk_num == hnum && + if (net_eq(sock_net(sk), net) && READ_ONCE(sk->sk_num) == hnum && !ipv6_only_sock(sk)) { if (sk->sk_rcv_saddr != daddr) return -1; @@ -1206,7 +1206,7 @@ error: sk->sk_hash = 0; inet_sk(sk)->inet_sport = 0; - inet_sk(sk)->inet_num = 0; + WRITE_ONCE(inet_sk(sk)->inet_num, 0); if (tw) inet_twsk_bind_unhash(tw, hinfo); diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 061751aabc8e..fc3affd9c801 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -378,9 +378,14 @@ static struct request_sock *cookie_tcp_check(struct net *net, struct sock *sk, tcp_parse_options(net, skb, &tcp_opt, 0, NULL); if (tcp_opt.saw_tstamp && tcp_opt.rcv_tsecr) { - tsoff = secure_tcp_ts_off(net, - ip_hdr(skb)->daddr, - ip_hdr(skb)->saddr); + union tcp_seq_and_ts_off st; + + st = secure_tcp_seq_and_ts_off(net, + ip_hdr(skb)->daddr, + ip_hdr(skb)->saddr, + tcp_hdr(skb)->dest, + tcp_hdr(skb)->source); + tsoff = st.ts_off; tcp_opt.rcv_tsecr -= tsoff; } diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 643763bc2142..5654cc9c8a0b 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -486,7 +486,8 @@ static void proc_fib_multipath_hash_set_seed(struct net *net, u32 user_seed) proc_fib_multipath_hash_rand_seed), }; - WRITE_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed, new); + WRITE_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed.user_seed, new.user_seed); + WRITE_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed.mp_seed, new.mp_seed); } static int proc_fib_multipath_hash_seed(const struct ctl_table *table, int write, @@ -500,7 +501,7 @@ static int proc_fib_multipath_hash_seed(const struct ctl_table *table, int write int ret; mphs = &net->ipv4.sysctl_fib_multipath_hash_seed; - user_seed = mphs->user_seed; + user_seed = READ_ONCE(mphs->user_seed); tmp = *table; tmp.data = &user_seed; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index f84d9a45cc9d..202a4e57a218 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -244,6 +244,7 @@ #define pr_fmt(fmt) "TCP: " fmt #include <crypto/md5.h> +#include <crypto/utils.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/types.h> @@ -1446,7 +1447,7 @@ out_err: err = sk_stream_error(sk, flags, err); /* make sure we wake any epoll edge trigger waiter */ if (unlikely(tcp_rtx_and_write_queues_empty(sk) && err == -EAGAIN)) { - sk->sk_write_space(sk); + READ_ONCE(sk->sk_write_space)(sk); tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED); } if (binding) @@ -4181,7 +4182,7 @@ ao_parse: break; case TCP_NOTSENT_LOWAT: WRITE_ONCE(tp->notsent_lowat, val); - sk->sk_write_space(sk); + READ_ONCE(sk->sk_write_space)(sk); break; case TCP_INQ: if (val > 1 || val < 0) @@ -4970,7 +4971,7 @@ tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb, tcp_v4_md5_hash_skb(newhash, key, NULL, skb); else tp->af_specific->calc_md5_hash(newhash, key, NULL, skb); - if (memcmp(hash_location, newhash, 16) != 0) { + if (crypto_memneq(hash_location, newhash, 16)) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5FAILURE); trace_tcp_hash_md5_mismatch(sk, skb); return SKB_DROP_REASON_TCP_MD5FAILURE; diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c index 4980caddb0fc..a97cdf3e6af4 100644 --- a/net/ipv4/tcp_ao.c +++ b/net/ipv4/tcp_ao.c @@ -10,6 +10,7 @@ #define pr_fmt(fmt) "TCP: " fmt #include <crypto/hash.h> +#include <crypto/utils.h> #include <linux/inetdevice.h> #include <linux/tcp.h> @@ -922,7 +923,7 @@ tcp_ao_verify_hash(const struct sock *sk, const struct sk_buff *skb, /* XXX: make it per-AF callback? */ tcp_ao_hash_skb(family, hash_buf, key, sk, skb, traffic_key, (phash - (u8 *)th), sne); - if (memcmp(phash, hash_buf, maclen)) { + if (crypto_memneq(phash, hash_buf, maclen)) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAOBAD); atomic64_inc(&info->counters.pkt_bad); atomic64_inc(&key->pkt_bad); diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index c449a044895e..813d2e498c93 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -725,7 +725,7 @@ int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore) WRITE_ONCE(sk->sk_prot->unhash, psock->saved_unhash); tcp_update_ulp(sk, psock->sk_proto, psock->saved_write_space); } else { - sk->sk_write_space = psock->saved_write_space; + WRITE_ONCE(sk->sk_write_space, psock->saved_write_space); /* Pairs with lockless read in sk_clone_lock() */ sock_replace_proto(sk, psock->sk_proto); } diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c index d83efd91f461..7935702e394b 100644 --- a/net/ipv4/tcp_diag.c +++ b/net/ipv4/tcp_diag.c @@ -509,7 +509,7 @@ next_chunk: if (r->sdiag_family != AF_UNSPEC && sk->sk_family != r->sdiag_family) goto next_normal; - if (r->id.idiag_sport != htons(sk->sk_num) && + if (r->id.idiag_sport != htons(READ_ONCE(sk->sk_num)) && r->id.idiag_sport) goto next_normal; if (r->id.idiag_dport != sk->sk_dport && diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 41c57efd125c..cba89733d121 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5374,25 +5374,11 @@ static void tcp_ofo_queue(struct sock *sk) static bool tcp_prune_ofo_queue(struct sock *sk, const struct sk_buff *in_skb); static int tcp_prune_queue(struct sock *sk, const struct sk_buff *in_skb); -/* Check if this incoming skb can be added to socket receive queues - * while satisfying sk->sk_rcvbuf limit. - * - * In theory we should use skb->truesize, but this can cause problems - * when applications use too small SO_RCVBUF values. - * When LRO / hw gro is used, the socket might have a high tp->scaling_ratio, - * allowing RWIN to be close to available space. - * Whenever the receive queue gets full, we can receive a small packet - * filling RWIN, but with a high skb->truesize, because most NIC use 4K page - * plus sk_buff metadata even when receiving less than 1500 bytes of payload. - * - * Note that we use skb->len to decide to accept or drop this packet, - * but sk->sk_rmem_alloc is the sum of all skb->truesize. - */ static bool tcp_can_ingest(const struct sock *sk, const struct sk_buff *skb) { unsigned int rmem = atomic_read(&sk->sk_rmem_alloc); - return rmem + skb->len <= sk->sk_rcvbuf; + return rmem <= sk->sk_rcvbuf; } static int tcp_try_rmem_schedule(struct sock *sk, const struct sk_buff *skb, @@ -5425,7 +5411,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) if (unlikely(tcp_try_rmem_schedule(sk, skb, skb->truesize))) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFODROP); - sk->sk_data_ready(sk); + READ_ONCE(sk->sk_data_ready)(sk); tcp_drop_reason(sk, skb, SKB_DROP_REASON_PROTO_MEM); return; } @@ -5635,7 +5621,7 @@ err: void tcp_data_ready(struct sock *sk) { if (tcp_epollin_ready(sk, sk->sk_rcvlowat) || sock_flag(sk, SOCK_DONE)) - sk->sk_data_ready(sk); + READ_ONCE(sk->sk_data_ready)(sk); } static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) @@ -5691,7 +5677,7 @@ queue_and_out: inet_csk(sk)->icsk_ack.pending |= (ICSK_ACK_NOMEM | ICSK_ACK_NOW); inet_csk_schedule_ack(sk); - sk->sk_data_ready(sk); + READ_ONCE(sk->sk_data_ready)(sk); if (skb_queue_len(&sk->sk_receive_queue) && skb->len) { reason = SKB_DROP_REASON_PROTO_MEM; @@ -6114,7 +6100,9 @@ static void tcp_new_space(struct sock *sk) tp->snd_cwnd_stamp = tcp_jiffies32; } - INDIRECT_CALL_1(sk->sk_write_space, sk_stream_write_space, sk); + INDIRECT_CALL_1(READ_ONCE(sk->sk_write_space), + sk_stream_write_space, + sk); } /* Caller made space either from: @@ -6325,7 +6313,7 @@ static void tcp_urg(struct sock *sk, struct sk_buff *skb, const struct tcphdr *t BUG(); WRITE_ONCE(tp->urg_data, TCP_URG_VALID | tmp); if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_data_ready(sk); + READ_ONCE(sk->sk_data_ready)(sk); } } } @@ -7658,6 +7646,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, const struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); struct sock *fastopen_sk = NULL; + union tcp_seq_and_ts_off st; struct request_sock *req; bool want_cookie = false; struct dst_entry *dst; @@ -7727,9 +7716,12 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, if (!dst) goto drop_and_free; + if (tmp_opt.tstamp_ok || (!want_cookie && !isn)) + st = af_ops->init_seq_and_ts_off(net, skb); + if (tmp_opt.tstamp_ok) { tcp_rsk(req)->req_usec_ts = dst_tcp_usec_ts(dst); - tcp_rsk(req)->ts_off = af_ops->init_ts_off(net, skb); + tcp_rsk(req)->ts_off = st.ts_off; } if (!want_cookie && !isn) { int max_syn_backlog = READ_ONCE(net->ipv4.sysctl_max_syn_backlog); @@ -7751,7 +7743,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, goto drop_and_release; } - isn = af_ops->init_seq(skb); + isn = st.seq; } tcp_ecn_create_request(req, skb, sk, dst); @@ -7792,7 +7784,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, sock_put(fastopen_sk); goto drop_and_free; } - sk->sk_data_ready(sk); + READ_ONCE(sk->sk_data_ready)(sk); bh_unlock_sock(fastopen_sk); sock_put(fastopen_sk); } else { diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index d53d39be291a..c7b2463c2e25 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -88,6 +88,7 @@ #include <linux/skbuff_ref.h> #include <crypto/md5.h> +#include <crypto/utils.h> #include <trace/events/tcp.h> @@ -104,17 +105,14 @@ static DEFINE_PER_CPU(struct sock_bh_locked, ipv4_tcp_sk) = { static DEFINE_MUTEX(tcp_exit_batch_mutex); -static u32 tcp_v4_init_seq(const struct sk_buff *skb) +static union tcp_seq_and_ts_off +tcp_v4_init_seq_and_ts_off(const struct net *net, const struct sk_buff *skb) { - return secure_tcp_seq(ip_hdr(skb)->daddr, - ip_hdr(skb)->saddr, - tcp_hdr(skb)->dest, - tcp_hdr(skb)->source); -} - -static u32 tcp_v4_init_ts_off(const struct net *net, const struct sk_buff *skb) -{ - return secure_tcp_ts_off(net, ip_hdr(skb)->daddr, ip_hdr(skb)->saddr); + return secure_tcp_seq_and_ts_off(net, + ip_hdr(skb)->daddr, + ip_hdr(skb)->saddr, + tcp_hdr(skb)->dest, + tcp_hdr(skb)->source); } int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) @@ -326,15 +324,16 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len rt = NULL; if (likely(!tp->repair)) { + union tcp_seq_and_ts_off st; + + st = secure_tcp_seq_and_ts_off(net, + inet->inet_saddr, + inet->inet_daddr, + inet->inet_sport, + usin->sin_port); if (!tp->write_seq) - WRITE_ONCE(tp->write_seq, - secure_tcp_seq(inet->inet_saddr, - inet->inet_daddr, - inet->inet_sport, - usin->sin_port)); - WRITE_ONCE(tp->tsoffset, - secure_tcp_ts_off(net, inet->inet_saddr, - inet->inet_daddr)); + WRITE_ONCE(tp->write_seq, st.seq); + WRITE_ONCE(tp->tsoffset, st.ts_off); } atomic_set(&inet->inet_id, get_random_u16()); @@ -839,7 +838,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb, goto out; tcp_v4_md5_hash_skb(newhash, key, NULL, skb); - if (memcmp(md5_hash_location, newhash, 16) != 0) + if (crypto_memneq(md5_hash_location, newhash, 16)) goto out; } @@ -1676,8 +1675,7 @@ const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = { .cookie_init_seq = cookie_v4_init_sequence, #endif .route_req = tcp_v4_route_req, - .init_seq = tcp_v4_init_seq, - .init_ts_off = tcp_v4_init_ts_off, + .init_seq_and_ts_off = tcp_v4_init_seq_and_ts_off, .send_synack = tcp_v4_send_synack, }; diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index d9c5a43bd281..dafb63b923d0 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -1004,7 +1004,7 @@ enum skb_drop_reason tcp_child_process(struct sock *parent, struct sock *child, reason = tcp_rcv_state_process(child, skb); /* Wakeup parent, send SIGIO */ if (state == TCP_SYN_RECV && child->sk_state != state) - parent->sk_data_ready(parent); + READ_ONCE(parent->sk_data_ready)(parent); } else { /* Alas, it is possible again, because we do lookup * in main socket hash table and lock on listening diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 6c6b68a66dcd..b60fad393e18 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1787,7 +1787,7 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb) * using prepare_to_wait_exclusive(). */ while (nb) { - INDIRECT_CALL_1(sk->sk_data_ready, + INDIRECT_CALL_1(READ_ONCE(sk->sk_data_ready), sock_def_readable, sk); nb--; } @@ -2287,7 +2287,6 @@ void udp_lib_rehash(struct sock *sk, u16 newhash, u16 newhash4) udp_sk(sk)->udp_port_hash); hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash); nhslot2 = udp_hashslot2(udptable, newhash); - udp_sk(sk)->udp_portaddr_hash = newhash; if (hslot2 != nhslot2 || rcu_access_pointer(sk->sk_reuseport_cb)) { @@ -2321,19 +2320,25 @@ void udp_lib_rehash(struct sock *sk, u16 newhash, u16 newhash4) if (udp_hashed4(sk)) { spin_lock_bh(&hslot->lock); - udp_rehash4(udptable, sk, newhash4); - if (hslot2 != nhslot2) { - spin_lock(&hslot2->lock); - udp_hash4_dec(hslot2); - spin_unlock(&hslot2->lock); - - spin_lock(&nhslot2->lock); - udp_hash4_inc(nhslot2); - spin_unlock(&nhslot2->lock); + if (inet_rcv_saddr_any(sk)) { + udp_unhash4(udptable, sk); + } else { + udp_rehash4(udptable, sk, newhash4); + if (hslot2 != nhslot2) { + spin_lock(&hslot2->lock); + udp_hash4_dec(hslot2); + spin_unlock(&hslot2->lock); + + spin_lock(&nhslot2->lock); + udp_hash4_inc(nhslot2); + spin_unlock(&nhslot2->lock); + } } spin_unlock_bh(&hslot->lock); } + + udp_sk(sk)->udp_portaddr_hash = newhash; } } EXPORT_IPV6_MOD(udp_lib_rehash); diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c index 91233e37cd97..779a3a03762f 100644 --- a/net/ipv4/udp_bpf.c +++ b/net/ipv4/udp_bpf.c @@ -158,7 +158,7 @@ int udp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore) int family = sk->sk_family == AF_INET ? UDP_BPF_IPV4 : UDP_BPF_IPV6; if (restore) { - sk->sk_write_space = psock->saved_write_space; + WRITE_ONCE(sk->sk_write_space, psock->saved_write_space); sock_replace_proto(sk, psock->sk_proto); return 0; } diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 5e1da088d8e1..182d38e6d6d8 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -95,7 +95,8 @@ static inline int compute_score(struct sock *sk, const struct net *net, { int score = -1; - if (net_eq(sock_net(sk), net) && inet_sk(sk)->inet_num == hnum && + if (net_eq(sock_net(sk), net) && + READ_ONCE(inet_sk(sk)->inet_num) == hnum && sk->sk_family == PF_INET6) { if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr)) return -1; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 85df25c36409..08cd86f49bf9 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1063,7 +1063,8 @@ static struct net_device *ip6_rt_get_dev_rcu(const struct fib6_result *res) */ if (netif_is_l3_slave(dev) && !rt6_need_strict(&res->f6i->fib6_dst.addr)) - dev = l3mdev_master_dev_rcu(dev); + dev = l3mdev_master_dev_rcu(dev) ? : + dev_net(dev)->loopback_dev; else if (!netif_is_l3_master(dev)) dev = dev_net(dev)->loopback_dev; /* last case is netif_is_l3_master(dev) is true in which @@ -3582,7 +3583,6 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh, netdevice_tracker *dev_tracker = &fib6_nh->fib_nh_dev_tracker; struct net_device *dev = NULL; struct inet6_dev *idev = NULL; - int addr_type; int err; fib6_nh->fib_nh_family = AF_INET6; @@ -3624,11 +3624,10 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh, fib6_nh->fib_nh_weight = 1; - /* We cannot add true routes via loopback here, - * they would result in kernel looping; promote them to reject routes + /* Reset the nexthop device to the loopback device in case of reject + * routes. */ - addr_type = ipv6_addr_type(&cfg->fc_dst); - if (fib6_is_reject(cfg->fc_flags, dev, addr_type)) { + if (cfg->fc_flags & RTF_REJECT) { /* hold loopback dev/idev if we haven't done so. */ if (dev != net->loopback_dev) { if (dev) { diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 7e007f013ec8..4f6f0d751d6c 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -151,9 +151,14 @@ static struct request_sock *cookie_tcp_check(struct net *net, struct sock *sk, tcp_parse_options(net, skb, &tcp_opt, 0, NULL); if (tcp_opt.saw_tstamp && tcp_opt.rcv_tsecr) { - tsoff = secure_tcpv6_ts_off(net, - ipv6_hdr(skb)->daddr.s6_addr32, - ipv6_hdr(skb)->saddr.s6_addr32); + union tcp_seq_and_ts_off st; + + st = secure_tcpv6_seq_and_ts_off(net, + ipv6_hdr(skb)->daddr.s6_addr32, + ipv6_hdr(skb)->saddr.s6_addr32, + tcp_hdr(skb)->dest, + tcp_hdr(skb)->source); + tsoff = st.ts_off; tcp_opt.rcv_tsecr -= tsoff; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index e46a0efae012..bb09d5ccf599 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -68,6 +68,7 @@ #include <linux/seq_file.h> #include <crypto/md5.h> +#include <crypto/utils.h> #include <trace/events/tcp.h> @@ -104,18 +105,14 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) } } -static u32 tcp_v6_init_seq(const struct sk_buff *skb) +static union tcp_seq_and_ts_off +tcp_v6_init_seq_and_ts_off(const struct net *net, const struct sk_buff *skb) { - return secure_tcpv6_seq(ipv6_hdr(skb)->daddr.s6_addr32, - ipv6_hdr(skb)->saddr.s6_addr32, - tcp_hdr(skb)->dest, - tcp_hdr(skb)->source); -} - -static u32 tcp_v6_init_ts_off(const struct net *net, const struct sk_buff *skb) -{ - return secure_tcpv6_ts_off(net, ipv6_hdr(skb)->daddr.s6_addr32, - ipv6_hdr(skb)->saddr.s6_addr32); + return secure_tcpv6_seq_and_ts_off(net, + ipv6_hdr(skb)->daddr.s6_addr32, + ipv6_hdr(skb)->saddr.s6_addr32, + tcp_hdr(skb)->dest, + tcp_hdr(skb)->source); } static int tcp_v6_pre_connect(struct sock *sk, struct sockaddr_unsized *uaddr, @@ -319,14 +316,16 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr_unsized *uaddr, sk_set_txhash(sk); if (likely(!tp->repair)) { + union tcp_seq_and_ts_off st; + + st = secure_tcpv6_seq_and_ts_off(net, + np->saddr.s6_addr32, + sk->sk_v6_daddr.s6_addr32, + inet->inet_sport, + inet->inet_dport); if (!tp->write_seq) - WRITE_ONCE(tp->write_seq, - secure_tcpv6_seq(np->saddr.s6_addr32, - sk->sk_v6_daddr.s6_addr32, - inet->inet_sport, - inet->inet_dport)); - tp->tsoffset = secure_tcpv6_ts_off(net, np->saddr.s6_addr32, - sk->sk_v6_daddr.s6_addr32); + WRITE_ONCE(tp->write_seq, st.seq); + tp->tsoffset = st.ts_off; } if (tcp_fastopen_defer_connect(sk, &err)) @@ -816,8 +815,7 @@ const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = { .cookie_init_seq = cookie_v6_init_sequence, #endif .route_req = tcp_v6_route_req, - .init_seq = tcp_v6_init_seq, - .init_ts_off = tcp_v6_init_ts_off, + .init_seq_and_ts_off = tcp_v6_init_seq_and_ts_off, .send_synack = tcp_v6_send_synack, }; @@ -1048,7 +1046,7 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb, key.type = TCP_KEY_MD5; tcp_v6_md5_hash_skb(newhash, key.md5_key, NULL, skb); - if (memcmp(md5_hash_location, newhash, 16) != 0) + if (crypto_memneq(md5_hash_location, newhash, 16)) goto out; } #endif diff --git a/net/mac80211/eht.c b/net/mac80211/eht.c index 75096b2195d2..078e1e23d8d1 100644 --- a/net/mac80211/eht.c +++ b/net/mac80211/eht.c @@ -154,6 +154,7 @@ void ieee80211_rx_eml_op_mode_notif(struct ieee80211_sub_if_data *sdata, u8 *ptr = mgmt->u.action.u.eml_omn.variable; struct ieee80211_eml_params eml_params = { .link_id = status->link_id, + .control = control, }; struct sta_info *sta; int opt_len = 0; diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 7298836469b3..57a456690406 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -212,9 +212,24 @@ void mptcp_pm_send_ack(struct mptcp_sock *msk, spin_lock_bh(&msk->pm.lock); } -void mptcp_pm_addr_send_ack(struct mptcp_sock *msk) +static bool subflow_in_rm_list(const struct mptcp_subflow_context *subflow, + const struct mptcp_rm_list *rm_list) +{ + u8 i, id = subflow_get_local_id(subflow); + + for (i = 0; i < rm_list->nr; i++) { + if (rm_list->ids[i] == id) + return true; + } + + return false; +} + +static void +mptcp_pm_addr_send_ack_avoid_list(struct mptcp_sock *msk, + const struct mptcp_rm_list *rm_list) { - struct mptcp_subflow_context *subflow, *alt = NULL; + struct mptcp_subflow_context *subflow, *stale = NULL, *same_id = NULL; msk_owned_by_me(msk); lockdep_assert_held(&msk->pm.lock); @@ -224,19 +239,35 @@ void mptcp_pm_addr_send_ack(struct mptcp_sock *msk) return; mptcp_for_each_subflow(msk, subflow) { - if (__mptcp_subflow_active(subflow)) { - if (!subflow->stale) { - mptcp_pm_send_ack(msk, subflow, false, false); - return; - } + if (!__mptcp_subflow_active(subflow)) + continue; - if (!alt) - alt = subflow; + if (unlikely(subflow->stale)) { + if (!stale) + stale = subflow; + } else if (unlikely(rm_list && + subflow_in_rm_list(subflow, rm_list))) { + if (!same_id) + same_id = subflow; + } else { + goto send_ack; } } - if (alt) - mptcp_pm_send_ack(msk, alt, false, false); + if (same_id) + subflow = same_id; + else if (stale) + subflow = stale; + else + return; + +send_ack: + mptcp_pm_send_ack(msk, subflow, false, false); +} + +void mptcp_pm_addr_send_ack(struct mptcp_sock *msk) +{ + mptcp_pm_addr_send_ack_avoid_list(msk, NULL); } int mptcp_pm_mp_prio_send_ack(struct mptcp_sock *msk, @@ -470,7 +501,7 @@ int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_ msk->pm.rm_list_tx = *rm_list; rm_addr |= BIT(MPTCP_RM_ADDR_SIGNAL); WRITE_ONCE(msk->pm.addr_signal, rm_addr); - mptcp_pm_addr_send_ack(msk); + mptcp_pm_addr_send_ack_avoid_list(msk, rm_list); return 0; } diff --git a/net/mptcp/pm_kernel.c b/net/mptcp/pm_kernel.c index b5316a6c7d1b..b2b9df43960e 100644 --- a/net/mptcp/pm_kernel.c +++ b/net/mptcp/pm_kernel.c @@ -418,6 +418,15 @@ subflow: } exit: + /* If an endpoint has both the signal and subflow flags, but it is not + * possible to create subflows -- the 'while' loop body above never + * executed -- then still mark the endp as used, which is somehow the + * case. This avoids issues later when removing the endpoint and calling + * __mark_subflow_endp_available(), which expects the increment here. + */ + if (signal_and_subflow && local.addr.id != msk->mpc_endpoint_id) + msk->pm.local_addr_used++; + mptcp_pm_nl_check_work_pending(msk); } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index fd7f7e4e2a43..1862bd7fe804 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -833,6 +833,11 @@ static void nft_map_catchall_deactivate(const struct nft_ctx *ctx, } } +/* Use NFT_ITER_UPDATE iterator even if this may be called from the preparation + * phase, the set clone might already exist from a previous command, or it might + * be a set that is going away and does not require a clone. The netns and + * netlink release paths also need to work on the live set. + */ static void nft_map_deactivate(const struct nft_ctx *ctx, struct nft_set *set) { struct nft_set_iter iter = { @@ -7170,6 +7175,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, struct nft_data_desc desc; enum nft_registers dreg; struct nft_trans *trans; + bool set_full = false; u64 expiration; u64 timeout; int err, i; @@ -7461,10 +7467,18 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (err < 0) goto err_elem_free; + if (!(flags & NFT_SET_ELEM_CATCHALL)) { + unsigned int max = nft_set_maxsize(set), nelems; + + nelems = atomic_inc_return(&set->nelems); + if (nelems > max) + set_full = true; + } + trans = nft_trans_elem_alloc(ctx, NFT_MSG_NEWSETELEM, set); if (trans == NULL) { err = -ENOMEM; - goto err_elem_free; + goto err_set_size; } ext->genmask = nft_genmask_cur(ctx->net); @@ -7516,7 +7530,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, ue->priv = elem_priv; nft_trans_commit_list_add_elem(ctx->net, trans); - goto err_elem_free; + goto err_set_size; } } } @@ -7534,23 +7548,16 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, goto err_element_clash; } - if (!(flags & NFT_SET_ELEM_CATCHALL)) { - unsigned int max = nft_set_maxsize(set); - - if (!atomic_add_unless(&set->nelems, 1, max)) { - err = -ENFILE; - goto err_set_full; - } - } - nft_trans_container_elem(trans)->elems[0].priv = elem.priv; nft_trans_commit_list_add_elem(ctx->net, trans); - return 0; -err_set_full: - nft_setelem_remove(ctx->net, set, elem.priv); + return set_full ? -ENFILE : 0; + err_element_clash: kfree(trans); +err_set_size: + if (!(flags & NFT_SET_ELEM_CATCHALL)) + atomic_dec(&set->nelems); err_elem_free: nf_tables_set_elem_destroy(ctx, set, elem.priv); err_parse_data: @@ -7901,9 +7908,12 @@ static int nft_set_catchall_flush(const struct nft_ctx *ctx, static int nft_set_flush(struct nft_ctx *ctx, struct nft_set *set, u8 genmask) { + /* The set backend might need to clone the set, do it now from the + * preparation phase, use NFT_ITER_UPDATE_CLONE iterator type. + */ struct nft_set_iter iter = { .genmask = genmask, - .type = NFT_ITER_UPDATE, + .type = NFT_ITER_UPDATE_CLONE, .fn = nft_setelem_flush, }; @@ -10483,11 +10493,6 @@ static void nft_trans_gc_queue_work(struct nft_trans_gc *trans) schedule_work(&trans_gc_work); } -static int nft_trans_gc_space(struct nft_trans_gc *trans) -{ - return NFT_TRANS_GC_BATCHCOUNT - trans->count; -} - struct nft_trans_gc *nft_trans_gc_queue_async(struct nft_trans_gc *gc, unsigned int gc_seq, gfp_t gfp) { diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 739b992bde59..b0e571c8e3f3 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -374,6 +374,7 @@ static void nft_rhash_walk(const struct nft_ctx *ctx, struct nft_set *set, { switch (iter->type) { case NFT_ITER_UPDATE: + case NFT_ITER_UPDATE_CLONE: /* only relevant for netlink dumps which use READ type */ WARN_ON_ONCE(iter->skip != 0); diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 7ef4b44471d3..a34632ae6048 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1680,11 +1680,11 @@ static void nft_pipapo_gc_deactivate(struct net *net, struct nft_set *set, } /** - * pipapo_gc() - Drop expired entries from set, destroy start and end elements + * pipapo_gc_scan() - Drop expired entries from set and link them to gc list * @set: nftables API set representation * @m: Matching data */ -static void pipapo_gc(struct nft_set *set, struct nft_pipapo_match *m) +static void pipapo_gc_scan(struct nft_set *set, struct nft_pipapo_match *m) { struct nft_pipapo *priv = nft_set_priv(set); struct net *net = read_pnet(&set->net); @@ -1697,6 +1697,8 @@ static void pipapo_gc(struct nft_set *set, struct nft_pipapo_match *m) if (!gc) return; + list_add(&gc->list, &priv->gc_head); + while ((rules_f0 = pipapo_rules_same_key(m->f, first_rule))) { union nft_pipapo_map_bucket rulemap[NFT_PIPAPO_MAX_FIELDS]; const struct nft_pipapo_field *f; @@ -1724,9 +1726,13 @@ static void pipapo_gc(struct nft_set *set, struct nft_pipapo_match *m) * NFT_SET_ELEM_DEAD_BIT. */ if (__nft_set_elem_expired(&e->ext, tstamp)) { - gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL); - if (!gc) - return; + if (!nft_trans_gc_space(gc)) { + gc = nft_trans_gc_alloc(set, 0, GFP_KERNEL); + if (!gc) + return; + + list_add(&gc->list, &priv->gc_head); + } nft_pipapo_gc_deactivate(net, set, e); pipapo_drop(m, rulemap); @@ -1740,10 +1746,30 @@ static void pipapo_gc(struct nft_set *set, struct nft_pipapo_match *m) } } - gc = nft_trans_gc_catchall_sync(gc); + priv->last_gc = jiffies; +} + +/** + * pipapo_gc_queue() - Free expired elements + * @set: nftables API set representation + */ +static void pipapo_gc_queue(struct nft_set *set) +{ + struct nft_pipapo *priv = nft_set_priv(set); + struct nft_trans_gc *gc, *next; + + /* always do a catchall cycle: */ + gc = nft_trans_gc_alloc(set, 0, GFP_KERNEL); if (gc) { + gc = nft_trans_gc_catchall_sync(gc); + if (gc) + nft_trans_gc_queue_sync_done(gc); + } + + /* always purge queued gc elements. */ + list_for_each_entry_safe(gc, next, &priv->gc_head, list) { + list_del(&gc->list); nft_trans_gc_queue_sync_done(gc); - priv->last_gc = jiffies; } } @@ -1797,6 +1823,10 @@ static void pipapo_reclaim_match(struct rcu_head *rcu) * * We also need to create a new working copy for subsequent insertions and * deletions. + * + * After the live copy has been replaced by the clone, we can safely queue + * expired elements that have been collected by pipapo_gc_scan() for + * memory reclaim. */ static void nft_pipapo_commit(struct nft_set *set) { @@ -1807,7 +1837,7 @@ static void nft_pipapo_commit(struct nft_set *set) return; if (time_after_eq(jiffies, priv->last_gc + nft_set_gc_interval(set))) - pipapo_gc(set, priv->clone); + pipapo_gc_scan(set, priv->clone); old = rcu_replace_pointer(priv->match, priv->clone, nft_pipapo_transaction_mutex_held(set)); @@ -1815,6 +1845,8 @@ static void nft_pipapo_commit(struct nft_set *set) if (old) call_rcu(&old->rcu, pipapo_reclaim_match); + + pipapo_gc_queue(set); } static void nft_pipapo_abort(const struct nft_set *set) @@ -2144,13 +2176,20 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_pipapo_match *m; switch (iter->type) { - case NFT_ITER_UPDATE: + case NFT_ITER_UPDATE_CLONE: m = pipapo_maybe_clone(set); if (!m) { iter->err = -ENOMEM; return; } - + nft_pipapo_do_walk(ctx, set, m, iter); + break; + case NFT_ITER_UPDATE: + if (priv->clone) + m = priv->clone; + else + m = rcu_dereference_protected(priv->match, + nft_pipapo_transaction_mutex_held(set)); nft_pipapo_do_walk(ctx, set, m, iter); break; case NFT_ITER_READ: @@ -2272,6 +2311,7 @@ static int nft_pipapo_init(const struct nft_set *set, f->mt = NULL; } + INIT_LIST_HEAD(&priv->gc_head); rcu_assign_pointer(priv->match, m); return 0; @@ -2321,6 +2361,8 @@ static void nft_pipapo_destroy(const struct nft_ctx *ctx, struct nft_pipapo *priv = nft_set_priv(set); struct nft_pipapo_match *m; + WARN_ON_ONCE(!list_empty(&priv->gc_head)); + m = rcu_dereference_protected(priv->match, true); if (priv->clone) { diff --git a/net/netfilter/nft_set_pipapo.h b/net/netfilter/nft_set_pipapo.h index eaab422aa56a..9aee9a9eaeb7 100644 --- a/net/netfilter/nft_set_pipapo.h +++ b/net/netfilter/nft_set_pipapo.h @@ -156,12 +156,14 @@ struct nft_pipapo_match { * @clone: Copy where pending insertions and deletions are kept * @width: Total bytes to be matched for one packet, including padding * @last_gc: Timestamp of last garbage collection run, jiffies + * @gc_head: list of nft_trans_gc to queue up for mem reclaim */ struct nft_pipapo { struct nft_pipapo_match __rcu *match; struct nft_pipapo_match *clone; int width; unsigned long last_gc; + struct list_head gc_head; }; struct nft_pipapo_elem; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 3f02e4478216..ee3d4f5b9ff7 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -861,13 +861,15 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx, struct nft_rbtree *priv = nft_set_priv(set); switch (iter->type) { - case NFT_ITER_UPDATE: - lockdep_assert_held(&nft_pernet(ctx->net)->commit_mutex); - + case NFT_ITER_UPDATE_CLONE: if (nft_array_may_resize(set) < 0) { iter->err = -ENOMEM; break; } + fallthrough; + case NFT_ITER_UPDATE: + lockdep_assert_held(&nft_pernet(ctx->net)->commit_mutex); + nft_rbtree_do_walk(ctx, set, iter); break; case NFT_ITER_READ: diff --git a/net/nfc/digital_core.c b/net/nfc/digital_core.c index 3670bb33732e..7cb1e6aaae90 100644 --- a/net/nfc/digital_core.c +++ b/net/nfc/digital_core.c @@ -707,8 +707,10 @@ static int digital_in_send(struct nfc_dev *nfc_dev, struct nfc_target *target, int rc; data_exch = kzalloc_obj(*data_exch); - if (!data_exch) + if (!data_exch) { + kfree_skb(skb); return -ENOMEM; + } data_exch->cb = cb; data_exch->cb_context = cb_context; @@ -731,8 +733,10 @@ static int digital_in_send(struct nfc_dev *nfc_dev, struct nfc_target *target, data_exch); exit: - if (rc) + if (rc) { + kfree_skb(skb); kfree(data_exch); + } return rc; } diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index 6e9b76e2cc56..43d871525dbc 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -567,6 +567,10 @@ static int nci_close_device(struct nci_dev *ndev) flush_workqueue(ndev->cmd_wq); timer_delete_sync(&ndev->cmd_timer); timer_delete_sync(&ndev->data_timer); + if (test_bit(NCI_DATA_EXCHANGE, &ndev->flags)) + nci_data_exchange_complete(ndev, NULL, + ndev->cur_conn_id, + -ENODEV); mutex_unlock(&ndev->req_lock); return 0; } @@ -598,6 +602,11 @@ static int nci_close_device(struct nci_dev *ndev) flush_workqueue(ndev->cmd_wq); timer_delete_sync(&ndev->cmd_timer); + timer_delete_sync(&ndev->data_timer); + + if (test_bit(NCI_DATA_EXCHANGE, &ndev->flags)) + nci_data_exchange_complete(ndev, NULL, ndev->cur_conn_id, + -ENODEV); /* Clear flags except NCI_UNREG */ ndev->flags &= BIT(NCI_UNREG); @@ -1035,18 +1044,23 @@ static int nci_transceive(struct nfc_dev *nfc_dev, struct nfc_target *target, struct nci_conn_info *conn_info; conn_info = ndev->rf_conn_info; - if (!conn_info) + if (!conn_info) { + kfree_skb(skb); return -EPROTO; + } pr_debug("target_idx %d, len %d\n", target->idx, skb->len); if (!ndev->target_active_prot) { pr_err("unable to exchange data, no active target\n"); + kfree_skb(skb); return -EINVAL; } - if (test_and_set_bit(NCI_DATA_EXCHANGE, &ndev->flags)) + if (test_and_set_bit(NCI_DATA_EXCHANGE, &ndev->flags)) { + kfree_skb(skb); return -EBUSY; + } /* store cb and context to be used on receiving data */ conn_info->data_exchange_cb = cb; @@ -1482,10 +1496,20 @@ static bool nci_valid_size(struct sk_buff *skb) unsigned int hdr_size = NCI_CTRL_HDR_SIZE; if (skb->len < hdr_size || - !nci_plen(skb->data) || skb->len < hdr_size + nci_plen(skb->data)) { return false; } + + if (!nci_plen(skb->data)) { + /* Allow zero length in proprietary notifications (0x20 - 0x3F). */ + if (nci_opcode_oid(nci_opcode(skb->data)) >= 0x20 && + nci_mt(skb->data) == NCI_MT_NTF_PKT) + return true; + + /* Disallow zero length otherwise. */ + return false; + } + return true; } diff --git a/net/nfc/nci/data.c b/net/nfc/nci/data.c index 78f4131af3cf..5f98c73db5af 100644 --- a/net/nfc/nci/data.c +++ b/net/nfc/nci/data.c @@ -33,7 +33,8 @@ void nci_data_exchange_complete(struct nci_dev *ndev, struct sk_buff *skb, conn_info = nci_get_conn_info_by_conn_id(ndev, conn_id); if (!conn_info) { kfree_skb(skb); - goto exit; + clear_bit(NCI_DATA_EXCHANGE, &ndev->flags); + return; } cb = conn_info->data_exchange_cb; @@ -45,6 +46,12 @@ void nci_data_exchange_complete(struct nci_dev *ndev, struct sk_buff *skb, timer_delete_sync(&ndev->data_timer); clear_bit(NCI_DATA_EXCHANGE_TO, &ndev->flags); + /* Mark the exchange as done before calling the callback. + * The callback (e.g. rawsock_data_exchange_complete) may + * want to immediately queue another data exchange. + */ + clear_bit(NCI_DATA_EXCHANGE, &ndev->flags); + if (cb) { /* forward skb to nfc core */ cb(cb_context, skb, err); @@ -54,9 +61,6 @@ void nci_data_exchange_complete(struct nci_dev *ndev, struct sk_buff *skb, /* no waiting callback, free skb */ kfree_skb(skb); } - -exit: - clear_bit(NCI_DATA_EXCHANGE, &ndev->flags); } /* ----------------- NCI TX Data ----------------- */ diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c index b049022399ae..f7d7a599fade 100644 --- a/net/nfc/rawsock.c +++ b/net/nfc/rawsock.c @@ -67,6 +67,17 @@ static int rawsock_release(struct socket *sock) if (sock->type == SOCK_RAW) nfc_sock_unlink(&raw_sk_list, sk); + if (sk->sk_state == TCP_ESTABLISHED) { + /* Prevent rawsock_tx_work from starting new transmits and + * wait for any in-progress work to finish. This must happen + * before the socket is orphaned to avoid a race where + * rawsock_tx_work runs after the NCI device has been freed. + */ + sk->sk_shutdown |= SEND_SHUTDOWN; + cancel_work_sync(&nfc_rawsock(sk)->tx_work); + rawsock_write_queue_purge(sk); + } + sock_orphan(sk); sock_put(sk); diff --git a/net/rds/tcp.c b/net/rds/tcp.c index 04f310255692..654e23d13e3d 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -490,18 +490,24 @@ bool rds_tcp_tune(struct socket *sock) struct rds_tcp_net *rtn; tcp_sock_set_nodelay(sock->sk); - lock_sock(sk); /* TCP timer functions might access net namespace even after * a process which created this net namespace terminated. */ if (!sk->sk_net_refcnt) { - if (!maybe_get_net(net)) { - release_sock(sk); + if (!maybe_get_net(net)) return false; - } + /* + * sk_net_refcnt_upgrade() must be called before lock_sock() + * because it does a GFP_KERNEL allocation, which can trigger + * fs_reclaim and create a circular lock dependency with the + * socket lock. The fields it modifies (sk_net_refcnt, + * ns_tracker) are not accessed by any concurrent code path + * at this point. + */ sk_net_refcnt_upgrade(sk); put_net(net); } + lock_sock(sk); rtn = net_generic(net, rds_tcp_netid); if (rtn->sndbuf_size > 0) { sk->sk_sndbuf = rtn->sndbuf_size; diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index bd51522c7953..7d5e50c921a0 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -1360,6 +1360,12 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla, return -EINVAL; } + if (bind && !(flags & TCA_ACT_FLAGS_AT_INGRESS_OR_CLSACT)) { + NL_SET_ERR_MSG_MOD(extack, + "Attaching ct to a non ingress/clsact qdisc is unsupported"); + return -EOPNOTSUPP; + } + err = nla_parse_nested(tb, TCA_CT_MAX, nla, ct_policy, extack); if (err < 0) return err; diff --git a/net/sched/act_gate.c b/net/sched/act_gate.c index 686eaed81b81..fdbfcaa3e2ab 100644 --- a/net/sched/act_gate.c +++ b/net/sched/act_gate.c @@ -32,9 +32,12 @@ static ktime_t gate_get_time(struct tcf_gate *gact) return KTIME_MAX; } -static void gate_get_start_time(struct tcf_gate *gact, ktime_t *start) +static void tcf_gate_params_free_rcu(struct rcu_head *head); + +static void gate_get_start_time(struct tcf_gate *gact, + const struct tcf_gate_params *param, + ktime_t *start) { - struct tcf_gate_params *param = &gact->param; ktime_t now, base, cycle; u64 n; @@ -69,12 +72,14 @@ static enum hrtimer_restart gate_timer_func(struct hrtimer *timer) { struct tcf_gate *gact = container_of(timer, struct tcf_gate, hitimer); - struct tcf_gate_params *p = &gact->param; struct tcfg_gate_entry *next; + struct tcf_gate_params *p; ktime_t close_time, now; spin_lock(&gact->tcf_lock); + p = rcu_dereference_protected(gact->param, + lockdep_is_held(&gact->tcf_lock)); next = gact->next_entry; /* cycle start, clear pending bit, clear total octets */ @@ -225,6 +230,35 @@ static void release_entry_list(struct list_head *entries) } } +static int tcf_gate_copy_entries(struct tcf_gate_params *dst, + const struct tcf_gate_params *src, + struct netlink_ext_ack *extack) +{ + struct tcfg_gate_entry *entry; + int i = 0; + + list_for_each_entry(entry, &src->entries, list) { + struct tcfg_gate_entry *new; + + new = kzalloc(sizeof(*new), GFP_ATOMIC); + if (!new) { + NL_SET_ERR_MSG(extack, "Not enough memory for entry"); + return -ENOMEM; + } + + new->index = entry->index; + new->gate_state = entry->gate_state; + new->interval = entry->interval; + new->ipv = entry->ipv; + new->maxoctets = entry->maxoctets; + list_add_tail(&new->list, &dst->entries); + i++; + } + + dst->num_entries = i; + return 0; +} + static int parse_gate_list(struct nlattr *list_attr, struct tcf_gate_params *sched, struct netlink_ext_ack *extack) @@ -270,24 +304,44 @@ release_list: return err; } -static void gate_setup_timer(struct tcf_gate *gact, u64 basetime, - enum tk_offsets tko, s32 clockid, - bool do_init) +static bool gate_timer_needs_cancel(u64 basetime, u64 old_basetime, + enum tk_offsets tko, + enum tk_offsets old_tko, + s32 clockid, s32 old_clockid) { - if (!do_init) { - if (basetime == gact->param.tcfg_basetime && - tko == gact->tk_offset && - clockid == gact->param.tcfg_clockid) - return; + return basetime != old_basetime || + clockid != old_clockid || + tko != old_tko; +} - spin_unlock_bh(&gact->tcf_lock); - hrtimer_cancel(&gact->hitimer); - spin_lock_bh(&gact->tcf_lock); +static int gate_clock_resolve(s32 clockid, enum tk_offsets *tko, + struct netlink_ext_ack *extack) +{ + switch (clockid) { + case CLOCK_REALTIME: + *tko = TK_OFFS_REAL; + return 0; + case CLOCK_MONOTONIC: + *tko = TK_OFFS_MAX; + return 0; + case CLOCK_BOOTTIME: + *tko = TK_OFFS_BOOT; + return 0; + case CLOCK_TAI: + *tko = TK_OFFS_TAI; + return 0; + default: + NL_SET_ERR_MSG(extack, "Invalid 'clockid'"); + return -EINVAL; } - gact->param.tcfg_basetime = basetime; - gact->param.tcfg_clockid = clockid; - gact->tk_offset = tko; - hrtimer_setup(&gact->hitimer, gate_timer_func, clockid, HRTIMER_MODE_ABS_SOFT); +} + +static void gate_setup_timer(struct tcf_gate *gact, s32 clockid, + enum tk_offsets tko) +{ + WRITE_ONCE(gact->tk_offset, tko); + hrtimer_setup(&gact->hitimer, gate_timer_func, clockid, + HRTIMER_MODE_ABS_SOFT); } static int tcf_gate_init(struct net *net, struct nlattr *nla, @@ -296,15 +350,22 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, act_gate_ops.net_id); - enum tk_offsets tk_offset = TK_OFFS_TAI; + u64 cycletime = 0, basetime = 0, cycletime_ext = 0; + struct tcf_gate_params *p = NULL, *old_p = NULL; + enum tk_offsets old_tk_offset = TK_OFFS_TAI; + const struct tcf_gate_params *cur_p = NULL; bool bind = flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_GATE_MAX + 1]; + enum tk_offsets tko = TK_OFFS_TAI; struct tcf_chain *goto_ch = NULL; - u64 cycletime = 0, basetime = 0; - struct tcf_gate_params *p; + s32 timer_clockid = CLOCK_TAI; + bool use_old_entries = false; + s32 old_clockid = CLOCK_TAI; + bool need_cancel = false; s32 clockid = CLOCK_TAI; struct tcf_gate *gact; struct tc_gate *parm; + u64 old_basetime = 0; int ret = 0, err; u32 gflags = 0; s32 prio = -1; @@ -321,26 +382,8 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla, if (!tb[TCA_GATE_PARMS]) return -EINVAL; - if (tb[TCA_GATE_CLOCKID]) { + if (tb[TCA_GATE_CLOCKID]) clockid = nla_get_s32(tb[TCA_GATE_CLOCKID]); - switch (clockid) { - case CLOCK_REALTIME: - tk_offset = TK_OFFS_REAL; - break; - case CLOCK_MONOTONIC: - tk_offset = TK_OFFS_MAX; - break; - case CLOCK_BOOTTIME: - tk_offset = TK_OFFS_BOOT; - break; - case CLOCK_TAI: - tk_offset = TK_OFFS_TAI; - break; - default: - NL_SET_ERR_MSG(extack, "Invalid 'clockid'"); - return -EINVAL; - } - } parm = nla_data(tb[TCA_GATE_PARMS]); index = parm->index; @@ -366,6 +409,60 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla, return -EEXIST; } + gact = to_gate(*a); + + err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); + if (err < 0) + goto release_idr; + + p = kzalloc(sizeof(*p), GFP_KERNEL); + if (!p) { + err = -ENOMEM; + goto chain_put; + } + INIT_LIST_HEAD(&p->entries); + + use_old_entries = !tb[TCA_GATE_ENTRY_LIST]; + if (!use_old_entries) { + err = parse_gate_list(tb[TCA_GATE_ENTRY_LIST], p, extack); + if (err < 0) + goto err_free; + use_old_entries = !err; + } + + if (ret == ACT_P_CREATED && use_old_entries) { + NL_SET_ERR_MSG(extack, "The entry list is empty"); + err = -EINVAL; + goto err_free; + } + + if (ret != ACT_P_CREATED) { + rcu_read_lock(); + cur_p = rcu_dereference(gact->param); + + old_basetime = cur_p->tcfg_basetime; + old_clockid = cur_p->tcfg_clockid; + old_tk_offset = READ_ONCE(gact->tk_offset); + + basetime = old_basetime; + cycletime_ext = cur_p->tcfg_cycletime_ext; + prio = cur_p->tcfg_priority; + gflags = cur_p->tcfg_flags; + + if (!tb[TCA_GATE_CLOCKID]) + clockid = old_clockid; + + err = 0; + if (use_old_entries) { + err = tcf_gate_copy_entries(p, cur_p, extack); + if (!err && !tb[TCA_GATE_CYCLE_TIME]) + cycletime = cur_p->tcfg_cycletime; + } + rcu_read_unlock(); + if (err) + goto err_free; + } + if (tb[TCA_GATE_PRIORITY]) prio = nla_get_s32(tb[TCA_GATE_PRIORITY]); @@ -375,25 +472,26 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla, if (tb[TCA_GATE_FLAGS]) gflags = nla_get_u32(tb[TCA_GATE_FLAGS]); - gact = to_gate(*a); - if (ret == ACT_P_CREATED) - INIT_LIST_HEAD(&gact->param.entries); + if (tb[TCA_GATE_CYCLE_TIME]) + cycletime = nla_get_u64(tb[TCA_GATE_CYCLE_TIME]); - err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); - if (err < 0) - goto release_idr; + if (tb[TCA_GATE_CYCLE_TIME_EXT]) + cycletime_ext = nla_get_u64(tb[TCA_GATE_CYCLE_TIME_EXT]); - spin_lock_bh(&gact->tcf_lock); - p = &gact->param; + err = gate_clock_resolve(clockid, &tko, extack); + if (err) + goto err_free; + timer_clockid = clockid; - if (tb[TCA_GATE_CYCLE_TIME]) - cycletime = nla_get_u64(tb[TCA_GATE_CYCLE_TIME]); + need_cancel = ret != ACT_P_CREATED && + gate_timer_needs_cancel(basetime, old_basetime, + tko, old_tk_offset, + timer_clockid, old_clockid); - if (tb[TCA_GATE_ENTRY_LIST]) { - err = parse_gate_list(tb[TCA_GATE_ENTRY_LIST], p, extack); - if (err < 0) - goto chain_put; - } + if (need_cancel) + hrtimer_cancel(&gact->hitimer); + + spin_lock_bh(&gact->tcf_lock); if (!cycletime) { struct tcfg_gate_entry *entry; @@ -402,22 +500,20 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla, list_for_each_entry(entry, &p->entries, list) cycle = ktime_add_ns(cycle, entry->interval); cycletime = cycle; - if (!cycletime) { - err = -EINVAL; - goto chain_put; - } } p->tcfg_cycletime = cycletime; + p->tcfg_cycletime_ext = cycletime_ext; - if (tb[TCA_GATE_CYCLE_TIME_EXT]) - p->tcfg_cycletime_ext = - nla_get_u64(tb[TCA_GATE_CYCLE_TIME_EXT]); - - gate_setup_timer(gact, basetime, tk_offset, clockid, - ret == ACT_P_CREATED); + if (need_cancel || ret == ACT_P_CREATED) + gate_setup_timer(gact, timer_clockid, tko); p->tcfg_priority = prio; p->tcfg_flags = gflags; - gate_get_start_time(gact, &start); + p->tcfg_basetime = basetime; + p->tcfg_clockid = timer_clockid; + gate_get_start_time(gact, p, &start); + + old_p = rcu_replace_pointer(gact->param, p, + lockdep_is_held(&gact->tcf_lock)); gact->current_close_time = start; gact->current_gate_status = GATE_ACT_GATE_OPEN | GATE_ACT_PENDING; @@ -434,11 +530,15 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla, if (goto_ch) tcf_chain_put_by_act(goto_ch); + if (old_p) + call_rcu(&old_p->rcu, tcf_gate_params_free_rcu); + return ret; +err_free: + release_entry_list(&p->entries); + kfree(p); chain_put: - spin_unlock_bh(&gact->tcf_lock); - if (goto_ch) tcf_chain_put_by_act(goto_ch); release_idr: @@ -446,21 +546,29 @@ release_idr: * without taking tcf_lock. */ if (ret == ACT_P_CREATED) - gate_setup_timer(gact, gact->param.tcfg_basetime, - gact->tk_offset, gact->param.tcfg_clockid, - true); + gate_setup_timer(gact, timer_clockid, tko); + tcf_idr_release(*a, bind); return err; } +static void tcf_gate_params_free_rcu(struct rcu_head *head) +{ + struct tcf_gate_params *p = container_of(head, struct tcf_gate_params, rcu); + + release_entry_list(&p->entries); + kfree(p); +} + static void tcf_gate_cleanup(struct tc_action *a) { struct tcf_gate *gact = to_gate(a); struct tcf_gate_params *p; - p = &gact->param; hrtimer_cancel(&gact->hitimer); - release_entry_list(&p->entries); + p = rcu_dereference_protected(gact->param, 1); + if (p) + call_rcu(&p->rcu, tcf_gate_params_free_rcu); } static int dumping_entry(struct sk_buff *skb, @@ -509,10 +617,9 @@ static int tcf_gate_dump(struct sk_buff *skb, struct tc_action *a, struct nlattr *entry_list; struct tcf_t t; - spin_lock_bh(&gact->tcf_lock); - opt.action = gact->tcf_action; - - p = &gact->param; + rcu_read_lock(); + opt.action = READ_ONCE(gact->tcf_action); + p = rcu_dereference(gact->param); if (nla_put(skb, TCA_GATE_PARMS, sizeof(opt), &opt)) goto nla_put_failure; @@ -552,12 +659,12 @@ static int tcf_gate_dump(struct sk_buff *skb, struct tc_action *a, tcf_tm_dump(&t, &gact->tcf_tm); if (nla_put_64bit(skb, TCA_GATE_TM, sizeof(t), &t, TCA_GATE_PAD)) goto nla_put_failure; - spin_unlock_bh(&gact->tcf_lock); + rcu_read_unlock(); return skb->len; nla_put_failure: - spin_unlock_bh(&gact->tcf_lock); + rcu_read_unlock(); nlmsg_trim(skb, b); return -1; } diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 79df81d12894..d5e8a91bb4eb 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -293,8 +293,8 @@ static int load_metaops_and_vet(u32 metaid, void *val, int len, bool rtnl_held) /* called when adding new meta information */ static int __add_metainfo(const struct tcf_meta_ops *ops, - struct tcf_ife_info *ife, u32 metaid, void *metaval, - int len, bool atomic, bool exists) + struct tcf_ife_params *p, u32 metaid, void *metaval, + int len, bool atomic) { struct tcf_meta_info *mi = NULL; int ret = 0; @@ -313,45 +313,40 @@ static int __add_metainfo(const struct tcf_meta_ops *ops, } } - if (exists) - spin_lock_bh(&ife->tcf_lock); - list_add_tail(&mi->metalist, &ife->metalist); - if (exists) - spin_unlock_bh(&ife->tcf_lock); + list_add_tail(&mi->metalist, &p->metalist); return ret; } static int add_metainfo_and_get_ops(const struct tcf_meta_ops *ops, - struct tcf_ife_info *ife, u32 metaid, - bool exists) + struct tcf_ife_params *p, u32 metaid) { int ret; if (!try_module_get(ops->owner)) return -ENOENT; - ret = __add_metainfo(ops, ife, metaid, NULL, 0, true, exists); + ret = __add_metainfo(ops, p, metaid, NULL, 0, true); if (ret) module_put(ops->owner); return ret; } -static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval, - int len, bool exists) +static int add_metainfo(struct tcf_ife_params *p, u32 metaid, void *metaval, + int len) { const struct tcf_meta_ops *ops = find_ife_oplist(metaid); int ret; if (!ops) return -ENOENT; - ret = __add_metainfo(ops, ife, metaid, metaval, len, false, exists); + ret = __add_metainfo(ops, p, metaid, metaval, len, false); if (ret) /*put back what find_ife_oplist took */ module_put(ops->owner); return ret; } -static int use_all_metadata(struct tcf_ife_info *ife, bool exists) +static int use_all_metadata(struct tcf_ife_params *p) { struct tcf_meta_ops *o; int rc = 0; @@ -359,7 +354,7 @@ static int use_all_metadata(struct tcf_ife_info *ife, bool exists) read_lock(&ife_mod_lock); list_for_each_entry(o, &ifeoplist, list) { - rc = add_metainfo_and_get_ops(o, ife, o->metaid, exists); + rc = add_metainfo_and_get_ops(o, p, o->metaid); if (rc == 0) installed += 1; } @@ -371,7 +366,7 @@ static int use_all_metadata(struct tcf_ife_info *ife, bool exists) return -EINVAL; } -static int dump_metalist(struct sk_buff *skb, struct tcf_ife_info *ife) +static int dump_metalist(struct sk_buff *skb, struct tcf_ife_params *p) { struct tcf_meta_info *e; struct nlattr *nest; @@ -379,14 +374,14 @@ static int dump_metalist(struct sk_buff *skb, struct tcf_ife_info *ife) int total_encoded = 0; /*can only happen on decode */ - if (list_empty(&ife->metalist)) + if (list_empty(&p->metalist)) return 0; nest = nla_nest_start_noflag(skb, TCA_IFE_METALST); if (!nest) goto out_nlmsg_trim; - list_for_each_entry(e, &ife->metalist, metalist) { + list_for_each_entry(e, &p->metalist, metalist) { if (!e->ops->get(skb, e)) total_encoded += 1; } @@ -403,13 +398,11 @@ out_nlmsg_trim: return -1; } -/* under ife->tcf_lock */ -static void _tcf_ife_cleanup(struct tc_action *a) +static void __tcf_ife_cleanup(struct tcf_ife_params *p) { - struct tcf_ife_info *ife = to_ife(a); struct tcf_meta_info *e, *n; - list_for_each_entry_safe(e, n, &ife->metalist, metalist) { + list_for_each_entry_safe(e, n, &p->metalist, metalist) { list_del(&e->metalist); if (e->metaval) { if (e->ops->release) @@ -422,18 +415,23 @@ static void _tcf_ife_cleanup(struct tc_action *a) } } +static void tcf_ife_cleanup_params(struct rcu_head *head) +{ + struct tcf_ife_params *p = container_of(head, struct tcf_ife_params, + rcu); + + __tcf_ife_cleanup(p); + kfree(p); +} + static void tcf_ife_cleanup(struct tc_action *a) { struct tcf_ife_info *ife = to_ife(a); struct tcf_ife_params *p; - spin_lock_bh(&ife->tcf_lock); - _tcf_ife_cleanup(a); - spin_unlock_bh(&ife->tcf_lock); - p = rcu_dereference_protected(ife->params, 1); if (p) - kfree_rcu(p, rcu); + call_rcu(&p->rcu, tcf_ife_cleanup_params); } static int load_metalist(struct nlattr **tb, bool rtnl_held) @@ -455,8 +453,7 @@ static int load_metalist(struct nlattr **tb, bool rtnl_held) return 0; } -static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb, - bool exists, bool rtnl_held) +static int populate_metalist(struct tcf_ife_params *p, struct nlattr **tb) { int len = 0; int rc = 0; @@ -468,7 +465,7 @@ static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb, val = nla_data(tb[i]); len = nla_len(tb[i]); - rc = add_metainfo(ife, i, val, len, exists); + rc = add_metainfo(p, i, val, len); if (rc) return rc; } @@ -523,6 +520,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, p = kzalloc_obj(*p); if (!p) return -ENOMEM; + INIT_LIST_HEAD(&p->metalist); if (tb[TCA_IFE_METALST]) { err = nla_parse_nested_deprecated(tb2, IFE_META_MAX, @@ -567,8 +565,6 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, } ife = to_ife(*a); - if (ret == ACT_P_CREATED) - INIT_LIST_HEAD(&ife->metalist); err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); if (err < 0) @@ -600,8 +596,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, } if (tb[TCA_IFE_METALST]) { - err = populate_metalist(ife, tb2, exists, - !(flags & TCA_ACT_FLAGS_NO_RTNL)); + err = populate_metalist(p, tb2); if (err) goto metadata_parse_err; } else { @@ -610,7 +605,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, * as we can. You better have at least one else we are * going to bail out */ - err = use_all_metadata(ife, exists); + err = use_all_metadata(p); if (err) goto metadata_parse_err; } @@ -626,13 +621,14 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, if (goto_ch) tcf_chain_put_by_act(goto_ch); if (p) - kfree_rcu(p, rcu); + call_rcu(&p->rcu, tcf_ife_cleanup_params); return ret; metadata_parse_err: if (goto_ch) tcf_chain_put_by_act(goto_ch); release_idr: + __tcf_ife_cleanup(p); kfree(p); tcf_idr_release(*a, bind); return err; @@ -679,7 +675,7 @@ static int tcf_ife_dump(struct sk_buff *skb, struct tc_action *a, int bind, if (nla_put(skb, TCA_IFE_TYPE, 2, &p->eth_type)) goto nla_put_failure; - if (dump_metalist(skb, ife)) { + if (dump_metalist(skb, p)) { /*ignore failure to dump metalist */ pr_info("Failed to dump metalist\n"); } @@ -693,13 +689,13 @@ nla_put_failure: return -1; } -static int find_decode_metaid(struct sk_buff *skb, struct tcf_ife_info *ife, +static int find_decode_metaid(struct sk_buff *skb, struct tcf_ife_params *p, u16 metaid, u16 mlen, void *mdata) { struct tcf_meta_info *e; /* XXX: use hash to speed up */ - list_for_each_entry(e, &ife->metalist, metalist) { + list_for_each_entry_rcu(e, &p->metalist, metalist) { if (metaid == e->metaid) { if (e->ops) { /* We check for decode presence already */ @@ -716,10 +712,13 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, { struct tcf_ife_info *ife = to_ife(a); int action = ife->tcf_action; + struct tcf_ife_params *p; u8 *ifehdr_end; u8 *tlv_data; u16 metalen; + p = rcu_dereference_bh(ife->params); + bstats_update(this_cpu_ptr(ife->common.cpu_bstats), skb); tcf_lastuse_update(&ife->tcf_tm); @@ -745,7 +744,7 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, return TC_ACT_SHOT; } - if (find_decode_metaid(skb, ife, mtype, dlen, curr_data)) { + if (find_decode_metaid(skb, p, mtype, dlen, curr_data)) { /* abuse overlimits to count when we receive metadata * but dont have an ops for it */ @@ -769,12 +768,12 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, /*XXX: check if we can do this at install time instead of current * send data path **/ -static int ife_get_sz(struct sk_buff *skb, struct tcf_ife_info *ife) +static int ife_get_sz(struct sk_buff *skb, struct tcf_ife_params *p) { - struct tcf_meta_info *e, *n; + struct tcf_meta_info *e; int tot_run_sz = 0, run_sz = 0; - list_for_each_entry_safe(e, n, &ife->metalist, metalist) { + list_for_each_entry_rcu(e, &p->metalist, metalist) { if (e->ops->check_presence) { run_sz = e->ops->check_presence(skb, e); tot_run_sz += run_sz; @@ -795,7 +794,7 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, OUTERHDR:TOTMETALEN:{TLVHDR:Metadatum:TLVHDR..}:ORIGDATA where ORIGDATA = original ethernet header ... */ - u16 metalen = ife_get_sz(skb, ife); + u16 metalen = ife_get_sz(skb, p); int hdrm = metalen + skb->dev->hard_header_len + IFE_METAHDRLEN; unsigned int skboff = 0; int new_len = skb->len + hdrm; @@ -833,25 +832,21 @@ drop: if (!ife_meta) goto drop; - spin_lock(&ife->tcf_lock); - /* XXX: we dont have a clever way of telling encode to * not repeat some of the computations that are done by * ops->presence_check... */ - list_for_each_entry(e, &ife->metalist, metalist) { + list_for_each_entry_rcu(e, &p->metalist, metalist) { if (e->ops->encode) { err = e->ops->encode(skb, (void *)(ife_meta + skboff), e); } if (err < 0) { /* too corrupt to keep around if overwritten */ - spin_unlock(&ife->tcf_lock); goto drop; } skboff += err; } - spin_unlock(&ife->tcf_lock); oethh = (struct ethhdr *)skb->data; if (!is_zero_ether_addr(p->eth_src)) diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 343309e9009b..4829c27446e3 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -2228,6 +2228,11 @@ static bool is_qdisc_ingress(__u32 classid) return (TC_H_MIN(classid) == TC_H_MIN(TC_H_MIN_INGRESS)); } +static bool is_ingress_or_clsact(struct tcf_block *block, struct Qdisc *q) +{ + return tcf_block_shared(block) || (q && !!(q->flags & TCQ_F_INGRESS)); +} + static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n, struct netlink_ext_ack *extack) { @@ -2420,6 +2425,8 @@ replay: flags |= TCA_ACT_FLAGS_NO_RTNL; if (is_qdisc_ingress(parent)) flags |= TCA_ACT_FLAGS_AT_INGRESS; + if (is_ingress_or_clsact(block, q)) + flags |= TCA_ACT_FLAGS_AT_INGRESS_OR_CLSACT; err = tp->ops->change(net, skb, tp, cl, t->tcm_handle, tca, &fh, flags, extack); if (err == 0) { diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index a01f14b1c216..9efe23f8371b 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -391,8 +391,8 @@ static const u32 inv_sqrt_cache[REC_INV_SQRT_CACHE] = { 1239850263, 1191209601, 1147878294, 1108955788 }; -static void cake_set_rate(struct cake_tin_data *b, u64 rate, u32 mtu, - u64 target_ns, u64 rtt_est_ns); +static void cake_configure_rates(struct Qdisc *sch, u64 rate, bool rate_adjust); + /* http://en.wikipedia.org/wiki/Methods_of_computing_square_roots * new_invsqrt = (invsqrt / 2) * (3 - count * invsqrt^2) * @@ -2013,7 +2013,8 @@ static struct sk_buff *cake_dequeue(struct Qdisc *sch) u64 delay; u32 len; - if (q->config->is_shared && now - q->last_checked_active >= q->config->sync_time) { + if (q->config->is_shared && q->rate_ns && + now - q->last_checked_active >= q->config->sync_time) { struct net_device *dev = qdisc_dev(sch); struct cake_sched_data *other_priv; u64 new_rate = q->config->rate_bps; @@ -2039,12 +2040,9 @@ static struct sk_buff *cake_dequeue(struct Qdisc *sch) if (num_active_qs > 1) new_rate = div64_u64(q->config->rate_bps, num_active_qs); - /* mtu = 0 is used to only update the rate and not mess with cobalt params */ - cake_set_rate(b, new_rate, 0, 0, 0); + cake_configure_rates(sch, new_rate, true); q->last_checked_active = now; q->active_queues = num_active_qs; - q->rate_ns = b->tin_rate_ns; - q->rate_shft = b->tin_rate_shft; } begin: @@ -2361,12 +2359,10 @@ static void cake_set_rate(struct cake_tin_data *b, u64 rate, u32 mtu, b->cparams.p_dec = 1 << 20; /* 1/4096 */ } -static int cake_config_besteffort(struct Qdisc *sch) +static int cake_config_besteffort(struct Qdisc *sch, u64 rate, u32 mtu) { struct cake_sched_data *q = qdisc_priv(sch); struct cake_tin_data *b = &q->tins[0]; - u32 mtu = psched_mtu(qdisc_dev(sch)); - u64 rate = q->config->rate_bps; q->tin_cnt = 1; @@ -2380,12 +2376,10 @@ static int cake_config_besteffort(struct Qdisc *sch) return 0; } -static int cake_config_precedence(struct Qdisc *sch) +static int cake_config_precedence(struct Qdisc *sch, u64 rate, u32 mtu) { /* convert high-level (user visible) parameters into internal format */ struct cake_sched_data *q = qdisc_priv(sch); - u32 mtu = psched_mtu(qdisc_dev(sch)); - u64 rate = q->config->rate_bps; u32 quantum = 256; u32 i; @@ -2456,7 +2450,7 @@ static int cake_config_precedence(struct Qdisc *sch) * Total 12 traffic classes. */ -static int cake_config_diffserv8(struct Qdisc *sch) +static int cake_config_diffserv8(struct Qdisc *sch, u64 rate, u32 mtu) { /* Pruned list of traffic classes for typical applications: * @@ -2473,8 +2467,6 @@ static int cake_config_diffserv8(struct Qdisc *sch) */ struct cake_sched_data *q = qdisc_priv(sch); - u32 mtu = psched_mtu(qdisc_dev(sch)); - u64 rate = q->config->rate_bps; u32 quantum = 256; u32 i; @@ -2504,7 +2496,7 @@ static int cake_config_diffserv8(struct Qdisc *sch) return 0; } -static int cake_config_diffserv4(struct Qdisc *sch) +static int cake_config_diffserv4(struct Qdisc *sch, u64 rate, u32 mtu) { /* Further pruned list of traffic classes for four-class system: * @@ -2517,8 +2509,6 @@ static int cake_config_diffserv4(struct Qdisc *sch) */ struct cake_sched_data *q = qdisc_priv(sch); - u32 mtu = psched_mtu(qdisc_dev(sch)); - u64 rate = q->config->rate_bps; u32 quantum = 1024; q->tin_cnt = 4; @@ -2546,7 +2536,7 @@ static int cake_config_diffserv4(struct Qdisc *sch) return 0; } -static int cake_config_diffserv3(struct Qdisc *sch) +static int cake_config_diffserv3(struct Qdisc *sch, u64 rate, u32 mtu) { /* Simplified Diffserv structure with 3 tins. * Latency Sensitive (CS7, CS6, EF, VA, TOS4) @@ -2554,8 +2544,6 @@ static int cake_config_diffserv3(struct Qdisc *sch) * Low Priority (LE, CS1) */ struct cake_sched_data *q = qdisc_priv(sch); - u32 mtu = psched_mtu(qdisc_dev(sch)); - u64 rate = q->config->rate_bps; u32 quantum = 1024; q->tin_cnt = 3; @@ -2580,32 +2568,33 @@ static int cake_config_diffserv3(struct Qdisc *sch) return 0; } -static void cake_reconfigure(struct Qdisc *sch) +static void cake_configure_rates(struct Qdisc *sch, u64 rate, bool rate_adjust) { + u32 mtu = likely(rate_adjust) ? 0 : psched_mtu(qdisc_dev(sch)); struct cake_sched_data *qd = qdisc_priv(sch); struct cake_sched_config *q = qd->config; int c, ft; switch (q->tin_mode) { case CAKE_DIFFSERV_BESTEFFORT: - ft = cake_config_besteffort(sch); + ft = cake_config_besteffort(sch, rate, mtu); break; case CAKE_DIFFSERV_PRECEDENCE: - ft = cake_config_precedence(sch); + ft = cake_config_precedence(sch, rate, mtu); break; case CAKE_DIFFSERV_DIFFSERV8: - ft = cake_config_diffserv8(sch); + ft = cake_config_diffserv8(sch, rate, mtu); break; case CAKE_DIFFSERV_DIFFSERV4: - ft = cake_config_diffserv4(sch); + ft = cake_config_diffserv4(sch, rate, mtu); break; case CAKE_DIFFSERV_DIFFSERV3: default: - ft = cake_config_diffserv3(sch); + ft = cake_config_diffserv3(sch, rate, mtu); break; } @@ -2616,6 +2605,14 @@ static void cake_reconfigure(struct Qdisc *sch) qd->rate_ns = qd->tins[ft].tin_rate_ns; qd->rate_shft = qd->tins[ft].tin_rate_shft; +} + +static void cake_reconfigure(struct Qdisc *sch) +{ + struct cake_sched_data *qd = qdisc_priv(sch); + struct cake_sched_config *q = qd->config; + + cake_configure_rates(sch, qd->config->rate_bps, false); if (q->buffer_config_limit) { qd->buffer_limit = q->buffer_config_limit; diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c index 306e046276d4..a4b07b661b77 100644 --- a/net/sched/sch_ets.c +++ b/net/sched/sch_ets.c @@ -115,12 +115,12 @@ static void ets_offload_change(struct Qdisc *sch) struct ets_sched *q = qdisc_priv(sch); struct tc_ets_qopt_offload qopt; unsigned int w_psum_prev = 0; - unsigned int q_psum = 0; - unsigned int q_sum = 0; unsigned int quantum; unsigned int w_psum; unsigned int weight; unsigned int i; + u64 q_psum = 0; + u64 q_sum = 0; if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) return; @@ -138,8 +138,12 @@ static void ets_offload_change(struct Qdisc *sch) for (i = 0; i < q->nbands; i++) { quantum = q->classes[i].quantum; - q_psum += quantum; - w_psum = quantum ? q_psum * 100 / q_sum : 0; + if (quantum) { + q_psum += quantum; + w_psum = div64_u64(q_psum * 100, q_sum); + } else { + w_psum = 0; + } weight = w_psum - w_psum_prev; w_psum_prev = w_psum; diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 80235e85f844..05084c9af48e 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -827,6 +827,7 @@ static void fq_reset(struct Qdisc *sch) for (idx = 0; idx < FQ_BANDS; idx++) { q->band_flows[idx].new_flows.first = NULL; q->band_flows[idx].old_flows.first = NULL; + q->band_pkt_count[idx] = 0; } q->delayed = RB_ROOT; q->flows = 0; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 3756a93dc63a..7eaa5b187fef 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1785,7 +1785,7 @@ restart: __skb_queue_tail(&other->sk_receive_queue, skb); spin_unlock(&other->sk_receive_queue.lock); unix_state_unlock(other); - other->sk_data_ready(other); + READ_ONCE(other->sk_data_ready)(other); sock_put(other); return 0; @@ -2278,7 +2278,7 @@ restart_locked: scm_stat_add(other, skb); skb_queue_tail(&other->sk_receive_queue, skb); unix_state_unlock(other); - other->sk_data_ready(other); + READ_ONCE(other->sk_data_ready)(other); sock_put(other); scm_destroy(&scm); return len; @@ -2351,7 +2351,7 @@ static int queue_oob(struct sock *sk, struct msghdr *msg, struct sock *other, sk_send_sigurg(other); unix_state_unlock(other); - other->sk_data_ready(other); + READ_ONCE(other->sk_data_ready)(other); return 0; out_unlock: @@ -2477,7 +2477,7 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, spin_unlock(&other->sk_receive_queue.lock); unix_state_unlock(other); - other->sk_data_ready(other); + READ_ONCE(other->sk_data_ready)(other); sent += size; } diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 3b46bc635c43..6149f6a79897 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -167,26 +167,32 @@ static int xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len) struct xdp_buff_xsk *pos, *tmp; struct list_head *xskb_list; u32 contd = 0; + u32 num_desc; int err; - if (frags) - contd = XDP_PKT_CONTD; + if (likely(!frags)) { + err = __xsk_rcv_zc(xs, xskb, len, contd); + if (err) + goto err; + return 0; + } - err = __xsk_rcv_zc(xs, xskb, len, contd); - if (err) + contd = XDP_PKT_CONTD; + num_desc = xdp_get_shared_info_from_buff(xdp)->nr_frags + 1; + if (xskq_prod_nb_free(xs->rx, num_desc) < num_desc) { + xs->rx_queue_full++; + err = -ENOBUFS; goto err; - if (likely(!frags)) - return 0; + } + __xsk_rcv_zc(xs, xskb, len, contd); xskb_list = &xskb->pool->xskb_list; list_for_each_entry_safe(pos, tmp, xskb_list, list_node) { if (list_is_singular(xskb_list)) contd = 0; len = pos->xdp.data_end - pos->xdp.data; - err = __xsk_rcv_zc(xs, pos, len, contd); - if (err) - goto err; - list_del(&pos->list_node); + __xsk_rcv_zc(xs, pos, len, contd); + list_del_init(&pos->list_node); } return 0; diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c index fb952703653e..e8ea26464349 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c @@ -610,6 +610,61 @@ out: system("ip link del bond"); } +/* + * Test that changing xmit_hash_policy to vlan+srcmac is rejected when a + * native XDP program is loaded on a bond in 802.3ad or balance-xor mode. + * These modes support XDP only when xmit_hash_policy != vlan+srcmac; freely + * changing the policy creates an inconsistency that triggers a WARNING in + * dev_xdp_uninstall() during device teardown. + */ +static void test_xdp_bonding_xmit_policy_compat(struct skeletons *skeletons) +{ + struct nstoken *nstoken = NULL; + int bond_ifindex = -1; + int xdp_fd, err; + + SYS(out, "ip netns add ns_xmit_policy"); + nstoken = open_netns("ns_xmit_policy"); + if (!ASSERT_OK_PTR(nstoken, "open ns_xmit_policy")) + goto out; + + /* 802.3ad with layer2+3 policy: native XDP is supported */ + SYS(out, "ip link add bond0 type bond mode 802.3ad xmit_hash_policy layer2+3"); + SYS(out, "ip link add veth0 type veth peer name veth0p"); + SYS(out, "ip link set veth0 master bond0"); + SYS(out, "ip link set bond0 up"); + + bond_ifindex = if_nametoindex("bond0"); + if (!ASSERT_GT(bond_ifindex, 0, "bond0 ifindex")) + goto out; + + xdp_fd = bpf_program__fd(skeletons->xdp_dummy->progs.xdp_dummy_prog); + if (!ASSERT_GE(xdp_fd, 0, "xdp_dummy fd")) + goto out; + + err = bpf_xdp_attach(bond_ifindex, xdp_fd, XDP_FLAGS_DRV_MODE, NULL); + if (!ASSERT_OK(err, "attach XDP to bond0")) + goto out; + + /* With XDP loaded, switching to vlan+srcmac must be rejected */ + err = system("ip link set bond0 type bond xmit_hash_policy vlan+srcmac 2>/dev/null"); + ASSERT_NEQ(err, 0, "vlan+srcmac change with XDP loaded should fail"); + + /* Detach XDP first, then the same change must succeed */ + ASSERT_OK(bpf_xdp_detach(bond_ifindex, XDP_FLAGS_DRV_MODE, NULL), + "detach XDP from bond0"); + + bond_ifindex = -1; + err = system("ip link set bond0 type bond xmit_hash_policy vlan+srcmac 2>/dev/null"); + ASSERT_OK(err, "vlan+srcmac change without XDP should succeed"); + +out: + if (bond_ifindex > 0) + bpf_xdp_detach(bond_ifindex, XDP_FLAGS_DRV_MODE, NULL); + close_netns(nstoken); + SYS_NOFAIL("ip netns del ns_xmit_policy"); +} + static int libbpf_debug_print(enum libbpf_print_level level, const char *format, va_list args) { @@ -677,6 +732,9 @@ void serial_test_xdp_bonding(void) test_case->xmit_policy); } + if (test__start_subtest("xdp_bonding_xmit_policy_compat")) + test_xdp_bonding_xmit_policy_compat(&skeletons); + if (test__start_subtest("xdp_bonding_redirect_multi")) test_xdp_bonding_redirect_multi(&skeletons); diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index 16a119a4656c..4afaef01c22e 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -76,6 +76,9 @@ static inline void __kselftest_memset_safe(void *s, int c, size_t n) memset(s, c, n); } +#define KSELFTEST_PRIO_TEST_F 20000 +#define KSELFTEST_PRIO_XFAIL 20001 + #define TEST_TIMEOUT_DEFAULT 30 /* Utilities exposed to the test definitions */ @@ -465,7 +468,7 @@ static inline void __kselftest_memset_safe(void *s, int c, size_t n) fixture_name##_teardown(_metadata, self, variant); \ } \ static struct __test_metadata *_##fixture_name##_##test_name##_object; \ - static void __attribute__((constructor)) \ + static void __attribute__((constructor(KSELFTEST_PRIO_TEST_F))) \ _register_##fixture_name##_##test_name(void) \ { \ struct __test_metadata *object = mmap(NULL, sizeof(*object), \ @@ -880,7 +883,7 @@ struct __test_xfail { .fixture = &_##fixture_name##_fixture_object, \ .variant = &_##fixture_name##_##variant_name##_object, \ }; \ - static void __attribute__((constructor)) \ + static void __attribute__((constructor(KSELFTEST_PRIO_XFAIL))) \ _register_##fixture_name##_##variant_name##_##test_name##_xfail(void) \ { \ _##fixture_name##_##variant_name##_##test_name##_xfail.test = \ diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index afdea6d95bde..605c54c0e8a3 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -15,6 +15,7 @@ TEST_PROGS := \ big_tcp.sh \ bind_bhash.sh \ bpf_offload.py \ + bridge_vlan_dump.sh \ broadcast_ether_dst.sh \ broadcast_pmtu.sh \ busy_poll_test.sh \ diff --git a/tools/testing/selftests/net/bridge_vlan_dump.sh b/tools/testing/selftests/net/bridge_vlan_dump.sh new file mode 100755 index 000000000000..ad66731d2a6f --- /dev/null +++ b/tools/testing/selftests/net/bridge_vlan_dump.sh @@ -0,0 +1,204 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test bridge VLAN range grouping. VLANs are collapsed into a range entry in +# the dump if they have the same per-VLAN options. These tests verify that +# VLANs with different per-VLAN option values are not grouped together. + +# shellcheck disable=SC1091,SC2034,SC2154,SC2317 +source lib.sh + +ALL_TESTS=" + vlan_range_neigh_suppress + vlan_range_mcast_max_groups + vlan_range_mcast_n_groups + vlan_range_mcast_enabled +" + +setup_prepare() +{ + setup_ns NS + defer cleanup_all_ns + + ip -n "$NS" link add name br0 type bridge vlan_filtering 1 \ + vlan_default_pvid 0 mcast_snooping 1 mcast_vlan_snooping 1 + ip -n "$NS" link set dev br0 up + + ip -n "$NS" link add name dummy0 type dummy + ip -n "$NS" link set dev dummy0 master br0 + ip -n "$NS" link set dev dummy0 up +} + +vlan_range_neigh_suppress() +{ + RET=0 + + # Add two new consecutive VLANs for range grouping test + bridge -n "$NS" vlan add vid 10 dev dummy0 + defer bridge -n "$NS" vlan del vid 10 dev dummy0 + + bridge -n "$NS" vlan add vid 11 dev dummy0 + defer bridge -n "$NS" vlan del vid 11 dev dummy0 + + # Configure different neigh_suppress values and verify no range grouping + bridge -n "$NS" vlan set vid 10 dev dummy0 neigh_suppress on + check_err $? "Failed to set neigh_suppress for VLAN 10" + + bridge -n "$NS" vlan set vid 11 dev dummy0 neigh_suppress off + check_err $? "Failed to set neigh_suppress for VLAN 11" + + # Verify VLANs are not shown as a range, but individual entries exist + bridge -n "$NS" -d vlan show dev dummy0 | grep -q "10-11" + check_fail $? "VLANs with different neigh_suppress incorrectly grouped" + + bridge -n "$NS" -d vlan show dev dummy0 | grep -Eq "^\S+\s+10$|^\s+10$" + check_err $? "VLAN 10 individual entry not found" + + bridge -n "$NS" -d vlan show dev dummy0 | grep -Eq "^\S+\s+11$|^\s+11$" + check_err $? "VLAN 11 individual entry not found" + + # Configure same neigh_suppress value and verify range grouping + bridge -n "$NS" vlan set vid 11 dev dummy0 neigh_suppress on + check_err $? "Failed to set neigh_suppress for VLAN 11" + + bridge -n "$NS" -d vlan show dev dummy0 | grep -q "10-11" + check_err $? "VLANs with same neigh_suppress not grouped" + + log_test "VLAN range grouping with neigh_suppress" +} + +vlan_range_mcast_max_groups() +{ + RET=0 + + # Add two new consecutive VLANs for range grouping test + bridge -n "$NS" vlan add vid 10 dev dummy0 + defer bridge -n "$NS" vlan del vid 10 dev dummy0 + + bridge -n "$NS" vlan add vid 11 dev dummy0 + defer bridge -n "$NS" vlan del vid 11 dev dummy0 + + # Configure different mcast_max_groups values and verify no range grouping + bridge -n "$NS" vlan set vid 10 dev dummy0 mcast_max_groups 100 + check_err $? "Failed to set mcast_max_groups for VLAN 10" + + bridge -n "$NS" vlan set vid 11 dev dummy0 mcast_max_groups 200 + check_err $? "Failed to set mcast_max_groups for VLAN 11" + + # Verify VLANs are not shown as a range, but individual entries exist + bridge -n "$NS" -d vlan show dev dummy0 | grep -q "10-11" + check_fail $? "VLANs with different mcast_max_groups incorrectly grouped" + + bridge -n "$NS" -d vlan show dev dummy0 | grep -Eq "^\S+\s+10$|^\s+10$" + check_err $? "VLAN 10 individual entry not found" + + bridge -n "$NS" -d vlan show dev dummy0 | grep -Eq "^\S+\s+11$|^\s+11$" + check_err $? "VLAN 11 individual entry not found" + + # Configure same mcast_max_groups value and verify range grouping + bridge -n "$NS" vlan set vid 11 dev dummy0 mcast_max_groups 100 + check_err $? "Failed to set mcast_max_groups for VLAN 11" + + bridge -n "$NS" -d vlan show dev dummy0 | grep -q "10-11" + check_err $? "VLANs with same mcast_max_groups not grouped" + + log_test "VLAN range grouping with mcast_max_groups" +} + +vlan_range_mcast_n_groups() +{ + RET=0 + + # Add two new consecutive VLANs for range grouping test + bridge -n "$NS" vlan add vid 10 dev dummy0 + defer bridge -n "$NS" vlan del vid 10 dev dummy0 + + bridge -n "$NS" vlan add vid 11 dev dummy0 + defer bridge -n "$NS" vlan del vid 11 dev dummy0 + + # Add different numbers of multicast groups to each VLAN + bridge -n "$NS" mdb add dev br0 port dummy0 grp 239.1.1.1 vid 10 + check_err $? "Failed to add mdb entry to VLAN 10" + defer bridge -n "$NS" mdb del dev br0 port dummy0 grp 239.1.1.1 vid 10 + + bridge -n "$NS" mdb add dev br0 port dummy0 grp 239.1.1.2 vid 10 + check_err $? "Failed to add second mdb entry to VLAN 10" + defer bridge -n "$NS" mdb del dev br0 port dummy0 grp 239.1.1.2 vid 10 + + bridge -n "$NS" mdb add dev br0 port dummy0 grp 239.1.1.1 vid 11 + check_err $? "Failed to add mdb entry to VLAN 11" + defer bridge -n "$NS" mdb del dev br0 port dummy0 grp 239.1.1.1 vid 11 + + # Verify VLANs are not shown as a range due to different mcast_n_groups + bridge -n "$NS" -d vlan show dev dummy0 | grep -q "10-11" + check_fail $? "VLANs with different mcast_n_groups incorrectly grouped" + + bridge -n "$NS" -d vlan show dev dummy0 | grep -Eq "^\S+\s+10$|^\s+10$" + check_err $? "VLAN 10 individual entry not found" + + bridge -n "$NS" -d vlan show dev dummy0 | grep -Eq "^\S+\s+11$|^\s+11$" + check_err $? "VLAN 11 individual entry not found" + + # Add another group to VLAN 11 to match VLAN 10's count + bridge -n "$NS" mdb add dev br0 port dummy0 grp 239.1.1.2 vid 11 + check_err $? "Failed to add second mdb entry to VLAN 11" + defer bridge -n "$NS" mdb del dev br0 port dummy0 grp 239.1.1.2 vid 11 + + bridge -n "$NS" -d vlan show dev dummy0 | grep -q "10-11" + check_err $? "VLANs with same mcast_n_groups not grouped" + + log_test "VLAN range grouping with mcast_n_groups" +} + +vlan_range_mcast_enabled() +{ + RET=0 + + # Add two new consecutive VLANs for range grouping test + bridge -n "$NS" vlan add vid 10 dev br0 self + defer bridge -n "$NS" vlan del vid 10 dev br0 self + + bridge -n "$NS" vlan add vid 11 dev br0 self + defer bridge -n "$NS" vlan del vid 11 dev br0 self + + bridge -n "$NS" vlan add vid 10 dev dummy0 + defer bridge -n "$NS" vlan del vid 10 dev dummy0 + + bridge -n "$NS" vlan add vid 11 dev dummy0 + defer bridge -n "$NS" vlan del vid 11 dev dummy0 + + # Configure different mcast_snooping for bridge VLANs + # Port VLANs inherit BR_VLFLAG_MCAST_ENABLED from bridge VLANs + bridge -n "$NS" vlan global set dev br0 vid 10 mcast_snooping 1 + bridge -n "$NS" vlan global set dev br0 vid 11 mcast_snooping 0 + + # Verify port VLANs are not grouped due to different mcast_enabled + bridge -n "$NS" -d vlan show dev dummy0 | grep -q "10-11" + check_fail $? "VLANs with different mcast_enabled incorrectly grouped" + + bridge -n "$NS" -d vlan show dev dummy0 | grep -Eq "^\S+\s+10$|^\s+10$" + check_err $? "VLAN 10 individual entry not found" + + bridge -n "$NS" -d vlan show dev dummy0 | grep -Eq "^\S+\s+11$|^\s+11$" + check_err $? "VLAN 11 individual entry not found" + + # Configure same mcast_snooping and verify range grouping + bridge -n "$NS" vlan global set dev br0 vid 11 mcast_snooping 1 + + bridge -n "$NS" -d vlan show dev dummy0 | grep -q "10-11" + check_err $? "VLANs with same mcast_enabled not grouped" + + log_test "VLAN range grouping with mcast_enabled" +} + +# Verify the newest tested option is supported +if ! bridge vlan help 2>&1 | grep -q "neigh_suppress"; then + echo "SKIP: iproute2 too old, missing per-VLAN neighbor suppression support" + exit "$ksft_skip" +fi + +trap defer_scopes_cleanup EXIT +setup_prepare +tests_run + +exit "$EXIT_STATUS" diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index 21026b667667..6eb7f95e70e1 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -1672,6 +1672,17 @@ ipv4_withv6_fcnal() run_cmd "$IP ro replace 172.16.101.1/32 via inet6 2001:db8:50::1 dev veth1" log_test $? 2 "IPv4 route with invalid IPv6 gateway" + + # Test IPv4 route with loopback IPv6 nexthop + # Regression test: loopback IPv6 nexthop was misclassified as reject + # route, skipping nhc_pcpu_rth_output allocation, causing panic when + # an IPv4 route references it and triggers __mkroute_output(). + run_cmd "$IP -6 nexthop add id 20 dev lo" + run_cmd "$IP ro add 172.20.20.0/24 nhid 20" + run_cmd "ip netns exec $me ping -c1 -W1 172.20.20.1" + log_test $? 1 "IPv4 route with loopback IPv6 nexthop (no crash)" + run_cmd "$IP ro del 172.20.20.0/24" + run_cmd "$IP nexthop del id 20" } ipv4_fcnal_runtime() diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index dc1f200aaa81..a3144d7298a5 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -104,6 +104,24 @@ CBPF_MPTCP_SUBOPTION_ADD_ADDR="14, 6 0 0 65535, 6 0 0 0" +# IPv4: TCP hdr of 48B, a first suboption of 12B (DACK8), the RM_ADDR suboption +# generated using "nfbpf_compile '(ip[32] & 0xf0) == 0xc0 && ip[53] == 0x0c && +# (ip[66] & 0xf0) == 0x40'" +CBPF_MPTCP_SUBOPTION_RM_ADDR="13, + 48 0 0 0, + 84 0 0 240, + 21 0 9 64, + 48 0 0 32, + 84 0 0 240, + 21 0 6 192, + 48 0 0 53, + 21 0 4 12, + 48 0 0 66, + 84 0 0 240, + 21 0 1 64, + 6 0 0 65535, + 6 0 0 0" + init_partial() { capout=$(mktemp) @@ -2608,6 +2626,19 @@ remove_tests() chk_rst_nr 0 0 fi + # signal+subflow with limits, remove + if reset "remove signal+subflow with limits"; then + pm_nl_set_limits $ns1 0 0 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal,subflow + pm_nl_set_limits $ns2 0 0 + addr_nr_ns1=-1 speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + chk_add_nr 1 1 + chk_rm_nr 1 0 invert + chk_rst_nr 0 0 + fi + # addresses remove if reset "remove addresses"; then pm_nl_set_limits $ns1 3 3 @@ -4217,6 +4248,14 @@ endpoint_tests() chk_subflow_nr "after no reject" 3 chk_mptcp_info subflows 2 subflows 2 + # To make sure RM_ADDR are sent over a different subflow, but + # allow the rest to quickly and cleanly close the subflow + local ipt=1 + ip netns exec "${ns2}" ${iptables} -I OUTPUT -s "10.0.1.2" \ + -p tcp -m tcp --tcp-option 30 \ + -m bpf --bytecode \ + "$CBPF_MPTCP_SUBOPTION_RM_ADDR" \ + -j DROP || ipt=0 local i for i in $(seq 3); do pm_nl_del_endpoint $ns2 1 10.0.1.2 @@ -4229,6 +4268,7 @@ endpoint_tests() chk_subflow_nr "after re-add id 0 ($i)" 3 chk_mptcp_info subflows 3 subflows 3 done + [ ${ipt} = 1 ] && ip netns exec "${ns2}" ${iptables} -D OUTPUT 1 mptcp_lib_kill_group_wait $tests_pid @@ -4288,11 +4328,20 @@ endpoint_tests() chk_mptcp_info subflows 2 subflows 2 chk_mptcp_info add_addr_signal 2 add_addr_accepted 2 + # To make sure RM_ADDR are sent over a different subflow, but + # allow the rest to quickly and cleanly close the subflow + local ipt=1 + ip netns exec "${ns1}" ${iptables} -I OUTPUT -s "10.0.1.1" \ + -p tcp -m tcp --tcp-option 30 \ + -m bpf --bytecode \ + "$CBPF_MPTCP_SUBOPTION_RM_ADDR" \ + -j DROP || ipt=0 pm_nl_del_endpoint $ns1 42 10.0.1.1 sleep 0.5 chk_subflow_nr "after delete ID 0" 2 chk_mptcp_info subflows 2 subflows 2 chk_mptcp_info add_addr_signal 2 add_addr_accepted 2 + [ ${ipt} = 1 ] && ip netns exec "${ns1}" ${iptables} -D OUTPUT 1 pm_nl_add_endpoint $ns1 10.0.1.1 id 99 flags signal wait_mpj 4 diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh index 806aaa7d2d61..d11a8b949aab 100755 --- a/tools/testing/selftests/net/mptcp/simult_flows.sh +++ b/tools/testing/selftests/net/mptcp/simult_flows.sh @@ -237,10 +237,13 @@ run_test() for dev in ns2eth1 ns2eth2; do tc -n $ns2 qdisc del dev $dev root >/dev/null 2>&1 done - tc -n $ns1 qdisc add dev ns1eth1 root netem rate ${rate1}mbit $delay1 - tc -n $ns1 qdisc add dev ns1eth2 root netem rate ${rate2}mbit $delay2 - tc -n $ns2 qdisc add dev ns2eth1 root netem rate ${rate1}mbit $delay1 - tc -n $ns2 qdisc add dev ns2eth2 root netem rate ${rate2}mbit $delay2 + + # keep the queued pkts number low, or the RTT estimator will see + # increasing latency over time. + tc -n $ns1 qdisc add dev ns1eth1 root netem rate ${rate1}mbit $delay1 limit 50 + tc -n $ns1 qdisc add dev ns1eth2 root netem rate ${rate2}mbit $delay2 limit 50 + tc -n $ns2 qdisc add dev ns2eth1 root netem rate ${rate1}mbit $delay1 limit 50 + tc -n $ns2 qdisc add dev ns2eth2 root netem rate ${rate2}mbit $delay2 limit 50 # time is measured in ms, account for transfer size, aggregated link speed # and header overhead (10%) diff --git a/tools/testing/selftests/net/netfilter/nf_queue.c b/tools/testing/selftests/net/netfilter/nf_queue.c index 9e56b9d47037..116c0ca0eabb 100644 --- a/tools/testing/selftests/net/netfilter/nf_queue.c +++ b/tools/testing/selftests/net/netfilter/nf_queue.c @@ -18,6 +18,7 @@ struct options { bool count_packets; bool gso_enabled; + bool failopen; int verbose; unsigned int queue_num; unsigned int timeout; @@ -30,7 +31,7 @@ static struct options opts; static void help(const char *p) { - printf("Usage: %s [-c|-v [-vv] ] [-t timeout] [-q queue_num] [-Qdst_queue ] [ -d ms_delay ] [-G]\n", p); + printf("Usage: %s [-c|-v [-vv] ] [-o] [-t timeout] [-q queue_num] [-Qdst_queue ] [ -d ms_delay ] [-G]\n", p); } static int parse_attr_cb(const struct nlattr *attr, void *data) @@ -236,6 +237,8 @@ struct mnl_socket *open_queue(void) flags = opts.gso_enabled ? NFQA_CFG_F_GSO : 0; flags |= NFQA_CFG_F_UID_GID; + if (opts.failopen) + flags |= NFQA_CFG_F_FAIL_OPEN; mnl_attr_put_u32(nlh, NFQA_CFG_FLAGS, htonl(flags)); mnl_attr_put_u32(nlh, NFQA_CFG_MASK, htonl(flags)); @@ -329,7 +332,7 @@ static void parse_opts(int argc, char **argv) { int c; - while ((c = getopt(argc, argv, "chvt:q:Q:d:G")) != -1) { + while ((c = getopt(argc, argv, "chvot:q:Q:d:G")) != -1) { switch (c) { case 'c': opts.count_packets = true; @@ -366,6 +369,9 @@ static void parse_opts(int argc, char **argv) case 'G': opts.gso_enabled = false; break; + case 'o': + opts.failopen = true; + break; case 'v': opts.verbose++; break; diff --git a/tools/testing/selftests/net/netfilter/nft_queue.sh b/tools/testing/selftests/net/netfilter/nft_queue.sh index 139bc1211878..ea766bdc5d04 100755 --- a/tools/testing/selftests/net/netfilter/nft_queue.sh +++ b/tools/testing/selftests/net/netfilter/nft_queue.sh @@ -591,6 +591,7 @@ EOF test_udp_gro_ct() { local errprefix="FAIL: test_udp_gro_ct:" + local timeout=5 ip netns exec "$nsrouter" conntrack -F 2>/dev/null @@ -630,10 +631,10 @@ table inet udpq { } } EOF - timeout 10 ip netns exec "$ns2" socat UDP-LISTEN:12346,fork,pf=ipv4 OPEN:"$TMPFILE1",trunc & + timeout "$timeout" ip netns exec "$ns2" socat UDP-LISTEN:12346,fork,pf=ipv4 OPEN:"$TMPFILE1",trunc & local rpid=$! - ip netns exec "$nsrouter" ./nf_queue -G -c -q 1 -t 2 > "$TMPFILE2" & + ip netns exec "$nsrouter" nice -n -19 ./nf_queue -G -c -q 1 -o -t 2 > "$TMPFILE2" & local nfqpid=$! ip netns exec "$nsrouter" ethtool -K "veth0" rx-udp-gro-forwarding on rx-gro-list on generic-receive-offload on @@ -643,8 +644,12 @@ EOF local bs=512 local count=$(((32 * 1024 * 1024) / bs)) - dd if=/dev/zero bs="$bs" count="$count" 2>/dev/null | for i in $(seq 1 16); do - timeout 5 ip netns exec "$ns1" \ + + local nprocs=$(nproc) + [ $nprocs -gt 1 ] && nprocs=$((nprocs - 1)) + + dd if=/dev/zero bs="$bs" count="$count" 2>/dev/null | for i in $(seq 1 $nprocs); do + timeout "$timeout" nice -n 19 ip netns exec "$ns1" \ socat -u -b 512 STDIN UDP-DATAGRAM:10.0.2.99:12346,reuseport,bind=0.0.0.0:55221 & done diff --git a/tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt b/tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt index 3848b419e68c..6c0f32c40f19 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt @@ -38,7 +38,7 @@ // If queue is empty, accept a packet even if its end_seq is above wup + rcv_wnd +0 < P. 4001:54001(50000) ack 1 win 257 - +0 > . 1:1(0) ack 54001 win 0 + * > . 1:1(0) ack 54001 win 0 // Check LINUX_MIB_BEYOND_WINDOW has been incremented 3 times. +0 `nstat | grep TcpExtBeyondWindow | grep -q " 3 "` diff --git a/tools/testing/selftests/net/packetdrill/tcp_rcv_toobig.pkt b/tools/testing/selftests/net/packetdrill/tcp_rcv_toobig.pkt deleted file mode 100644 index f575c0ff89da..000000000000 --- a/tools/testing/selftests/net/packetdrill/tcp_rcv_toobig.pkt +++ /dev/null @@ -1,33 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 - ---mss=1000 - -`./defaults.sh` - - 0 `nstat -n` - -// Establish a connection. - +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 - +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 - +0 setsockopt(3, SOL_SOCKET, SO_RCVBUF, [20000], 4) = 0 - +0 bind(3, ..., ...) = 0 - +0 listen(3, 1) = 0 - - +0 < S 0:0(0) win 32792 <mss 1000,nop,wscale 7> - +0 > S. 0:0(0) ack 1 win 18980 <mss 1460,nop,wscale 0> - +.1 < . 1:1(0) ack 1 win 257 - - +0 accept(3, ..., ...) = 4 - - +0 < P. 1:20001(20000) ack 1 win 257 - +.04 > . 1:1(0) ack 20001 win 18000 - - +0 setsockopt(4, SOL_SOCKET, SO_RCVBUF, [12000], 4) = 0 - +0 < P. 20001:80001(60000) ack 1 win 257 - +0 > . 1:1(0) ack 20001 win 18000 - - +0 read(4, ..., 20000) = 20000 -// A too big packet is accepted if the receive queue is empty - +0 < P. 20001:80001(60000) ack 1 win 257 - +0 > . 1:1(0) ack 80001 win 0 - diff --git a/tools/testing/selftests/net/tun.c b/tools/testing/selftests/net/tun.c index 8a5cd5cb5472..cf106a49b55e 100644 --- a/tools/testing/selftests/net/tun.c +++ b/tools/testing/selftests/net/tun.c @@ -944,8 +944,8 @@ TEST_F(tun_vnet_udptnl, send_gso_packet) ASSERT_EQ(ret, off); ret = receive_gso_packet_from_tunnel(self, variant, &r_num_mss); - ASSERT_EQ(ret, variant->data_size); - ASSERT_EQ(r_num_mss, variant->r_num_mss); + EXPECT_EQ(ret, variant->data_size); + EXPECT_EQ(r_num_mss, variant->r_num_mss); } TEST_F(tun_vnet_udptnl, recv_gso_packet) @@ -955,18 +955,18 @@ TEST_F(tun_vnet_udptnl, recv_gso_packet) int ret, gso_type = VIRTIO_NET_HDR_GSO_UDP_L4; ret = send_gso_packet_into_tunnel(self, variant); - ASSERT_EQ(ret, variant->data_size); + EXPECT_EQ(ret, variant->data_size); memset(&vnet_hdr, 0, sizeof(vnet_hdr)); ret = receive_gso_packet_from_tun(self, variant, &vnet_hdr); - ASSERT_EQ(ret, variant->data_size); + EXPECT_EQ(ret, variant->data_size); if (!variant->no_gso) { - ASSERT_EQ(vh->gso_size, variant->gso_size); + EXPECT_EQ(vh->gso_size, variant->gso_size); gso_type |= (variant->tunnel_type & UDP_TUNNEL_OUTER_IPV4) ? (VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV4) : (VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV6); - ASSERT_EQ(vh->gso_type, gso_type); + EXPECT_EQ(vh->gso_type, gso_type); } } diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/ct.json b/tools/testing/selftests/tc-testing/tc-tests/actions/ct.json index 7d07c55bb668..33bb8f3ff8ed 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/ct.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/ct.json @@ -505,5 +505,164 @@ "teardown": [ "$TC qdisc del dev $DEV1 ingress" ] + }, + { + "id": "8883", + "name": "Try to attach act_ct to an ets qdisc", + "category": [ + "actions", + "ct" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + [ + "$TC actions flush action ct", + 0, + 1, + 255 + ], + "$TC qdisc add dev $DEV1 root handle 1: ets bands 2" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent 1: prio 1 protocol ip matchall action ct index 42", + "expExitCode": "2", + "verifyCmd": "$TC -j filter ls dev $DEV1 parent 1: prio 1 protocol ip", + "matchJSON": [], + "teardown": [ + "$TC qdisc del dev $DEV1 root" + ] + }, + { + "id": "3b10", + "name": "Attach act_ct to an ingress qdisc", + "category": [ + "actions", + "ct" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + [ + "$TC actions flush action ct", + 0, + 1, + 255 + ], + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 ingress prio 1 protocol ip matchall action ct index 42", + "expExitCode": "0", + "verifyCmd": "$TC -j filter ls dev $DEV1 ingress prio 1 protocol ip", + "matchJSON": [ + { + "kind": "matchall" + }, + { + "options": { + "actions": [ + { + "order": 1, + "kind": "ct", + "index": 42, + "ref": 1, + "bind": 1 + } + ] + } + } + ], + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "0337", + "name": "Attach act_ct to a clsact/egress qdisc", + "category": [ + "actions", + "ct" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + [ + "$TC actions flush action ct", + 0, + 1, + 255 + ], + "$TC qdisc add dev $DEV1 clsact" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 egress prio 1 protocol ip matchall action ct index 42", + "expExitCode": "0", + "verifyCmd": "$TC -j filter ls dev $DEV1 egress prio 1 protocol ip", + "matchJSON": [ + { + "kind": "matchall" + }, + { + "options": { + "actions": [ + { + "order": 1, + "kind": "ct", + "index": 42, + "ref": 1, + "bind": 1 + } + ] + } + } + ], + "teardown": [ + "$TC qdisc del dev $DEV1 clsact" + ] + }, + { + "id": "4f60", + "name": "Attach act_ct to a shared block", + "category": [ + "actions", + "ct" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + [ + "$TC actions flush action ct", + 0, + 1, + 255 + ], + "$TC qdisc add dev $DEV1 ingress_block 21 clsact" + ], + "cmdUnderTest": "$TC filter add block 21 prio 1 protocol ip matchall action ct index 42", + "expExitCode": "0", + "verifyCmd": "$TC -j filter ls block 21 prio 1 protocol ip", + "matchJSON": [ + { + "kind": "matchall" + }, + { + "options": { + "actions": [ + { + "order": 1, + "kind": "ct", + "index": 42, + "ref": 1, + "bind": 1 + } + ] + } + } + ], + "teardown": [ + "$TC qdisc del dev $DEV1 ingress_block 21 clsact" + ] } ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json b/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json index f587a32e44c4..808aef4afe22 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json @@ -1279,5 +1279,104 @@ "teardown": [ "$TC actions flush action ife" ] + }, + { + "id": "f2a0", + "name": "Update decode ife action with encode metadata", + "category": [ + "actions", + "ife" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ], + "$TC actions add action ife decode index 10" + ], + "cmdUnderTest": "$TC actions replace action ife encode use tcindex 1 index 10", + "expExitCode": "0", + "verifyCmd": "$TC -j actions get action ife index 10", + "matchJSON": [ + { + "total acts": 0 + }, + { + "actions": [ + { + "order": 1, + "kind": "ife", + "mode": "encode", + "control_action": { + "type": "pipe" + }, + "type": "0xed3e", + "tcindex": 1, + "index": 10, + "ref": 1, + "bind": 0, + "not_in_hw": true + } + ] + } + ], + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "d352", + "name": "Update decode ife action into encode with multiple metadata", + "category": [ + "actions", + "ife" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ], + "$TC actions add action ife decode index 10" + ], + "cmdUnderTest": "$TC actions replace action ife encode use tcindex 1 use mark 22 index 10", + "expExitCode": "0", + "verifyCmd": "$TC -j actions get action ife index 10", + "matchJSON": [ + { + "total acts": 0 + }, + { + "actions": [ + { + "order": 1, + "kind": "ife", + "mode": "encode", + "control_action": { + "type": "pipe" + }, + "type": "0xed3e", + "tcindex": 1, + "mark": 22, + "index": 10, + "ref": 1, + "bind": 0, + "not_in_hw": true + } + ] + } + ], + "teardown": [ + "$TC actions flush action ife" + ] } ] diff --git a/tools/testing/selftests/tc-testing/tdc_helper.py b/tools/testing/selftests/tc-testing/tdc_helper.py index 0440d252c4c5..bc447ca57333 100644 --- a/tools/testing/selftests/tc-testing/tdc_helper.py +++ b/tools/testing/selftests/tc-testing/tdc_helper.py @@ -38,10 +38,14 @@ def list_test_cases(testlist): def list_categories(testlist): - """ Show all categories that are present in a test case file. """ - categories = set(map(lambda x: x['category'], testlist)) + """Show all unique categories present in the test cases.""" + categories = set() + for t in testlist: + if 'category' in t: + categories.update(t['category']) + print("Available categories:") - print(", ".join(str(s) for s in categories)) + print(", ".join(sorted(categories))) print("") |