diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2025-04-04 09:15:35 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2025-04-04 09:15:35 -0700 |
| commit | 61f96e684edd28ca40555ec49ea1555df31ba619 (patch) | |
| tree | 5042c3c391a8bcb6fc5bab65253adcd23d30a366 | |
| parent | 96364527357980ea68bb8bc7ec1490e22b9ed0cd (diff) | |
| parent | 94f68c0f99a548d33a102672690100bf76a7c460 (diff) | |
Merge tag 'net-6.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Jakub Kicinski:
"Including fixes from netfilter.
Current release - regressions:
- four fixes for the netdev per-instance locking
Current release - new code bugs:
- consolidate more code between existing Rx zero-copy and uring so
that the latter doesn't miss / have to duplicate the safety checks
Previous releases - regressions:
- ipv6: fix omitted Netlink attributes when using SKIP_STATS
Previous releases - always broken:
- net: fix geneve_opt length integer overflow
- udp: fix multiple wrap arounds of sk->sk_rmem_alloc when it
approaches INT_MAX
- dsa: mvpp2: add a lock to avoid corruption of the shared TCAM
- dsa: airoha: fix issues with traffic QoS configuration / offload,
and flow table offload
Misc:
- touch up the Netlink YAML specs of old families to make them usable
for user space C codegen"
* tag 'net-6.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (56 commits)
selftests: net: amt: indicate progress in the stress test
netlink: specs: rt_route: pull the ifa- prefix out of the names
netlink: specs: rt_addr: pull the ifa- prefix out of the names
netlink: specs: rt_addr: fix get multi command name
netlink: specs: rt_addr: fix the spec format / schema failures
net: avoid false positive warnings in __net_mp_close_rxq()
net: move mp dev config validation to __net_mp_open_rxq()
net: ibmveth: make veth_pool_store stop hanging
arcnet: Add NULL check in com20020pci_probe()
ipv6: Do not consider link down nexthops in path selection
ipv6: Start path selection from the first nexthop
usbnet:fix NPE during rx_complete
net: octeontx2: Handle XDP_ABORTED and XDP invalid as XDP_DROP
net: fix geneve_opt length integer overflow
io_uring/zcrx: fix selftests w/ updated netdev Python helpers
selftests: net: use netdevsim in netns test
docs: net: document netdev notifier expectations
net: dummy: request ops lock
netdevsim: add dummy device notifiers
net: rename rtnl_net_debug to lock_debug
...
69 files changed, 864 insertions, 442 deletions
@@ -3670,6 +3670,10 @@ S: 149 Union St. S: Kingston, Ontario S: Canada K7L 2P4 +N: Pravin B Shelar +E: pshelar@ovn.org +D: Open vSwitch maintenance and contributions + N: John Shifflett E: john@geolog.com E: jshiffle@netcom.com diff --git a/Documentation/netlink/specs/rt_addr.yaml b/Documentation/netlink/specs/rt_addr.yaml index 5dd5469044c7..df6b23f06a22 100644 --- a/Documentation/netlink/specs/rt_addr.yaml +++ b/Documentation/netlink/specs/rt_addr.yaml @@ -78,45 +78,46 @@ definitions: attribute-sets: - name: addr-attrs + name-prefix: ifa- attributes: - - name: ifa-address + name: address type: binary display-hint: ipv4 - - name: ifa-local + name: local type: binary display-hint: ipv4 - - name: ifa-label + name: label type: string - - name: ifa-broadcast + name: broadcast type: binary display-hint: ipv4 - - name: ifa-anycast + name: anycast type: binary - - name: ifa-cacheinfo + name: cacheinfo type: binary struct: ifa-cacheinfo - - name: ifa-multicast + name: multicast type: binary - - name: ifa-flags + name: flags type: u32 enum: ifa-flags enum-as-flags: true - - name: ifa-rt-priority + name: rt-priority type: u32 - - name: ifa-target-netnsid + name: target-netnsid type: binary - - name: ifa-proto + name: proto type: u8 @@ -137,10 +138,10 @@ operations: - ifa-prefixlen - ifa-scope - ifa-index - - ifa-address - - ifa-label - - ifa-local - - ifa-cacheinfo + - address + - label + - local + - cacheinfo - name: deladdr doc: Remove address @@ -154,8 +155,8 @@ operations: - ifa-prefixlen - ifa-scope - ifa-index - - ifa-address - - ifa-local + - address + - local - name: getaddr doc: Dump address information. @@ -169,7 +170,7 @@ operations: value: 20 attributes: *ifaddr-all - - name: getmaddrs + name: getmulticast doc: Get / dump IPv4/IPv6 multicast addresses. attribute-set: addr-attrs fixed-header: ifaddrmsg @@ -182,11 +183,12 @@ operations: reply: value: 58 attributes: &mcaddr-attrs - - ifa-multicast - - ifa-cacheinfo + - multicast + - cacheinfo dump: request: value: 58 + attributes: - ifa-family reply: value: 58 diff --git a/Documentation/netlink/specs/rt_route.yaml b/Documentation/netlink/specs/rt_route.yaml index a674103e5bc4..292469c7d4b9 100644 --- a/Documentation/netlink/specs/rt_route.yaml +++ b/Documentation/netlink/specs/rt_route.yaml @@ -80,165 +80,167 @@ definitions: attribute-sets: - name: route-attrs + name-prefix: rta- attributes: - - name: rta-dst + name: dst type: binary display-hint: ipv4 - - name: rta-src + name: src type: binary display-hint: ipv4 - - name: rta-iif + name: iif type: u32 - - name: rta-oif + name: oif type: u32 - - name: rta-gateway + name: gateway type: binary display-hint: ipv4 - - name: rta-priority + name: priority type: u32 - - name: rta-prefsrc + name: prefsrc type: binary display-hint: ipv4 - - name: rta-metrics + name: metrics type: nest - nested-attributes: rta-metrics + nested-attributes: metrics - - name: rta-multipath + name: multipath type: binary - - name: rta-protoinfo # not used + name: protoinfo # not used type: binary - - name: rta-flow + name: flow type: u32 - - name: rta-cacheinfo + name: cacheinfo type: binary struct: rta-cacheinfo - - name: rta-session # not used + name: session # not used type: binary - - name: rta-mp-algo # not used + name: mp-algo # not used type: binary - - name: rta-table + name: table type: u32 - - name: rta-mark + name: mark type: u32 - - name: rta-mfc-stats + name: mfc-stats type: binary - - name: rta-via + name: via type: binary - - name: rta-newdst + name: newdst type: binary - - name: rta-pref + name: pref type: u8 - - name: rta-encap-type + name: encap-type type: u16 - - name: rta-encap + name: encap type: binary # tunnel specific nest - - name: rta-expires + name: expires type: u32 - - name: rta-pad + name: pad type: binary - - name: rta-uid + name: uid type: u32 - - name: rta-ttl-propagate + name: ttl-propagate type: u8 - - name: rta-ip-proto + name: ip-proto type: u8 - - name: rta-sport + name: sport type: u16 - - name: rta-dport + name: dport type: u16 - - name: rta-nh-id + name: nh-id type: u32 - - name: rta-flowlabel + name: flowlabel type: u32 byte-order: big-endian display-hint: hex - - name: rta-metrics + name: metrics + name-prefix: rtax- attributes: - - name: rtax-unspec + name: unspec type: unused value: 0 - - name: rtax-lock + name: lock type: u32 - - name: rtax-mtu + name: mtu type: u32 - - name: rtax-window + name: window type: u32 - - name: rtax-rtt + name: rtt type: u32 - - name: rtax-rttvar + name: rttvar type: u32 - - name: rtax-ssthresh + name: ssthresh type: u32 - - name: rtax-cwnd + name: cwnd type: u32 - - name: rtax-advmss + name: advmss type: u32 - - name: rtax-reordering + name: reordering type: u32 - - name: rtax-hoplimit + name: hoplimit type: u32 - - name: rtax-initcwnd + name: initcwnd type: u32 - - name: rtax-features + name: features type: u32 - - name: rtax-rto-min + name: rto-min type: u32 - - name: rtax-initrwnd + name: initrwnd type: u32 - - name: rtax-quickack + name: quickack type: u32 - - name: rtax-cc-algo + name: cc-algo type: string - - name: rtax-fastopen-no-cookie + name: fastopen-no-cookie type: u32 operations: @@ -254,18 +256,18 @@ operations: value: 26 attributes: - rtm-family - - rta-src + - src - rtm-src-len - - rta-dst + - dst - rtm-dst-len - - rta-iif - - rta-oif - - rta-ip-proto - - rta-sport - - rta-dport - - rta-mark - - rta-uid - - rta-flowlabel + - iif + - oif + - ip-proto + - sport + - dport + - mark + - uid + - flowlabel reply: value: 24 attributes: &all-route-attrs @@ -278,34 +280,34 @@ operations: - rtm-scope - rtm-type - rtm-flags - - rta-dst - - rta-src - - rta-iif - - rta-oif - - rta-gateway - - rta-priority - - rta-prefsrc - - rta-metrics - - rta-multipath - - rta-flow - - rta-cacheinfo - - rta-table - - rta-mark - - rta-mfc-stats - - rta-via - - rta-newdst - - rta-pref - - rta-encap-type - - rta-encap - - rta-expires - - rta-pad - - rta-uid - - rta-ttl-propagate - - rta-ip-proto - - rta-sport - - rta-dport - - rta-nh-id - - rta-flowlabel + - dst + - src + - iif + - oif + - gateway + - priority + - prefsrc + - metrics + - multipath + - flow + - cacheinfo + - table + - mark + - mfc-stats + - via + - newdst + - pref + - encap-type + - encap + - expires + - pad + - uid + - ttl-propagate + - ip-proto + - sport + - dport + - nh-id + - flowlabel dump: request: value: 26 diff --git a/Documentation/networking/netdevices.rst b/Documentation/networking/netdevices.rst index ebb868f50ac2..6c2d8945f597 100644 --- a/Documentation/networking/netdevices.rst +++ b/Documentation/networking/netdevices.rst @@ -343,6 +343,29 @@ there are two sets of interfaces: ``dev_xxx`` and ``netif_xxx`` (e.g., acquiring the instance lock themselves, while the ``netif_xxx`` functions assume that the driver has already acquired the instance lock. +Notifiers and netdev instance lock +================================== + +For device drivers that implement shaping or queue management APIs, +some of the notifiers (``enum netdev_cmd``) are running under the netdev +instance lock. + +For devices with locked ops, currently only the following notifiers are +running under the lock: +* ``NETDEV_REGISTER`` +* ``NETDEV_UP`` + +The following notifiers are running without the lock: +* ``NETDEV_UNREGISTER`` + +There are no clear expectations for the remaining notifiers. Notifiers not on +the list may run with or without the instance lock, potentially even invoking +the same notifier type with and without the lock from different code paths. +The goal is to eventually ensure that all (or most, with a few documented +exceptions) notifiers run under the instance lock. Please extend this +documentation whenever you make explicit assumption about lock being held +from a notifier. + NETDEV_INTERNAL symbol namespace ================================ diff --git a/MAINTAINERS b/MAINTAINERS index a9dbf29f0f3b..4c5c2e2c1278 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -18131,7 +18131,9 @@ F: drivers/irqchip/irq-ompic.c F: drivers/irqchip/irq-or1k-* OPENVSWITCH -M: Pravin B Shelar <pshelar@ovn.org> +M: Aaron Conole <aconole@redhat.com> +M: Eelco Chaudron <echaudro@redhat.com> +M: Ilya Maximets <i.maximets@ovn.org> L: netdev@vger.kernel.org L: dev@openvswitch.org S: Maintained @@ -19903,7 +19905,7 @@ F: Documentation/devicetree/bindings/i2c/qcom,i2c-geni-qcom.yaml F: drivers/i2c/busses/i2c-qcom-geni.c QUALCOMM I2C CCI DRIVER -M: Loic Poulain <loic.poulain@linaro.org> +M: Loic Poulain <loic.poulain@oss.qualcomm.com> M: Robert Foss <rfoss@kernel.org> L: linux-i2c@vger.kernel.org L: linux-arm-msm@vger.kernel.org @@ -20036,7 +20038,7 @@ F: Documentation/devicetree/bindings/media/*venus* F: drivers/media/platform/qcom/venus/ QUALCOMM WCN36XX WIRELESS DRIVER -M: Loic Poulain <loic.poulain@linaro.org> +M: Loic Poulain <loic.poulain@oss.qualcomm.com> L: wcn36xx@lists.infradead.org S: Supported W: https://wireless.wiki.kernel.org/en/users/Drivers/wcn36xx @@ -26075,7 +26077,7 @@ F: kernel/workqueue.c F: kernel/workqueue_internal.h WWAN DRIVERS -M: Loic Poulain <loic.poulain@linaro.org> +M: Loic Poulain <loic.poulain@oss.qualcomm.com> M: Sergey Ryazanov <ryazanov.s.a@gmail.com> R: Johannes Berg <johannes@sipsolutions.net> L: netdev@vger.kernel.org diff --git a/drivers/net/arcnet/com20020-pci.c b/drivers/net/arcnet/com20020-pci.c index c5e571ec94c9..0472bcdff130 100644 --- a/drivers/net/arcnet/com20020-pci.c +++ b/drivers/net/arcnet/com20020-pci.c @@ -251,18 +251,33 @@ static int com20020pci_probe(struct pci_dev *pdev, card->tx_led.default_trigger = devm_kasprintf(&pdev->dev, GFP_KERNEL, "arc%d-%d-tx", dev->dev_id, i); + if (!card->tx_led.default_trigger) { + ret = -ENOMEM; + goto err_free_arcdev; + } card->tx_led.name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "pci:green:tx:%d-%d", dev->dev_id, i); - + if (!card->tx_led.name) { + ret = -ENOMEM; + goto err_free_arcdev; + } card->tx_led.dev = &dev->dev; card->recon_led.brightness_set = led_recon_set; card->recon_led.default_trigger = devm_kasprintf(&pdev->dev, GFP_KERNEL, "arc%d-%d-recon", dev->dev_id, i); + if (!card->recon_led.default_trigger) { + ret = -ENOMEM; + goto err_free_arcdev; + } card->recon_led.name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "pci:red:recon:%d-%d", dev->dev_id, i); + if (!card->recon_led.name) { + ret = -ENOMEM; + goto err_free_arcdev; + } card->recon_led.dev = &dev->dev; ret = devm_led_classdev_register(&pdev->dev, &card->tx_led); diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 901929f96b38..29a89ab4b789 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -7350,13 +7350,13 @@ static int mv88e6xxx_probe(struct mdio_device *mdiodev) err = mv88e6xxx_switch_reset(chip); mv88e6xxx_reg_unlock(chip); if (err) - goto out; + goto out_phy; if (np) { chip->irq = of_irq_get(np, 0); if (chip->irq == -EPROBE_DEFER) { err = chip->irq; - goto out; + goto out_phy; } } @@ -7375,7 +7375,7 @@ static int mv88e6xxx_probe(struct mdio_device *mdiodev) mv88e6xxx_reg_unlock(chip); if (err) - goto out; + goto out_phy; if (chip->info->g2_irqs > 0) { err = mv88e6xxx_g2_irq_setup(chip); @@ -7409,6 +7409,8 @@ out_g1_irq: mv88e6xxx_g1_irq_free(chip); else mv88e6xxx_irq_poll_free(chip); +out_phy: + mv88e6xxx_phy_destroy(chip); out: if (pdata) dev_put(pdata->netdev); @@ -7431,7 +7433,6 @@ static void mv88e6xxx_remove(struct mdio_device *mdiodev) mv88e6xxx_ptp_free(chip); } - mv88e6xxx_phy_destroy(chip); mv88e6xxx_unregister_switch(chip); mv88e6xxx_g1_vtu_prob_irq_free(chip); @@ -7444,6 +7445,8 @@ static void mv88e6xxx_remove(struct mdio_device *mdiodev) mv88e6xxx_g1_irq_free(chip); else mv88e6xxx_irq_poll_free(chip); + + mv88e6xxx_phy_destroy(chip); } static void mv88e6xxx_shutdown(struct mdio_device *mdiodev) diff --git a/drivers/net/dsa/mv88e6xxx/phy.c b/drivers/net/dsa/mv88e6xxx/phy.c index 8bb88b3d900d..ee9e5d7e5277 100644 --- a/drivers/net/dsa/mv88e6xxx/phy.c +++ b/drivers/net/dsa/mv88e6xxx/phy.c @@ -229,7 +229,10 @@ static void mv88e6xxx_phy_ppu_state_init(struct mv88e6xxx_chip *chip) static void mv88e6xxx_phy_ppu_state_destroy(struct mv88e6xxx_chip *chip) { + mutex_lock(&chip->ppu_mutex); del_timer_sync(&chip->ppu_timer); + cancel_work_sync(&chip->ppu_work); + mutex_unlock(&chip->ppu_mutex); } int mv88e6185_phy_ppu_read(struct mv88e6xxx_chip *chip, struct mii_bus *bus, diff --git a/drivers/net/dummy.c b/drivers/net/dummy.c index a4938c6a5ebb..d6bdad4baadd 100644 --- a/drivers/net/dummy.c +++ b/drivers/net/dummy.c @@ -105,6 +105,7 @@ static void dummy_setup(struct net_device *dev) dev->netdev_ops = &dummy_netdev_ops; dev->ethtool_ops = &dummy_ethtool_ops; dev->needs_free_netdev = true; + dev->request_ops_lock = true; /* Fill in device structure with ethernet-generic values. */ dev->flags |= IFF_NOARP; diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c index c0a642568ac1..d748dc6de923 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.c +++ b/drivers/net/ethernet/airoha/airoha_eth.c @@ -2028,7 +2028,7 @@ static int airoha_qdma_set_tx_ets_sched(struct airoha_gdm_port *port, struct tc_ets_qopt_offload_replace_params *p = &opt->replace_params; enum tx_sched_mode mode = TC_SCH_SP; u16 w[AIROHA_NUM_QOS_QUEUES] = {}; - int i, nstrict = 0, nwrr, qidx; + int i, nstrict = 0; if (p->bands > AIROHA_NUM_QOS_QUEUES) return -EINVAL; @@ -2046,17 +2046,17 @@ static int airoha_qdma_set_tx_ets_sched(struct airoha_gdm_port *port, * lowest priorities with respect to SP ones. * e.g: WRR0, WRR1, .., WRRm, SP0, SP1, .., SPn */ - nwrr = p->bands - nstrict; - qidx = nstrict && nwrr ? nstrict : 0; - for (i = 1; i <= p->bands; i++) { - if (p->priomap[i % AIROHA_NUM_QOS_QUEUES] != qidx) + for (i = 0; i < nstrict; i++) { + if (p->priomap[p->bands - i - 1] != i) return -EINVAL; - - qidx = i == nwrr ? 0 : qidx + 1; } - for (i = 0; i < nwrr; i++) + for (i = 0; i < p->bands - nstrict; i++) { + if (p->priomap[i] != nstrict + i) + return -EINVAL; + w[i] = p->weights[nstrict + i]; + } if (!nstrict) mode = TC_SCH_WRR8; @@ -2358,7 +2358,7 @@ static int airoha_tc_get_htb_get_leaf_queue(struct airoha_gdm_port *port, return -EINVAL; } - opt->qid = channel; + opt->qid = AIROHA_NUM_TX_RING + channel; return 0; } @@ -2454,6 +2454,19 @@ static void airoha_metadata_dst_free(struct airoha_gdm_port *port) } } +bool airoha_is_valid_gdm_port(struct airoha_eth *eth, + struct airoha_gdm_port *port) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(eth->ports); i++) { + if (eth->ports[i] == port) + return true; + } + + return false; +} + static int airoha_alloc_gdm_port(struct airoha_eth *eth, struct device_node *np, int index) { diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h index 60690b685710..ec8908f904c6 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.h +++ b/drivers/net/ethernet/airoha/airoha_eth.h @@ -532,6 +532,9 @@ u32 airoha_rmw(void __iomem *base, u32 offset, u32 mask, u32 val); #define airoha_qdma_clear(qdma, offset, val) \ airoha_rmw((qdma)->regs, (offset), (val), 0) +bool airoha_is_valid_gdm_port(struct airoha_eth *eth, + struct airoha_gdm_port *port); + void airoha_ppe_check_skb(struct airoha_ppe *ppe, u16 hash); int airoha_ppe_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_priv); diff --git a/drivers/net/ethernet/airoha/airoha_ppe.c b/drivers/net/ethernet/airoha/airoha_ppe.c index 8b55e871352d..f10dab935cab 100644 --- a/drivers/net/ethernet/airoha/airoha_ppe.c +++ b/drivers/net/ethernet/airoha/airoha_ppe.c @@ -197,7 +197,8 @@ static int airoha_get_dsa_port(struct net_device **dev) #endif } -static int airoha_ppe_foe_entry_prepare(struct airoha_foe_entry *hwe, +static int airoha_ppe_foe_entry_prepare(struct airoha_eth *eth, + struct airoha_foe_entry *hwe, struct net_device *dev, int type, struct airoha_flow_data *data, int l4proto) @@ -225,6 +226,9 @@ static int airoha_ppe_foe_entry_prepare(struct airoha_foe_entry *hwe, struct airoha_gdm_port *port = netdev_priv(dev); u8 pse_port; + if (!airoha_is_valid_gdm_port(eth, port)) + return -EINVAL; + if (dsa_port >= 0) pse_port = port->id == 4 ? FE_PSE_PORT_GDM4 : port->id; else @@ -633,7 +637,7 @@ static int airoha_ppe_flow_offload_replace(struct airoha_gdm_port *port, !is_valid_ether_addr(data.eth.h_dest)) return -EINVAL; - err = airoha_ppe_foe_entry_prepare(&hwe, odev, offload_type, + err = airoha_ppe_foe_entry_prepare(eth, &hwe, odev, offload_type, &data, l4proto); if (err) return err; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 1a70605fad38..28ee12186c37 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -15909,7 +15909,7 @@ static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx) goto err_reset; } - napi_enable(&bnapi->napi); + napi_enable_locked(&bnapi->napi); bnxt_db_nq_arm(bp, &cpr->cp_db, cpr->cp_raw_cons); for (i = 0; i < bp->nr_vnics; i++) { @@ -15931,7 +15931,7 @@ static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx) err_reset: netdev_err(bp->dev, "Unexpected HWRM error during queue start rc: %d\n", rc); - napi_enable(&bnapi->napi); + napi_enable_locked(&bnapi->napi); bnxt_db_nq_arm(bp, &cpr->cp_db, cpr->cp_raw_cons); bnxt_reset_task(bp, true); return rc; @@ -15971,7 +15971,7 @@ static int bnxt_queue_stop(struct net_device *dev, void *qmem, int idx) * completion is handled in NAPI to guarantee no more DMA on that ring * after seeing the completion. */ - napi_disable(&bnapi->napi); + napi_disable_locked(&bnapi->napi); if (bp->tph_mode) { bnxt_hwrm_cp_ring_free(bp, rxr->rx_cpr); diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c index 31a21ccf4863..4dea1fdce748 100644 --- a/drivers/net/ethernet/google/gve/gve_ethtool.c +++ b/drivers/net/ethernet/google/gve/gve_ethtool.c @@ -392,7 +392,9 @@ gve_get_ethtool_stats(struct net_device *netdev, */ data[i++] = 0; data[i++] = 0; - data[i++] = tx->dqo_tx.tail - tx->dqo_tx.head; + data[i++] = + (tx->dqo_tx.tail - tx->dqo_tx.head) & + tx->mask; } do { start = diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index b619a3ec245b..04192190beba 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -1802,18 +1802,22 @@ static ssize_t veth_pool_store(struct kobject *kobj, struct attribute *attr, long value = simple_strtol(buf, NULL, 10); long rc; + rtnl_lock(); + if (attr == &veth_active_attr) { if (value && !pool->active) { if (netif_running(netdev)) { if (ibmveth_alloc_buffer_pool(pool)) { netdev_err(netdev, "unable to alloc pool\n"); - return -ENOMEM; + rc = -ENOMEM; + goto unlock_err; } pool->active = 1; ibmveth_close(netdev); - if ((rc = ibmveth_open(netdev))) - return rc; + rc = ibmveth_open(netdev); + if (rc) + goto unlock_err; } else { pool->active = 1; } @@ -1833,48 +1837,59 @@ static ssize_t veth_pool_store(struct kobject *kobj, struct attribute *attr, if (i == IBMVETH_NUM_BUFF_POOLS) { netdev_err(netdev, "no active pool >= MTU\n"); - return -EPERM; + rc = -EPERM; + goto unlock_err; } if (netif_running(netdev)) { ibmveth_close(netdev); pool->active = 0; - if ((rc = ibmveth_open(netdev))) - return rc; + rc = ibmveth_open(netdev); + if (rc) + goto unlock_err; } pool->active = 0; } } else if (attr == &veth_num_attr) { if (value <= 0 || value > IBMVETH_MAX_POOL_COUNT) { - return -EINVAL; + rc = -EINVAL; + goto unlock_err; } else { if (netif_running(netdev)) { ibmveth_close(netdev); pool->size = value; - if ((rc = ibmveth_open(netdev))) - return rc; + rc = ibmveth_open(netdev); + if (rc) + goto unlock_err; } else { pool->size = value; } } } else if (attr == &veth_size_attr) { if (value <= IBMVETH_BUFF_OH || value > IBMVETH_MAX_BUF_SIZE) { - return -EINVAL; + rc = -EINVAL; + goto unlock_err; } else { if (netif_running(netdev)) { ibmveth_close(netdev); pool->buff_size = value; - if ((rc = ibmveth_open(netdev))) - return rc; + rc = ibmveth_open(netdev); + if (rc) + goto unlock_err; } else { pool->buff_size = value; } } } + rtnl_unlock(); /* kick the interrupt handler to allocate/deallocate pools */ ibmveth_interrupt(netdev->irq, netdev); return count; + +unlock_err: + rtnl_unlock(); + return rc; } diff --git a/drivers/net/ethernet/intel/e1000e/defines.h b/drivers/net/ethernet/intel/e1000e/defines.h index 5e2cfa73f889..8294a7c4f122 100644 --- a/drivers/net/ethernet/intel/e1000e/defines.h +++ b/drivers/net/ethernet/intel/e1000e/defines.h @@ -803,4 +803,7 @@ /* SerDes Control */ #define E1000_GEN_POLL_TIMEOUT 640 +#define E1000_FEXTNVM12_PHYPD_CTRL_MASK 0x00C00000 +#define E1000_FEXTNVM12_PHYPD_CTRL_P1 0x00800000 + #endif /* _E1000_DEFINES_H_ */ diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index 2f9655cf5dd9..364378133526 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -286,6 +286,45 @@ static void e1000_toggle_lanphypc_pch_lpt(struct e1000_hw *hw) } /** + * e1000_reconfigure_k1_exit_timeout - reconfigure K1 exit timeout to + * align to MTP and later platform requirements. + * @hw: pointer to the HW structure + * + * Context: PHY semaphore must be held by caller. + * Return: 0 on success, negative on failure + */ +static s32 e1000_reconfigure_k1_exit_timeout(struct e1000_hw *hw) +{ + u16 phy_timeout; + u32 fextnvm12; + s32 ret_val; + + if (hw->mac.type < e1000_pch_mtp) + return 0; + + /* Change Kumeran K1 power down state from P0s to P1 */ + fextnvm12 = er32(FEXTNVM12); + fextnvm12 &= ~E1000_FEXTNVM12_PHYPD_CTRL_MASK; + fextnvm12 |= E1000_FEXTNVM12_PHYPD_CTRL_P1; + ew32(FEXTNVM12, fextnvm12); + + /* Wait for the interface the settle */ + usleep_range(1000, 1100); + + /* Change K1 exit timeout */ + ret_val = e1e_rphy_locked(hw, I217_PHY_TIMEOUTS_REG, + &phy_timeout); + if (ret_val) + return ret_val; + + phy_timeout &= ~I217_PHY_TIMEOUTS_K1_EXIT_TO_MASK; + phy_timeout |= 0xF00; + + return e1e_wphy_locked(hw, I217_PHY_TIMEOUTS_REG, + phy_timeout); +} + +/** * e1000_init_phy_workarounds_pchlan - PHY initialization workarounds * @hw: pointer to the HW structure * @@ -327,15 +366,22 @@ static s32 e1000_init_phy_workarounds_pchlan(struct e1000_hw *hw) * LANPHYPC Value bit to force the interconnect to PCIe mode. */ switch (hw->mac.type) { + case e1000_pch_mtp: + case e1000_pch_lnp: + case e1000_pch_ptp: + case e1000_pch_nvp: + /* At this point the PHY might be inaccessible so don't + * propagate the failure + */ + if (e1000_reconfigure_k1_exit_timeout(hw)) + e_dbg("Failed to reconfigure K1 exit timeout\n"); + + fallthrough; case e1000_pch_lpt: case e1000_pch_spt: case e1000_pch_cnp: case e1000_pch_tgp: case e1000_pch_adp: - case e1000_pch_mtp: - case e1000_pch_lnp: - case e1000_pch_ptp: - case e1000_pch_nvp: if (e1000_phy_is_accessible_pchlan(hw)) break; @@ -419,8 +465,20 @@ static s32 e1000_init_phy_workarounds_pchlan(struct e1000_hw *hw) * the PHY is in. */ ret_val = hw->phy.ops.check_reset_block(hw); - if (ret_val) + if (ret_val) { e_err("ME blocked access to PHY after reset\n"); + goto out; + } + + if (hw->mac.type >= e1000_pch_mtp) { + ret_val = hw->phy.ops.acquire(hw); + if (ret_val) { + e_err("Failed to reconfigure K1 exit timeout\n"); + goto out; + } + ret_val = e1000_reconfigure_k1_exit_timeout(hw); + hw->phy.ops.release(hw); + } } out: @@ -4888,6 +4946,18 @@ static s32 e1000_init_hw_ich8lan(struct e1000_hw *hw) u16 i; e1000_initialize_hw_bits_ich8lan(hw); + if (hw->mac.type >= e1000_pch_mtp) { + ret_val = hw->phy.ops.acquire(hw); + if (ret_val) + return ret_val; + + ret_val = e1000_reconfigure_k1_exit_timeout(hw); + hw->phy.ops.release(hw); + if (ret_val) { + e_dbg("Error failed to reconfigure K1 exit timeout\n"); + return ret_val; + } + } /* Initialize identification LED */ ret_val = mac->ops.id_led_init(hw); diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.h b/drivers/net/ethernet/intel/e1000e/ich8lan.h index 2504b11c3169..5feb589a9b5f 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.h +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.h @@ -219,6 +219,10 @@ #define I217_PLL_CLOCK_GATE_REG PHY_REG(772, 28) #define I217_PLL_CLOCK_GATE_MASK 0x07FF +/* PHY Timeouts */ +#define I217_PHY_TIMEOUTS_REG PHY_REG(770, 21) +#define I217_PHY_TIMEOUTS_K1_EXIT_TO_MASK 0x0FC0 + #define SW_FLAG_TIMEOUT 1000 /* SW Semaphore flag timeout in ms */ /* Inband Control */ diff --git a/drivers/net/ethernet/intel/idpf/idpf_main.c b/drivers/net/ethernet/intel/idpf/idpf_main.c index b6c515d14cbf..bec4a02c5373 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_main.c +++ b/drivers/net/ethernet/intel/idpf/idpf_main.c @@ -87,7 +87,11 @@ destroy_wqs: */ static void idpf_shutdown(struct pci_dev *pdev) { - idpf_remove(pdev); + struct idpf_adapter *adapter = pci_get_drvdata(pdev); + + cancel_delayed_work_sync(&adapter->vc_event_task); + idpf_vc_core_deinit(adapter); + idpf_deinit_dflt_mbx(adapter); if (system_state == SYSTEM_POWER_OFF) pci_set_power_state(pdev, PCI_D3hot); diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index cd1d7b6c1782..c35cc5cb1185 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -337,8 +337,6 @@ struct igc_adapter { struct igc_led_classdev *leds; }; -void igc_set_queue_napi(struct igc_adapter *adapter, int q_idx, - struct napi_struct *napi); void igc_up(struct igc_adapter *adapter); void igc_down(struct igc_adapter *adapter); int igc_open(struct net_device *netdev); diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 491d942cefca..156d123c0e21 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -3042,7 +3042,7 @@ static void igc_xdp_xmit_zc(struct igc_ring *ring) * descriptors. Therefore, to be safe, we always ensure we have at least * 4 descriptors available. */ - while (xsk_tx_peek_desc(pool, &xdp_desc) && budget >= 4) { + while (budget >= 4 && xsk_tx_peek_desc(pool, &xdp_desc)) { struct igc_metadata_request meta_req; struct xsk_tx_metadata *meta = NULL; struct igc_tx_buffer *bi; @@ -5022,8 +5022,8 @@ static int igc_sw_init(struct igc_adapter *adapter) return 0; } -void igc_set_queue_napi(struct igc_adapter *adapter, int vector, - struct napi_struct *napi) +static void igc_set_queue_napi(struct igc_adapter *adapter, int vector, + struct napi_struct *napi) { struct igc_q_vector *q_vector = adapter->q_vector[vector]; diff --git a/drivers/net/ethernet/intel/igc/igc_xdp.c b/drivers/net/ethernet/intel/igc/igc_xdp.c index c538e6b18aad..9eb47b4beb06 100644 --- a/drivers/net/ethernet/intel/igc/igc_xdp.c +++ b/drivers/net/ethernet/intel/igc/igc_xdp.c @@ -97,7 +97,6 @@ static int igc_xdp_enable_pool(struct igc_adapter *adapter, napi_disable(napi); } - igc_set_queue_napi(adapter, queue_id, NULL); set_bit(IGC_RING_FLAG_AF_XDP_ZC, &rx_ring->flags); set_bit(IGC_RING_FLAG_AF_XDP_ZC, &tx_ring->flags); @@ -147,7 +146,6 @@ static int igc_xdp_disable_pool(struct igc_adapter *adapter, u16 queue_id) xsk_pool_dma_unmap(pool, IGC_RX_DMA_ATTR); clear_bit(IGC_RING_FLAG_AF_XDP_ZC, &rx_ring->flags); clear_bit(IGC_RING_FLAG_AF_XDP_ZC, &tx_ring->flags); - igc_set_queue_napi(adapter, queue_id, napi); if (needs_reset) { napi_enable(napi); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c index cb07ecd8937d..00935747c8c5 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c @@ -1453,9 +1453,11 @@ enum ixgbe_media_type ixgbe_get_media_type_e610(struct ixgbe_hw *hw) hw->link.link_info.phy_type_low = 0; } else { highest_bit = fls64(le64_to_cpu(pcaps.phy_type_low)); - if (highest_bit) + if (highest_bit) { hw->link.link_info.phy_type_low = BIT_ULL(highest_bit - 1); + hw->link.link_info.phy_type_high = 0; + } } } diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h index 44fe9b68d1c2..061fcd444d50 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h @@ -1113,6 +1113,9 @@ struct mvpp2 { /* Spinlocks for CM3 shared memory configuration */ spinlock_t mss_spinlock; + + /* Spinlock for shared PRS parser memory and shadow table */ + spinlock_t prs_spinlock; }; struct mvpp2_pcpu_stats { diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 566c12c89520..416a926a8281 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -7723,8 +7723,9 @@ static int mvpp2_probe(struct platform_device *pdev) if (mvpp2_read(priv, MVPP2_VER_ID_REG) == MVPP2_VER_PP23) priv->hw_version = MVPP23; - /* Init mss lock */ + /* Init locks for shared packet processor resources */ spin_lock_init(&priv->mss_spinlock); + spin_lock_init(&priv->prs_spinlock); /* Initialize network controller */ err = mvpp2_init(pdev, priv); diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c index 9af22f497a40..93e978bdf303 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c @@ -23,6 +23,8 @@ static int mvpp2_prs_hw_write(struct mvpp2 *priv, struct mvpp2_prs_entry *pe) { int i; + lockdep_assert_held(&priv->prs_spinlock); + if (pe->index > MVPP2_PRS_TCAM_SRAM_SIZE - 1) return -EINVAL; @@ -43,11 +45,13 @@ static int mvpp2_prs_hw_write(struct mvpp2 *priv, struct mvpp2_prs_entry *pe) } /* Initialize tcam entry from hw */ -int mvpp2_prs_init_from_hw(struct mvpp2 *priv, struct mvpp2_prs_entry *pe, - int tid) +static int __mvpp2_prs_init_from_hw(struct mvpp2 *priv, + struct mvpp2_prs_entry *pe, int tid) { int i; + lockdep_assert_held(&priv->prs_spinlock); + if (tid > MVPP2_PRS_TCAM_SRAM_SIZE - 1) return -EINVAL; @@ -73,6 +77,18 @@ int mvpp2_prs_init_from_hw(struct mvpp2 *priv, struct mvpp2_prs_entry *pe, return 0; } +int mvpp2_prs_init_from_hw(struct mvpp2 *priv, struct mvpp2_prs_entry *pe, + int tid) +{ + int err; + + spin_lock_bh(&priv->prs_spinlock); + err = __mvpp2_prs_init_from_hw(priv, pe, tid); + spin_unlock_bh(&priv->prs_spinlock); + + return err; +} + /* Invalidate tcam hw entry */ static void mvpp2_prs_hw_inv(struct mvpp2 *priv, int index) { @@ -374,7 +390,7 @@ static int mvpp2_prs_flow_find(struct mvpp2 *priv, int flow) priv->prs_shadow[tid].lu != MVPP2_PRS_LU_FLOWS) continue; - mvpp2_prs_init_from_hw(priv, &pe, tid); + __mvpp2_prs_init_from_hw(priv, &pe, tid); bits = mvpp2_prs_sram_ai_get(&pe); /* Sram store classification lookup ID in AI bits [5:0] */ @@ -441,7 +457,7 @@ static void mvpp2_prs_mac_drop_all_set(struct mvpp2 *priv, int port, bool add) if (priv->prs_shadow[MVPP2_PE_DROP_ALL].valid) { /* Entry exist - update port only */ - mvpp2_prs_init_from_hw(priv, &pe, MVPP2_PE_DROP_ALL); + __mvpp2_prs_init_from_hw(priv, &pe, MVPP2_PE_DROP_ALL); } else { /* Entry doesn't exist - create new */ memset(&pe, 0, sizeof(pe)); @@ -469,14 +485,17 @@ static void mvpp2_prs_mac_drop_all_set(struct mvpp2 *priv, int port, bool add) } /* Set port to unicast or multicast promiscuous mode */ -void mvpp2_prs_mac_promisc_set(struct mvpp2 *priv, int port, - enum mvpp2_prs_l2_cast l2_cast, bool add) +static void __mvpp2_prs_mac_promisc_set(struct mvpp2 *priv, int port, + enum mvpp2_prs_l2_cast l2_cast, + bool add) { struct mvpp2_prs_entry pe; unsigned char cast_match; unsigned int ri; int tid; + lockdep_assert_held(&priv->prs_spinlock); + if (l2_cast == MVPP2_PRS_L2_UNI_CAST) { cast_match = MVPP2_PRS_UCAST_VAL; tid = MVPP2_PE_MAC_UC_PROMISCUOUS; @@ -489,7 +508,7 @@ void mvpp2_prs_mac_promisc_set(struct mvpp2 *priv, int port, /* promiscuous mode - Accept unknown unicast or multicast packets */ if (priv->prs_shadow[tid].valid) { - mvpp2_prs_init_from_hw(priv, &pe, tid); + __mvpp2_prs_init_from_hw(priv, &pe, tid); } else { memset(&pe, 0, sizeof(pe)); mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_MAC); @@ -522,6 +541,14 @@ void mvpp2_prs_mac_promisc_set(struct mvpp2 *priv, int port, mvpp2_prs_hw_write(priv, &pe); } +void mvpp2_prs_mac_promisc_set(struct mvpp2 *priv, int port, + enum mvpp2_prs_l2_cast l2_cast, bool add) +{ + spin_lock_bh(&priv->prs_spinlock); + __mvpp2_prs_mac_promisc_set(priv, port, l2_cast, add); + spin_unlock_bh(&priv->prs_spinlock); +} + /* Set entry for dsa packets */ static void mvpp2_prs_dsa_tag_set(struct mvpp2 *priv, int port, bool add, bool tagged, bool extend) @@ -539,7 +566,7 @@ static void mvpp2_prs_dsa_tag_set(struct mvpp2 *priv, int port, bool add, if (priv->prs_shadow[tid].valid) { /* Entry exist - update port only */ - mvpp2_prs_init_from_hw(priv, &pe, tid); + __mvpp2_prs_init_from_hw(priv, &pe, tid); } else { /* Entry doesn't exist - create new */ memset(&pe, 0, sizeof(pe)); @@ -610,7 +637,7 @@ static void mvpp2_prs_dsa_tag_ethertype_set(struct mvpp2 *priv, int port, if (priv->prs_shadow[tid].valid) { /* Entry exist - update port only */ - mvpp2_prs_init_from_hw(priv, &pe, tid); + __mvpp2_prs_init_from_hw(priv, &pe, tid); } else { /* Entry doesn't exist - create new */ memset(&pe, 0, sizeof(pe)); @@ -673,7 +700,7 @@ static int mvpp2_prs_vlan_find(struct mvpp2 *priv, unsigned short tpid, int ai) priv->prs_shadow[tid].lu != MVPP2_PRS_LU_VLAN) continue; - mvpp2_prs_init_from_hw(priv, &pe, tid); + __mvpp2_prs_init_from_hw(priv, &pe, tid); match = mvpp2_prs_tcam_data_cmp(&pe, 0, tpid); if (!match) continue; @@ -726,7 +753,7 @@ static int mvpp2_prs_vlan_add(struct mvpp2 *priv, unsigned short tpid, int ai, priv->prs_shadow[tid_aux].lu != MVPP2_PRS_LU_VLAN) continue; - mvpp2_prs_init_from_hw(priv, &pe, tid_aux); + __mvpp2_prs_init_from_hw(priv, &pe, tid_aux); ri_bits = mvpp2_prs_sram_ri_get(&pe); if ((ri_bits & MVPP2_PRS_RI_VLAN_MASK) == MVPP2_PRS_RI_VLAN_DOUBLE) @@ -760,7 +787,7 @@ static int mvpp2_prs_vlan_add(struct mvpp2 *priv, unsigned short tpid, int ai, mvpp2_prs_shadow_set(priv, pe.index, MVPP2_PRS_LU_VLAN); } else { - mvpp2_prs_init_from_hw(priv, &pe, tid); + __mvpp2_prs_init_from_hw(priv, &pe, tid); } /* Update ports' mask */ mvpp2_prs_tcam_port_map_set(&pe, port_map); @@ -800,7 +827,7 @@ static int mvpp2_prs_double_vlan_find(struct mvpp2 *priv, unsigned short tpid1, priv->prs_shadow[tid].lu != MVPP2_PRS_LU_VLAN) continue; - mvpp2_prs_init_from_hw(priv, &pe, tid); + __mvpp2_prs_init_from_hw(priv, &pe, tid); match = mvpp2_prs_tcam_data_cmp(&pe, 0, tpid1) && mvpp2_prs_tcam_data_cmp(&pe, 4, tpid2); @@ -849,7 +876,7 @@ static int mvpp2_prs_double_vlan_add(struct mvpp2 *priv, unsigned short tpid1, priv->prs_shadow[tid_aux].lu != MVPP2_PRS_LU_VLAN) continue; - mvpp2_prs_init_from_hw(priv, &pe, tid_aux); + __mvpp2_prs_init_from_hw(priv, &pe, tid_aux); ri_bits = mvpp2_prs_sram_ri_get(&pe); ri_bits &= MVPP2_PRS_RI_VLAN_MASK; if (ri_bits == MVPP2_PRS_RI_VLAN_SINGLE || @@ -880,7 +907,7 @@ static int mvpp2_prs_double_vlan_add(struct mvpp2 *priv, unsigned short tpid1, mvpp2_prs_shadow_set(priv, pe.index, MVPP2_PRS_LU_VLAN); } else { - mvpp2_prs_init_from_hw(priv, &pe, tid); + __mvpp2_prs_init_from_hw(priv, &pe, tid); } /* Update ports' mask */ @@ -1213,8 +1240,8 @@ static void mvpp2_prs_mac_init(struct mvpp2 *priv) /* Create dummy entries for drop all and promiscuous modes */ mvpp2_prs_drop_fc(priv); mvpp2_prs_mac_drop_all_set(priv, 0, false); - mvpp2_prs_mac_promisc_set(priv, 0, MVPP2_PRS_L2_UNI_CAST, false); - mvpp2_prs_mac_promisc_set(priv, 0, MVPP2_PRS_L2_MULTI_CAST, false); + __mvpp2_prs_mac_promisc_set(priv, 0, MVPP2_PRS_L2_UNI_CAST, false); + __mvpp2_prs_mac_promisc_set(priv, 0, MVPP2_PRS_L2_MULTI_CAST, false); } /* Set default entries for various types of dsa packets */ @@ -1533,12 +1560,6 @@ static int mvpp2_prs_vlan_init(struct platform_device *pdev, struct mvpp2 *priv) struct mvpp2_prs_entry pe; int err; - priv->prs_double_vlans = devm_kcalloc(&pdev->dev, sizeof(bool), - MVPP2_PRS_DBL_VLANS_MAX, - GFP_KERNEL); - if (!priv->prs_double_vlans) - return -ENOMEM; - /* Double VLAN: 0x88A8, 0x8100 */ err = mvpp2_prs_double_vlan_add(priv, ETH_P_8021AD, ETH_P_8021Q, MVPP2_PRS_PORT_MASK); @@ -1941,7 +1962,7 @@ static int mvpp2_prs_vid_range_find(struct mvpp2_port *port, u16 vid, u16 mask) port->priv->prs_shadow[tid].lu != MVPP2_PRS_LU_VID) continue; - mvpp2_prs_init_from_hw(port->priv, &pe, tid); + __mvpp2_prs_init_from_hw(port->priv, &pe, tid); mvpp2_prs_tcam_data_byte_get(&pe, 2, &byte[0], &enable[0]); mvpp2_prs_tcam_data_byte_get(&pe, 3, &byte[1], &enable[1]); @@ -1970,6 +1991,8 @@ int mvpp2_prs_vid_entry_add(struct mvpp2_port *port, u16 vid) memset(&pe, 0, sizeof(pe)); + spin_lock_bh(&priv->prs_spinlock); + /* Scan TCAM and see if entry with this <vid,port> already exist */ tid = mvpp2_prs_vid_range_find(port, vid, mask); @@ -1988,8 +2011,10 @@ int mvpp2_prs_vid_entry_add(struct mvpp2_port *port, u16 vid) MVPP2_PRS_VLAN_FILT_MAX_ENTRY); /* There isn't room for a new VID filter */ - if (tid < 0) + if (tid < 0) { + spin_unlock_bh(&priv->prs_spinlock); return tid; + } mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_VID); pe.index = tid; @@ -1997,7 +2022,7 @@ int mvpp2_prs_vid_entry_add(struct mvpp2_port *port, u16 vid) /* Mask all ports */ mvpp2_prs_tcam_port_map_set(&pe, 0); } else { - mvpp2_prs_init_from_hw(priv, &pe, tid); + __mvpp2_prs_init_from_hw(priv, &pe, tid); } /* Enable the current port */ @@ -2019,6 +2044,7 @@ int mvpp2_prs_vid_entry_add(struct mvpp2_port *port, u16 vid) mvpp2_prs_shadow_set(priv, pe.index, MVPP2_PRS_LU_VID); mvpp2_prs_hw_write(priv, &pe); + spin_unlock_bh(&priv->prs_spinlock); return 0; } @@ -2028,15 +2054,16 @@ void mvpp2_prs_vid_entry_remove(struct mvpp2_port *port, u16 vid) struct mvpp2 *priv = port->priv; int tid; - /* Scan TCAM and see if entry with this <vid,port> already exist */ - tid = mvpp2_prs_vid_range_find(port, vid, 0xfff); + spin_lock_bh(&priv->prs_spinlock); - /* No such entry */ - if (tid < 0) - return; + /* Invalidate TCAM entry with this <vid,port>, if it exists */ + tid = mvpp2_prs_vid_range_find(port, vid, 0xfff); + if (tid >= 0) { + mvpp2_prs_hw_inv(priv, tid); + priv->prs_shadow[tid].valid = false; + } - mvpp2_prs_hw_inv(priv, tid); - priv->prs_shadow[tid].valid = false; + spin_unlock_bh(&priv->prs_spinlock); } /* Remove all existing VID filters on this port */ @@ -2045,6 +2072,8 @@ void mvpp2_prs_vid_remove_all(struct mvpp2_port *port) struct mvpp2 *priv = port->priv; int tid; + spin_lock_bh(&priv->prs_spinlock); + for (tid = MVPP2_PRS_VID_PORT_FIRST(port->id); tid <= MVPP2_PRS_VID_PORT_LAST(port->id); tid++) { if (priv->prs_shadow[tid].valid) { @@ -2052,6 +2081,8 @@ void mvpp2_prs_vid_remove_all(struct mvpp2_port *port) priv->prs_shadow[tid].valid = false; } } + + spin_unlock_bh(&priv->prs_spinlock); } /* Remove VID filering entry for this port */ @@ -2060,10 +2091,14 @@ void mvpp2_prs_vid_disable_filtering(struct mvpp2_port *port) unsigned int tid = MVPP2_PRS_VID_PORT_DFLT(port->id); struct mvpp2 *priv = port->priv; + spin_lock_bh(&priv->prs_spinlock); + /* Invalidate the guard entry */ mvpp2_prs_hw_inv(priv, tid); priv->prs_shadow[tid].valid = false; + + spin_unlock_bh(&priv->prs_spinlock); } /* Add guard entry that drops packets when no VID is matched on this port */ @@ -2079,6 +2114,8 @@ void mvpp2_prs_vid_enable_filtering(struct mvpp2_port *port) memset(&pe, 0, sizeof(pe)); + spin_lock_bh(&priv->prs_spinlock); + pe.index = tid; reg_val = mvpp2_read(priv, MVPP2_MH_REG(port->id)); @@ -2111,6 +2148,8 @@ void mvpp2_prs_vid_enable_filtering(struct mvpp2_port *port) /* Update shadow table */ mvpp2_prs_shadow_set(priv, pe.index, MVPP2_PRS_LU_VID); mvpp2_prs_hw_write(priv, &pe); + + spin_unlock_bh(&priv->prs_spinlock); } /* Parser default initialization */ @@ -2118,6 +2157,20 @@ int mvpp2_prs_default_init(struct platform_device *pdev, struct mvpp2 *priv) { int err, index, i; + priv->prs_shadow = devm_kcalloc(&pdev->dev, MVPP2_PRS_TCAM_SRAM_SIZE, + sizeof(*priv->prs_shadow), + GFP_KERNEL); + if (!priv->prs_shadow) + return -ENOMEM; + + priv->prs_double_vlans = devm_kcalloc(&pdev->dev, sizeof(bool), + MVPP2_PRS_DBL_VLANS_MAX, + GFP_KERNEL); + if (!priv->prs_double_vlans) + return -ENOMEM; + + spin_lock_bh(&priv->prs_spinlock); + /* Enable tcam table */ mvpp2_write(priv, MVPP2_PRS_TCAM_CTRL_REG, MVPP2_PRS_TCAM_EN_MASK); @@ -2136,12 +2189,6 @@ int mvpp2_prs_default_init(struct platform_device *pdev, struct mvpp2 *priv) for (index = 0; index < MVPP2_PRS_TCAM_SRAM_SIZE; index++) mvpp2_prs_hw_inv(priv, index); - priv->prs_shadow = devm_kcalloc(&pdev->dev, MVPP2_PRS_TCAM_SRAM_SIZE, - sizeof(*priv->prs_shadow), - GFP_KERNEL); - if (!priv->prs_shadow) - return -ENOMEM; - /* Always start from lookup = 0 */ for (index = 0; index < MVPP2_MAX_PORTS; index++) mvpp2_prs_hw_port_init(priv, index, MVPP2_PRS_LU_MH, @@ -2158,26 +2205,13 @@ int mvpp2_prs_default_init(struct platform_device *pdev, struct mvpp2 *priv) mvpp2_prs_vid_init(priv); err = mvpp2_prs_etype_init(priv); - if (err) - return err; - - err = mvpp2_prs_vlan_init(pdev, priv); - if (err) - return err; - - err = mvpp2_prs_pppoe_init(priv); - if (err) - return err; - - err = mvpp2_prs_ip6_init(priv); - if (err) - return err; - - err = mvpp2_prs_ip4_init(priv); - if (err) - return err; + err = err ? : mvpp2_prs_vlan_init(pdev, priv); + err = err ? : mvpp2_prs_pppoe_init(priv); + err = err ? : mvpp2_prs_ip6_init(priv); + err = err ? : mvpp2_prs_ip4_init(priv); - return 0; + spin_unlock_bh(&priv->prs_spinlock); + return err; } /* Compare MAC DA with tcam entry data */ @@ -2217,7 +2251,7 @@ mvpp2_prs_mac_da_range_find(struct mvpp2 *priv, int pmap, const u8 *da, (priv->prs_shadow[tid].udf != udf_type)) continue; - mvpp2_prs_init_from_hw(priv, &pe, tid); + __mvpp2_prs_init_from_hw(priv, &pe, tid); entry_pmap = mvpp2_prs_tcam_port_map_get(&pe); if (mvpp2_prs_mac_range_equals(&pe, da, mask) && @@ -2229,7 +2263,8 @@ mvpp2_prs_mac_da_range_find(struct mvpp2 *priv, int pmap, const u8 *da, } /* Update parser's mac da entry */ -int mvpp2_prs_mac_da_accept(struct mvpp2_port *port, const u8 *da, bool add) +static int __mvpp2_prs_mac_da_accept(struct mvpp2_port *port, + const u8 *da, bool add) { unsigned char mask[ETH_ALEN] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }; struct mvpp2 *priv = port->priv; @@ -2261,7 +2296,7 @@ int mvpp2_prs_mac_da_accept(struct mvpp2_port *port, const u8 *da, bool add) /* Mask all ports */ mvpp2_prs_tcam_port_map_set(&pe, 0); } else { - mvpp2_prs_init_from_hw(priv, &pe, tid); + __mvpp2_prs_init_from_hw(priv, &pe, tid); } mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_MAC); @@ -2317,6 +2352,17 @@ int mvpp2_prs_mac_da_accept(struct mvpp2_port *port, const u8 *da, bool add) return 0; } +int mvpp2_prs_mac_da_accept(struct mvpp2_port *port, const u8 *da, bool add) +{ + int err; + + spin_lock_bh(&port->priv->prs_spinlock); + err = __mvpp2_prs_mac_da_accept(port, da, add); + spin_unlock_bh(&port->priv->prs_spinlock); + + return err; +} + int mvpp2_prs_update_mac_da(struct net_device *dev, const u8 *da) { struct mvpp2_port *port = netdev_priv(dev); @@ -2345,6 +2391,8 @@ void mvpp2_prs_mac_del_all(struct mvpp2_port *port) unsigned long pmap; int index, tid; + spin_lock_bh(&priv->prs_spinlock); + for (tid = MVPP2_PE_MAC_RANGE_START; tid <= MVPP2_PE_MAC_RANGE_END; tid++) { unsigned char da[ETH_ALEN], da_mask[ETH_ALEN]; @@ -2354,7 +2402,7 @@ void mvpp2_prs_mac_del_all(struct mvpp2_port *port) (priv->prs_shadow[tid].udf != MVPP2_PRS_UDF_MAC_DEF)) continue; - mvpp2_prs_init_from_hw(priv, &pe, tid); + __mvpp2_prs_init_from_hw(priv, &pe, tid); pmap = mvpp2_prs_tcam_port_map_get(&pe); @@ -2375,14 +2423,17 @@ void mvpp2_prs_mac_del_all(struct mvpp2_port *port) continue; /* Remove entry from TCAM */ - mvpp2_prs_mac_da_accept(port, da, false); + __mvpp2_prs_mac_da_accept(port, da, false); } + + spin_unlock_bh(&priv->prs_spinlock); } int mvpp2_prs_tag_mode_set(struct mvpp2 *priv, int port, int type) { switch (type) { case MVPP2_TAG_TYPE_EDSA: + spin_lock_bh(&priv->prs_spinlock); /* Add port to EDSA entries */ mvpp2_prs_dsa_tag_set(priv, port, true, MVPP2_PRS_TAGGED, MVPP2_PRS_EDSA); @@ -2393,9 +2444,11 @@ int mvpp2_prs_tag_mode_set(struct mvpp2 *priv, int port, int type) MVPP2_PRS_TAGGED, MVPP2_PRS_DSA); mvpp2_prs_dsa_tag_set(priv, port, false, MVPP2_PRS_UNTAGGED, MVPP2_PRS_DSA); + spin_unlock_bh(&priv->prs_spinlock); break; case MVPP2_TAG_TYPE_DSA: + spin_lock_bh(&priv->prs_spinlock); /* Add port to DSA entries */ mvpp2_prs_dsa_tag_set(priv, port, true, MVPP2_PRS_TAGGED, MVPP2_PRS_DSA); @@ -2406,10 +2459,12 @@ int mvpp2_prs_tag_mode_set(struct mvpp2 *priv, int port, int type) MVPP2_PRS_TAGGED, MVPP2_PRS_EDSA); mvpp2_prs_dsa_tag_set(priv, port, false, MVPP2_PRS_UNTAGGED, MVPP2_PRS_EDSA); + spin_unlock_bh(&priv->prs_spinlock); break; case MVPP2_TAG_TYPE_MH: case MVPP2_TAG_TYPE_NONE: + spin_lock_bh(&priv->prs_spinlock); /* Remove port form EDSA and DSA entries */ mvpp2_prs_dsa_tag_set(priv, port, false, MVPP2_PRS_TAGGED, MVPP2_PRS_DSA); @@ -2419,6 +2474,7 @@ int mvpp2_prs_tag_mode_set(struct mvpp2 *priv, int port, int type) MVPP2_PRS_TAGGED, MVPP2_PRS_EDSA); mvpp2_prs_dsa_tag_set(priv, port, false, MVPP2_PRS_UNTAGGED, MVPP2_PRS_EDSA); + spin_unlock_bh(&priv->prs_spinlock); break; default: @@ -2437,11 +2493,15 @@ int mvpp2_prs_add_flow(struct mvpp2 *priv, int flow, u32 ri, u32 ri_mask) memset(&pe, 0, sizeof(pe)); + spin_lock_bh(&priv->prs_spinlock); + tid = mvpp2_prs_tcam_first_free(priv, MVPP2_PE_LAST_FREE_TID, MVPP2_PE_FIRST_FREE_TID); - if (tid < 0) + if (tid < 0) { + spin_unlock_bh(&priv->prs_spinlock); return tid; + } pe.index = tid; @@ -2461,6 +2521,7 @@ int mvpp2_prs_add_flow(struct mvpp2 *priv, int flow, u32 ri, u32 ri_mask) mvpp2_prs_tcam_port_map_set(&pe, MVPP2_PRS_PORT_MASK); mvpp2_prs_hw_write(priv, &pe); + spin_unlock_bh(&priv->prs_spinlock); return 0; } @@ -2472,6 +2533,8 @@ int mvpp2_prs_def_flow(struct mvpp2_port *port) memset(&pe, 0, sizeof(pe)); + spin_lock_bh(&port->priv->prs_spinlock); + tid = mvpp2_prs_flow_find(port->priv, port->id); /* Such entry not exist */ @@ -2480,8 +2543,10 @@ int mvpp2_prs_def_flow(struct mvpp2_port *port) tid = mvpp2_prs_tcam_first_free(port->priv, MVPP2_PE_LAST_FREE_TID, MVPP2_PE_FIRST_FREE_TID); - if (tid < 0) + if (tid < 0) { + spin_unlock_bh(&port->priv->prs_spinlock); return tid; + } pe.index = tid; @@ -2492,13 +2557,14 @@ int mvpp2_prs_def_flow(struct mvpp2_port *port) /* Update shadow table */ mvpp2_prs_shadow_set(port->priv, pe.index, MVPP2_PRS_LU_FLOWS); } else { - mvpp2_prs_init_from_hw(port->priv, &pe, tid); + __mvpp2_prs_init_from_hw(port->priv, &pe, tid); } mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_FLOWS); mvpp2_prs_tcam_port_map_set(&pe, (1 << port->id)); mvpp2_prs_hw_write(port->priv, &pe); + spin_unlock_bh(&port->priv->prs_spinlock); return 0; } @@ -2509,11 +2575,14 @@ int mvpp2_prs_hits(struct mvpp2 *priv, int index) if (index > MVPP2_PRS_TCAM_SRAM_SIZE) return -EINVAL; + spin_lock_bh(&priv->prs_spinlock); + mvpp2_write(priv, MVPP2_PRS_TCAM_HIT_IDX_REG, index); val = mvpp2_read(priv, MVPP2_PRS_TCAM_HIT_CNT_REG); val &= MVPP2_PRS_TCAM_HIT_CNT_MASK; + spin_unlock_bh(&priv->prs_spinlock); return val; } diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c index af8cabe828d0..0a6bb346ba45 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c @@ -1559,12 +1559,11 @@ handle_xdp_verdict: break; default: bpf_warn_invalid_xdp_action(pfvf->netdev, prog, act); - break; + fallthrough; case XDP_ABORTED: - if (xsk_buff) - xsk_buff_free(xsk_buff); - trace_xdp_exception(pfvf->netdev, prog, act); - break; + if (act == XDP_ABORTED) + trace_xdp_exception(pfvf->netdev, prog, act); + fallthrough; case XDP_DROP: cq->pool_ptrs++; if (xsk_buff) { diff --git a/drivers/net/ethernet/mellanox/mlx4/Kconfig b/drivers/net/ethernet/mellanox/mlx4/Kconfig index 825e05fb8607..0b1cb340206f 100644 --- a/drivers/net/ethernet/mellanox/mlx4/Kconfig +++ b/drivers/net/ethernet/mellanox/mlx4/Kconfig @@ -7,6 +7,7 @@ config MLX4_EN tristate "Mellanox Technologies 1/10/40Gbit Ethernet support" depends on PCI && NETDEVICES && ETHERNET && INET depends on PTP_1588_CLOCK_OPTIONAL + select PAGE_POOL select MLX4_CORE help This driver supports Mellanox Technologies ConnectX Ethernet diff --git a/drivers/net/ethernet/sfc/ef100_netdev.c b/drivers/net/ethernet/sfc/ef100_netdev.c index d941f073f1eb..3a06e3b1bd6b 100644 --- a/drivers/net/ethernet/sfc/ef100_netdev.c +++ b/drivers/net/ethernet/sfc/ef100_netdev.c @@ -450,8 +450,9 @@ int ef100_probe_netdev(struct efx_probe_data *probe_data) net_dev->hw_enc_features |= efx->type->offload_features; net_dev->vlan_features |= NETIF_F_HW_CSUM | NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_ALL_TSO; - netif_set_tso_max_segs(net_dev, - ESE_EF100_DP_GZ_TSO_MAX_HDR_NUM_SEGS_DEFAULT); + nic_data = efx->nic_data; + netif_set_tso_max_size(efx->net_dev, nic_data->tso_max_payload_len); + netif_set_tso_max_segs(efx->net_dev, nic_data->tso_max_payload_num_segs); rc = efx_ef100_init_datapath_caps(efx); if (rc < 0) @@ -477,7 +478,6 @@ int ef100_probe_netdev(struct efx_probe_data *probe_data) /* Don't fail init if RSS setup doesn't work. */ efx_mcdi_push_default_indir_table(efx, efx->n_rx_channels); - nic_data = efx->nic_data; rc = ef100_get_mac_address(efx, net_dev->perm_addr, CLIENT_HANDLE_SELF, efx->type->is_vf); if (rc) diff --git a/drivers/net/ethernet/sfc/ef100_nic.c b/drivers/net/ethernet/sfc/ef100_nic.c index 62e674d6ff60..3ad95a4c8af2 100644 --- a/drivers/net/ethernet/sfc/ef100_nic.c +++ b/drivers/net/ethernet/sfc/ef100_nic.c @@ -887,8 +887,7 @@ static int ef100_process_design_param(struct efx_nic *efx, case ESE_EF100_DP_GZ_TSO_MAX_HDR_NUM_SEGS: /* We always put HDR_NUM_SEGS=1 in our TSO descriptors */ if (!reader->value) { - netif_err(efx, probe, efx->net_dev, - "TSO_MAX_HDR_NUM_SEGS < 1\n"); + pci_err(efx->pci_dev, "TSO_MAX_HDR_NUM_SEGS < 1\n"); return -EOPNOTSUPP; } return 0; @@ -901,32 +900,28 @@ static int ef100_process_design_param(struct efx_nic *efx, */ if (!reader->value || reader->value > EFX_MIN_DMAQ_SIZE || EFX_MIN_DMAQ_SIZE % (u32)reader->value) { - netif_err(efx, probe, efx->net_dev, - "%s size granularity is %llu, can't guarantee safety\n", - reader->type == ESE_EF100_DP_GZ_RXQ_SIZE_GRANULARITY ? "RXQ" : "TXQ", - reader->value); + pci_err(efx->pci_dev, + "%s size granularity is %llu, can't guarantee safety\n", + reader->type == ESE_EF100_DP_GZ_RXQ_SIZE_GRANULARITY ? "RXQ" : "TXQ", + reader->value); return -EOPNOTSUPP; } return 0; case ESE_EF100_DP_GZ_TSO_MAX_PAYLOAD_LEN: nic_data->tso_max_payload_len = min_t(u64, reader->value, GSO_LEGACY_MAX_SIZE); - netif_set_tso_max_size(efx->net_dev, - nic_data->tso_max_payload_len); return 0; case ESE_EF100_DP_GZ_TSO_MAX_PAYLOAD_NUM_SEGS: nic_data->tso_max_payload_num_segs = min_t(u64, reader->value, 0xffff); - netif_set_tso_max_segs(efx->net_dev, - nic_data->tso_max_payload_num_segs); return 0; case ESE_EF100_DP_GZ_TSO_MAX_NUM_FRAMES: nic_data->tso_max_frames = min_t(u64, reader->value, 0xffff); return 0; case ESE_EF100_DP_GZ_COMPAT: if (reader->value) { - netif_err(efx, probe, efx->net_dev, - "DP_COMPAT has unknown bits %#llx, driver not compatible with this hw\n", - reader->value); + pci_err(efx->pci_dev, + "DP_COMPAT has unknown bits %#llx, driver not compatible with this hw\n", + reader->value); return -EOPNOTSUPP; } return 0; @@ -946,10 +941,10 @@ static int ef100_process_design_param(struct efx_nic *efx, * So the value of this shouldn't matter. */ if (reader->value != ESE_EF100_DP_GZ_VI_STRIDES_DEFAULT) - netif_dbg(efx, probe, efx->net_dev, - "NIC has other than default VI_STRIDES (mask " - "%#llx), early probing might use wrong one\n", - reader->value); + pci_dbg(efx->pci_dev, + "NIC has other than default VI_STRIDES (mask " + "%#llx), early probing might use wrong one\n", + reader->value); return 0; case ESE_EF100_DP_GZ_RX_MAX_RUNT: /* Driver doesn't look at L2_STATUS:LEN_ERR bit, so we don't @@ -961,9 +956,9 @@ static int ef100_process_design_param(struct efx_nic *efx, /* Host interface says "Drivers should ignore design parameters * that they do not recognise." */ - netif_dbg(efx, probe, efx->net_dev, - "Ignoring unrecognised design parameter %u\n", - reader->type); + pci_dbg(efx->pci_dev, + "Ignoring unrecognised design parameter %u\n", + reader->type); return 0; } } @@ -999,13 +994,13 @@ static int ef100_check_design_params(struct efx_nic *efx) */ if (reader.state != EF100_TLV_TYPE) { if (reader.state == EF100_TLV_TYPE_CONT) - netif_err(efx, probe, efx->net_dev, - "truncated design parameter (incomplete type %u)\n", - reader.type); + pci_err(efx->pci_dev, + "truncated design parameter (incomplete type %u)\n", + reader.type); else - netif_err(efx, probe, efx->net_dev, - "truncated design parameter %u\n", - reader.type); + pci_err(efx->pci_dev, + "truncated design parameter %u\n", + reader.type); rc = -EIO; } out: diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c index b67af4651185..ddda0c1e7a6d 100644 --- a/drivers/net/netdevsim/netdev.c +++ b/drivers/net/netdevsim/netdev.c @@ -939,6 +939,7 @@ static int nsim_init_netdevsim(struct netdevsim *ns) ns->netdev->netdev_ops = &nsim_netdev_ops; ns->netdev->stat_ops = &nsim_stat_ops; ns->netdev->queue_mgmt_ops = &nsim_queue_mgmt_ops; + netdev_lockdep_set_classes(ns->netdev); err = nsim_udp_tunnels_info_create(ns->nsim_dev, ns->netdev); if (err) @@ -960,6 +961,14 @@ static int nsim_init_netdevsim(struct netdevsim *ns) if (err) goto err_ipsec_teardown; rtnl_unlock(); + + if (IS_ENABLED(CONFIG_DEBUG_NET)) { + ns->nb.notifier_call = netdev_debug_event; + if (register_netdevice_notifier_dev_net(ns->netdev, &ns->nb, + &ns->nn)) + ns->nb.notifier_call = NULL; + } + return 0; err_ipsec_teardown: @@ -1043,6 +1052,10 @@ void nsim_destroy(struct netdevsim *ns) debugfs_remove(ns->qr_dfs); debugfs_remove(ns->pp_dfs); + if (ns->nb.notifier_call) + unregister_netdevice_notifier_dev_net(ns->netdev, &ns->nb, + &ns->nn); + rtnl_lock(); peer = rtnl_dereference(ns->peer); if (peer) diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h index 665020d18f29..d04401f0bdf7 100644 --- a/drivers/net/netdevsim/netdevsim.h +++ b/drivers/net/netdevsim/netdevsim.h @@ -144,6 +144,9 @@ struct netdevsim { struct nsim_ethtool ethtool; struct netdevsim __rcu *peer; + + struct notifier_block nb; + struct netdev_net_notifier nn; }; struct netdevsim * diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index aeab2308b150..724b93aa4f7e 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -530,7 +530,8 @@ static int rx_submit (struct usbnet *dev, struct urb *urb, gfp_t flags) netif_device_present (dev->net) && test_bit(EVENT_DEV_OPEN, &dev->flags) && !test_bit (EVENT_RX_HALT, &dev->flags) && - !test_bit (EVENT_DEV_ASLEEP, &dev->flags)) { + !test_bit (EVENT_DEV_ASLEEP, &dev->flags) && + !usbnet_going_away(dev)) { switch (retval = usb_submit_urb (urb, GFP_ATOMIC)) { case -EPIPE: usbnet_defer_kevent (dev, EVENT_RX_HALT); @@ -551,8 +552,7 @@ static int rx_submit (struct usbnet *dev, struct urb *urb, gfp_t flags) tasklet_schedule (&dev->bh); break; case 0: - if (!usbnet_going_away(dev)) - __usbnet_queue_skb(&dev->rxq, skb, rx_start); + __usbnet_queue_skb(&dev->rxq, skb, rx_start); } } else { netif_dbg(dev, ifdown, dev->net, "rx: stopped\n"); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index fa79145518d1..cf3b6445817b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4192,7 +4192,7 @@ int dev_change_flags(struct net_device *dev, unsigned int flags, int netif_set_alias(struct net_device *dev, const char *alias, size_t len); int dev_set_alias(struct net_device *, const char *, size_t); int dev_get_alias(const struct net_device *, char *, size_t); -int netif_change_net_namespace(struct net_device *dev, struct net *net, +int __dev_change_net_namespace(struct net_device *dev, struct net *net, const char *pat, int new_ifindex, struct netlink_ext_ack *extack); int dev_change_net_namespace(struct net_device *dev, struct net *net, diff --git a/include/net/ip.h b/include/net/ip.h index 8a48ade24620..47ed6d23853d 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -667,14 +667,6 @@ static inline void ip_ipgre_mc_map(__be32 naddr, const unsigned char *broadcast, memcpy(buf, &naddr, sizeof(naddr)); } -#if IS_MODULE(CONFIG_IPV6) -#define EXPORT_IPV6_MOD(X) EXPORT_SYMBOL(X) -#define EXPORT_IPV6_MOD_GPL(X) EXPORT_SYMBOL_GPL(X) -#else -#define EXPORT_IPV6_MOD(X) -#define EXPORT_IPV6_MOD_GPL(X) -#endif - #if IS_ENABLED(CONFIG_IPV6) #include <linux/ipv6.h> #endif @@ -694,6 +686,14 @@ static __inline__ void inet_reset_saddr(struct sock *sk) #endif +#if IS_MODULE(CONFIG_IPV6) +#define EXPORT_IPV6_MOD(X) EXPORT_SYMBOL(X) +#define EXPORT_IPV6_MOD_GPL(X) EXPORT_SYMBOL_GPL(X) +#else +#define EXPORT_IPV6_MOD(X) +#define EXPORT_IPV6_MOD_GPL(X) +#endif + static inline unsigned int ipv4_addr_hash(__be32 ip) { return (__force unsigned int) ip; diff --git a/include/net/netdev_lock.h b/include/net/netdev_lock.h index 1c0c9a94cc22..c316b551df8d 100644 --- a/include/net/netdev_lock.h +++ b/include/net/netdev_lock.h @@ -98,4 +98,7 @@ static inline int netdev_lock_cmp_fn(const struct lockdep_map *a, &qdisc_xmit_lock_key); \ } +int netdev_debug_event(struct notifier_block *nb, unsigned long event, + void *ptr); + #endif diff --git a/include/net/page_pool/memory_provider.h b/include/net/page_pool/memory_provider.h index b3e665897767..ada4f968960a 100644 --- a/include/net/page_pool/memory_provider.h +++ b/include/net/page_pool/memory_provider.h @@ -6,6 +6,7 @@ #include <net/page_pool/types.h> struct netdev_rx_queue; +struct netlink_ext_ack; struct sk_buff; struct memory_provider_ops { @@ -24,8 +25,13 @@ void net_mp_niov_clear_page_pool(struct net_iov *niov); int net_mp_open_rxq(struct net_device *dev, unsigned ifq_idx, struct pp_memory_provider_params *p); +int __net_mp_open_rxq(struct net_device *dev, unsigned int rxq_idx, + const struct pp_memory_provider_params *p, + struct netlink_ext_ack *extack); void net_mp_close_rxq(struct net_device *dev, unsigned ifq_idx, struct pp_memory_provider_params *old_p); +void __net_mp_close_rxq(struct net_device *dev, unsigned int rxq_idx, + const struct pp_memory_provider_params *old_p); /** * net_mp_netmem_place_in_cache() - give a netmem to a page pool diff --git a/net/core/Makefile b/net/core/Makefile index a10c3bd96798..b2a76ce33932 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -45,5 +45,5 @@ obj-$(CONFIG_BPF_SYSCALL) += bpf_sk_storage.o obj-$(CONFIG_OF) += of_net.o obj-$(CONFIG_NET_TEST) += net_test.o obj-$(CONFIG_NET_DEVMEM) += devmem.o -obj-$(CONFIG_DEBUG_NET_SMALL_RTNL) += rtnl_net_debug.o +obj-$(CONFIG_DEBUG_NET) += lock_debug.o obj-$(CONFIG_FAIL_SKB_REALLOC) += skb_fault_injection.o diff --git a/net/core/dev.c b/net/core/dev.c index be17e0660144..0608605cfc24 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1771,6 +1771,7 @@ void netif_disable_lro(struct net_device *dev) netdev_unlock_ops(lower_dev); } } +EXPORT_IPV6_MOD(netif_disable_lro); /** * dev_disable_gro_hw - disable HW Generic Receive Offload on a device @@ -1858,7 +1859,9 @@ static int call_netdevice_register_net_notifiers(struct notifier_block *nb, int err; for_each_netdev(net, dev) { + netdev_lock_ops(dev); err = call_netdevice_register_notifiers(nb, dev); + netdev_unlock_ops(dev); if (err) goto rollback; } @@ -10284,7 +10287,9 @@ int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) goto unlock; } + netdev_lock_ops(dev); err = dev_xdp_attach_link(dev, &extack, link); + netdev_unlock_ops(dev); rtnl_unlock(); if (err) { @@ -11045,7 +11050,9 @@ int register_netdevice(struct net_device *dev) memcpy(dev->perm_addr, dev->dev_addr, dev->addr_len); /* Notify protocols, that a new device appeared. */ + netdev_lock_ops(dev); ret = call_netdevice_notifiers(NETDEV_REGISTER, dev); + netdev_unlock_ops(dev); ret = notifier_to_errno(ret); if (ret) { /* Expect explicit free_netdev() on failure */ @@ -12057,7 +12064,7 @@ void unregister_netdev(struct net_device *dev) } EXPORT_SYMBOL(unregister_netdev); -int netif_change_net_namespace(struct net_device *dev, struct net *net, +int __dev_change_net_namespace(struct net_device *dev, struct net *net, const char *pat, int new_ifindex, struct netlink_ext_ack *extack) { @@ -12142,11 +12149,12 @@ int netif_change_net_namespace(struct net_device *dev, struct net *net, * And now a mini version of register_netdevice unregister_netdevice. */ + netdev_lock_ops(dev); /* If device is running close it first. */ netif_close(dev); - /* And unlink it from device chain */ unlist_netdevice(dev); + netdev_unlock_ops(dev); synchronize_net(); @@ -12208,11 +12216,12 @@ int netif_change_net_namespace(struct net_device *dev, struct net *net, err = netdev_change_owner(dev, net_old, net); WARN_ON(err); + netdev_lock_ops(dev); /* Add the device back in the hashes */ list_netdevice(dev); - /* Notify protocols, that a new device appeared. */ call_netdevice_notifiers(NETDEV_REGISTER, dev); + netdev_unlock_ops(dev); /* * Prevent userspace races by waiting until the network diff --git a/net/core/dev_api.c b/net/core/dev_api.c index 8dbc60612100..90bafb0b1b8c 100644 --- a/net/core/dev_api.c +++ b/net/core/dev_api.c @@ -117,13 +117,7 @@ EXPORT_SYMBOL(dev_set_mac_address_user); int dev_change_net_namespace(struct net_device *dev, struct net *net, const char *pat) { - int ret; - - netdev_lock_ops(dev); - ret = netif_change_net_namespace(dev, net, pat, 0, NULL); - netdev_unlock_ops(dev); - - return ret; + return __dev_change_net_namespace(dev, net, pat, 0, NULL); } EXPORT_SYMBOL_GPL(dev_change_net_namespace); diff --git a/net/core/devmem.c b/net/core/devmem.c index ee145a2aa41c..6e27a47d0493 100644 --- a/net/core/devmem.c +++ b/net/core/devmem.c @@ -8,7 +8,6 @@ */ #include <linux/dma-buf.h> -#include <linux/ethtool_netlink.h> #include <linux/genalloc.h> #include <linux/mm.h> #include <linux/netdevice.h> @@ -117,21 +116,19 @@ void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding) struct netdev_rx_queue *rxq; unsigned long xa_idx; unsigned int rxq_idx; - int err; if (binding->list.next) list_del(&binding->list); xa_for_each(&binding->bound_rxqs, xa_idx, rxq) { - WARN_ON(rxq->mp_params.mp_priv != binding); - - rxq->mp_params.mp_priv = NULL; - rxq->mp_params.mp_ops = NULL; + const struct pp_memory_provider_params mp_params = { + .mp_priv = binding, + .mp_ops = &dmabuf_devmem_ops, + }; rxq_idx = get_netdev_rx_queue_index(rxq); - err = netdev_rx_queue_restart(binding->dev, rxq_idx); - WARN_ON(err && err != -ENETDOWN); + __net_mp_close_rxq(binding->dev, rxq_idx, &mp_params); } xa_erase(&net_devmem_dmabuf_bindings, binding->id); @@ -143,57 +140,28 @@ int net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx, struct net_devmem_dmabuf_binding *binding, struct netlink_ext_ack *extack) { + struct pp_memory_provider_params mp_params = { + .mp_priv = binding, + .mp_ops = &dmabuf_devmem_ops, + }; struct netdev_rx_queue *rxq; u32 xa_idx; int err; - if (rxq_idx >= dev->real_num_rx_queues) { - NL_SET_ERR_MSG(extack, "rx queue index out of range"); - return -ERANGE; - } - - if (dev->cfg->hds_config != ETHTOOL_TCP_DATA_SPLIT_ENABLED) { - NL_SET_ERR_MSG(extack, "tcp-data-split is disabled"); - return -EINVAL; - } - - if (dev->cfg->hds_thresh) { - NL_SET_ERR_MSG(extack, "hds-thresh is not zero"); - return -EINVAL; - } + err = __net_mp_open_rxq(dev, rxq_idx, &mp_params, extack); + if (err) + return err; rxq = __netif_get_rx_queue(dev, rxq_idx); - if (rxq->mp_params.mp_ops) { - NL_SET_ERR_MSG(extack, "designated queue already memory provider bound"); - return -EEXIST; - } - -#ifdef CONFIG_XDP_SOCKETS - if (rxq->pool) { - NL_SET_ERR_MSG(extack, "designated queue already in use by AF_XDP"); - return -EBUSY; - } -#endif - err = xa_alloc(&binding->bound_rxqs, &xa_idx, rxq, xa_limit_32b, GFP_KERNEL); if (err) - return err; - - rxq->mp_params.mp_priv = binding; - rxq->mp_params.mp_ops = &dmabuf_devmem_ops; - - err = netdev_rx_queue_restart(dev, rxq_idx); - if (err) - goto err_xa_erase; + goto err_close_rxq; return 0; -err_xa_erase: - rxq->mp_params.mp_priv = NULL; - rxq->mp_params.mp_ops = NULL; - xa_erase(&binding->bound_rxqs, xa_idx); - +err_close_rxq: + __net_mp_close_rxq(dev, rxq_idx, &mp_params); return err; } diff --git a/net/core/dst.c b/net/core/dst.c index c99b95cf9cbb..795ca07e28a4 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -165,6 +165,14 @@ static void dst_count_dec(struct dst_entry *dst) void dst_release(struct dst_entry *dst) { if (dst && rcuref_put(&dst->__rcuref)) { +#ifdef CONFIG_DST_CACHE + if (dst->flags & DST_METADATA) { + struct metadata_dst *md_dst = (struct metadata_dst *)dst; + + if (md_dst->type == METADATA_IP_TUNNEL) + dst_cache_reset_now(&md_dst->u.tun_info.dst_cache); + } +#endif dst_count_dec(dst); call_rcu_hurry(&dst->rcu_head, dst_destroy_rcu); } diff --git a/net/core/rtnl_net_debug.c b/net/core/lock_debug.c index 7ecd28cc1c22..b7f22dc92a6f 100644 --- a/net/core/rtnl_net_debug.c +++ b/net/core/lock_debug.c @@ -6,10 +6,11 @@ #include <linux/notifier.h> #include <linux/rtnetlink.h> #include <net/net_namespace.h> +#include <net/netdev_lock.h> #include <net/netns/generic.h> -static int rtnl_net_debug_event(struct notifier_block *nb, - unsigned long event, void *ptr) +int netdev_debug_event(struct notifier_block *nb, unsigned long event, + void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); @@ -17,11 +18,13 @@ static int rtnl_net_debug_event(struct notifier_block *nb, /* Keep enum and don't add default to trigger -Werror=switch */ switch (cmd) { + case NETDEV_REGISTER: case NETDEV_UP: + netdev_ops_assert_locked(dev); + fallthrough; case NETDEV_DOWN: case NETDEV_REBOOT: case NETDEV_CHANGE: - case NETDEV_REGISTER: case NETDEV_UNREGISTER: case NETDEV_CHANGEMTU: case NETDEV_CHANGEADDR: @@ -66,6 +69,7 @@ static int rtnl_net_debug_event(struct notifier_block *nb, return NOTIFY_DONE; } +EXPORT_SYMBOL_NS_GPL(netdev_debug_event, "NETDEV_INTERNAL"); static int rtnl_net_debug_net_id; @@ -74,7 +78,7 @@ static int __net_init rtnl_net_debug_net_init(struct net *net) struct notifier_block *nb; nb = net_generic(net, rtnl_net_debug_net_id); - nb->notifier_call = rtnl_net_debug_event; + nb->notifier_call = netdev_debug_event; return register_netdevice_notifier_net(net, nb); } @@ -95,14 +99,14 @@ static struct pernet_operations rtnl_net_debug_net_ops __net_initdata = { }; static struct notifier_block rtnl_net_debug_block = { - .notifier_call = rtnl_net_debug_event, + .notifier_call = netdev_debug_event, }; static int __init rtnl_net_debug_init(void) { int ret; - ret = register_pernet_device(&rtnl_net_debug_net_ops); + ret = register_pernet_subsys(&rtnl_net_debug_net_ops); if (ret) return ret; diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index 3afeaa8c5dc5..5d7af50fe702 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -874,12 +874,6 @@ int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info) goto err_unlock; } - if (dev_xdp_prog_count(netdev)) { - NL_SET_ERR_MSG(info->extack, "unable to bind dmabuf to device with XDP program attached"); - err = -EEXIST; - goto err_unlock; - } - binding = net_devmem_bind_dmabuf(netdev, dmabuf_fd, info->extack); if (IS_ERR(binding)) { err = PTR_ERR(binding); diff --git a/net/core/netdev_rx_queue.c b/net/core/netdev_rx_queue.c index 3af716f77a13..d126f10197bf 100644 --- a/net/core/netdev_rx_queue.c +++ b/net/core/netdev_rx_queue.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later +#include <linux/ethtool_netlink.h> #include <linux/netdevice.h> #include <net/netdev_lock.h> #include <net/netdev_queues.h> @@ -86,8 +87,9 @@ err_free_new_mem: } EXPORT_SYMBOL_NS_GPL(netdev_rx_queue_restart, "NETDEV_INTERNAL"); -static int __net_mp_open_rxq(struct net_device *dev, unsigned ifq_idx, - struct pp_memory_provider_params *p) +int __net_mp_open_rxq(struct net_device *dev, unsigned int rxq_idx, + const struct pp_memory_provider_params *p, + struct netlink_ext_ack *extack) { struct netdev_rx_queue *rxq; int ret; @@ -95,16 +97,41 @@ static int __net_mp_open_rxq(struct net_device *dev, unsigned ifq_idx, if (!netdev_need_ops_lock(dev)) return -EOPNOTSUPP; - if (ifq_idx >= dev->real_num_rx_queues) + if (rxq_idx >= dev->real_num_rx_queues) return -EINVAL; - ifq_idx = array_index_nospec(ifq_idx, dev->real_num_rx_queues); + rxq_idx = array_index_nospec(rxq_idx, dev->real_num_rx_queues); - rxq = __netif_get_rx_queue(dev, ifq_idx); - if (rxq->mp_params.mp_ops) + if (rxq_idx >= dev->real_num_rx_queues) { + NL_SET_ERR_MSG(extack, "rx queue index out of range"); + return -ERANGE; + } + if (dev->cfg->hds_config != ETHTOOL_TCP_DATA_SPLIT_ENABLED) { + NL_SET_ERR_MSG(extack, "tcp-data-split is disabled"); + return -EINVAL; + } + if (dev->cfg->hds_thresh) { + NL_SET_ERR_MSG(extack, "hds-thresh is not zero"); + return -EINVAL; + } + if (dev_xdp_prog_count(dev)) { + NL_SET_ERR_MSG(extack, "unable to custom memory provider to device with XDP program attached"); return -EEXIST; + } + + rxq = __netif_get_rx_queue(dev, rxq_idx); + if (rxq->mp_params.mp_ops) { + NL_SET_ERR_MSG(extack, "designated queue already memory provider bound"); + return -EEXIST; + } +#ifdef CONFIG_XDP_SOCKETS + if (rxq->pool) { + NL_SET_ERR_MSG(extack, "designated queue already in use by AF_XDP"); + return -EBUSY; + } +#endif rxq->mp_params = *p; - ret = netdev_rx_queue_restart(dev, ifq_idx); + ret = netdev_rx_queue_restart(dev, rxq_idx); if (ret) { rxq->mp_params.mp_ops = NULL; rxq->mp_params.mp_priv = NULL; @@ -112,21 +139,22 @@ static int __net_mp_open_rxq(struct net_device *dev, unsigned ifq_idx, return ret; } -int net_mp_open_rxq(struct net_device *dev, unsigned ifq_idx, +int net_mp_open_rxq(struct net_device *dev, unsigned int rxq_idx, struct pp_memory_provider_params *p) { int ret; netdev_lock(dev); - ret = __net_mp_open_rxq(dev, ifq_idx, p); + ret = __net_mp_open_rxq(dev, rxq_idx, p, NULL); netdev_unlock(dev); return ret; } -static void __net_mp_close_rxq(struct net_device *dev, unsigned ifq_idx, - struct pp_memory_provider_params *old_p) +void __net_mp_close_rxq(struct net_device *dev, unsigned int ifq_idx, + const struct pp_memory_provider_params *old_p) { struct netdev_rx_queue *rxq; + int err; if (WARN_ON_ONCE(ifq_idx >= dev->real_num_rx_queues)) return; @@ -146,7 +174,8 @@ static void __net_mp_close_rxq(struct net_device *dev, unsigned ifq_idx, rxq->mp_params.mp_ops = NULL; rxq->mp_params.mp_priv = NULL; - WARN_ON(netdev_rx_queue_restart(dev, ifq_idx)); + err = netdev_rx_queue_restart(dev, ifq_idx); + WARN_ON(err && err != -ENETDOWN); } void net_mp_close_rxq(struct net_device *dev, unsigned ifq_idx, diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 334db17be37d..c23852835050 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3025,8 +3025,6 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev, char ifname[IFNAMSIZ]; int err; - netdev_lock_ops(dev); - err = validate_linkmsg(dev, tb, extack); if (err < 0) goto errout; @@ -3042,14 +3040,16 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev, new_ifindex = nla_get_s32_default(tb[IFLA_NEW_IFINDEX], 0); - err = netif_change_net_namespace(dev, tgt_net, pat, + err = __dev_change_net_namespace(dev, tgt_net, pat, new_ifindex, extack); if (err) - goto errout; + return err; status |= DO_SETLINK_MODIFIED; } + netdev_lock_ops(dev); + if (tb[IFLA_MAP]) { struct rtnl_link_ifmap *u_map; struct ifmap k_map; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 754f60fb6e25..77e5705ac799 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -281,7 +281,7 @@ static struct in_device *inetdev_init(struct net_device *dev) if (!in_dev->arp_parms) goto out_kfree; if (IPV4_DEVCONF(in_dev->cnf, FORWARDING)) - dev_disable_lro(dev); + netif_disable_lro(dev); /* Reference in_dev->dev */ netdev_hold(dev, &in_dev->dev_tracker, GFP_KERNEL); /* Account for reference dev->ip_ptr (below) */ diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index a3676155be78..f65d2f727381 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -416,7 +416,7 @@ int skb_tunnel_check_pmtu(struct sk_buff *skb, struct dst_entry *encap_dst, skb_dst_update_pmtu_no_confirm(skb, mtu); - if (!reply || skb->pkt_type == PACKET_HOST) + if (!reply) return 0; if (skb->protocol == htons(ETH_P_IP)) @@ -451,7 +451,7 @@ static const struct nla_policy geneve_opt_policy[LWTUNNEL_IP_OPT_GENEVE_MAX + 1] = { [LWTUNNEL_IP_OPT_GENEVE_CLASS] = { .type = NLA_U16 }, [LWTUNNEL_IP_OPT_GENEVE_TYPE] = { .type = NLA_U8 }, - [LWTUNNEL_IP_OPT_GENEVE_DATA] = { .type = NLA_BINARY, .len = 128 }, + [LWTUNNEL_IP_OPT_GENEVE_DATA] = { .type = NLA_BINARY, .len = 127 }, }; static const struct nla_policy diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index d0bffcfa56d8..2742cc7602bb 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1625,12 +1625,12 @@ static bool udp_skb_has_head_state(struct sk_buff *skb) } /* fully reclaim rmem/fwd memory allocated for skb */ -static void udp_rmem_release(struct sock *sk, int size, int partial, - bool rx_queue_lock_held) +static void udp_rmem_release(struct sock *sk, unsigned int size, + int partial, bool rx_queue_lock_held) { struct udp_sock *up = udp_sk(sk); struct sk_buff_head *sk_queue; - int amt; + unsigned int amt; if (likely(partial)) { up->forward_deficit += size; @@ -1650,10 +1650,8 @@ static void udp_rmem_release(struct sock *sk, int size, int partial, if (!rx_queue_lock_held) spin_lock(&sk_queue->lock); - - sk_forward_alloc_add(sk, size); - amt = (sk->sk_forward_alloc - partial) & ~(PAGE_SIZE - 1); - sk_forward_alloc_add(sk, -amt); + amt = (size + sk->sk_forward_alloc - partial) & ~(PAGE_SIZE - 1); + sk_forward_alloc_add(sk, size - amt); if (amt) __sk_mem_reduce_allocated(sk, amt >> PAGE_SHIFT); @@ -1725,17 +1723,25 @@ static int udp_rmem_schedule(struct sock *sk, int size) int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb) { struct sk_buff_head *list = &sk->sk_receive_queue; - int rmem, err = -ENOMEM; + unsigned int rmem, rcvbuf; spinlock_t *busy = NULL; - int size, rcvbuf; + int size, err = -ENOMEM; - /* Immediately drop when the receive queue is full. - * Always allow at least one packet. - */ rmem = atomic_read(&sk->sk_rmem_alloc); rcvbuf = READ_ONCE(sk->sk_rcvbuf); - if (rmem > rcvbuf) - goto drop; + size = skb->truesize; + + /* Immediately drop when the receive queue is full. + * Cast to unsigned int performs the boundary check for INT_MAX. + */ + if (rmem + size > rcvbuf) { + if (rcvbuf > INT_MAX >> 1) + goto drop; + + /* Always allow at least one packet for small buffer. */ + if (rmem > rcvbuf) + goto drop; + } /* Under mem pressure, it might be helpful to help udp_recvmsg() * having linear skbs : @@ -1745,10 +1751,10 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb) */ if (rmem > (rcvbuf >> 1)) { skb_condense(skb); - + size = skb->truesize; busy = busylock_acquire(sk); } - size = skb->truesize; + udp_set_dev_scratch(skb); atomic_add(size, &sk->sk_rmem_alloc); @@ -1835,7 +1841,7 @@ EXPORT_IPV6_MOD_GPL(skb_consume_udp); static struct sk_buff *__first_packet_length(struct sock *sk, struct sk_buff_head *rcvq, - int *total) + unsigned int *total) { struct sk_buff *skb; @@ -1868,8 +1874,8 @@ static int first_packet_length(struct sock *sk) { struct sk_buff_head *rcvq = &udp_sk(sk)->reader_queue; struct sk_buff_head *sk_queue = &sk->sk_receive_queue; + unsigned int total = 0; struct sk_buff *skb; - int total = 0; int res; spin_lock_bh(&rcvq->lock); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index ac8cc1076536..c3b908fccbc1 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -80,6 +80,7 @@ #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/l3mdev.h> +#include <net/netdev_lock.h> #include <linux/if_tunnel.h> #include <linux/rtnetlink.h> #include <linux/netconf.h> @@ -377,6 +378,7 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev) int err = -ENOMEM; ASSERT_RTNL(); + netdev_ops_assert_locked(dev); if (dev->mtu < IPV6_MIN_MTU && dev != blackhole_netdev) return ERR_PTR(-EINVAL); @@ -402,7 +404,7 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev) return ERR_PTR(err); } if (ndev->cnf.forwarding) - dev_disable_lro(dev); + netif_disable_lro(dev); /* We refer to the device */ netdev_hold(dev, &ndev->dev_tracker, GFP_KERNEL); @@ -3152,10 +3154,12 @@ int addrconf_add_ifaddr(struct net *net, void __user *arg) rtnl_net_lock(net); dev = __dev_get_by_index(net, ireq.ifr6_ifindex); + netdev_lock_ops(dev); if (dev) err = inet6_addr_add(net, dev, &cfg, 0, 0, NULL); else err = -ENODEV; + netdev_unlock_ops(dev); rtnl_net_unlock(net); return err; } @@ -5026,9 +5030,10 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, if (!dev) { NL_SET_ERR_MSG_MOD(extack, "Unable to find the interface"); err = -ENODEV; - goto unlock; + goto unlock_rtnl; } + netdev_lock_ops(dev); idev = ipv6_find_idev(dev); if (IS_ERR(idev)) { err = PTR_ERR(idev); @@ -5065,6 +5070,8 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, in6_ifa_put(ifa); unlock: + netdev_unlock_ops(dev); +unlock_rtnl: rtnl_net_unlock(net); return err; @@ -5784,6 +5791,27 @@ static void snmp6_fill_stats(u64 *stats, struct inet6_dev *idev, int attrtype, } } +static int inet6_fill_ifla6_stats_attrs(struct sk_buff *skb, + struct inet6_dev *idev) +{ + struct nlattr *nla; + + nla = nla_reserve(skb, IFLA_INET6_STATS, IPSTATS_MIB_MAX * sizeof(u64)); + if (!nla) + goto nla_put_failure; + snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_STATS, nla_len(nla)); + + nla = nla_reserve(skb, IFLA_INET6_ICMP6STATS, ICMP6_MIB_MAX * sizeof(u64)); + if (!nla) + goto nla_put_failure; + snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_ICMP6STATS, nla_len(nla)); + + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + static int inet6_fill_ifla6_attrs(struct sk_buff *skb, struct inet6_dev *idev, u32 ext_filter_mask) { @@ -5806,18 +5834,10 @@ static int inet6_fill_ifla6_attrs(struct sk_buff *skb, struct inet6_dev *idev, /* XXX - MC not implemented */ - if (ext_filter_mask & RTEXT_FILTER_SKIP_STATS) - return 0; - - nla = nla_reserve(skb, IFLA_INET6_STATS, IPSTATS_MIB_MAX * sizeof(u64)); - if (!nla) - goto nla_put_failure; - snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_STATS, nla_len(nla)); - - nla = nla_reserve(skb, IFLA_INET6_ICMP6STATS, ICMP6_MIB_MAX * sizeof(u64)); - if (!nla) - goto nla_put_failure; - snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_ICMP6STATS, nla_len(nla)); + if (!(ext_filter_mask & RTEXT_FILTER_SKIP_STATS)) { + if (inet6_fill_ifla6_stats_attrs(skb, idev) < 0) + goto nla_put_failure; + } nla = nla_reserve(skb, IFLA_INET6_TOKEN, sizeof(struct in6_addr)); if (!nla) @@ -6503,7 +6523,9 @@ static int addrconf_sysctl_addr_gen_mode(const struct ctl_table *ctl, int write, if (idev->cnf.addr_gen_mode != new_val) { WRITE_ONCE(idev->cnf.addr_gen_mode, new_val); + netdev_lock_ops(idev->dev); addrconf_init_auto_addrs(idev->dev); + netdev_unlock_ops(idev->dev); } } else if (&net->ipv6.devconf_all->addr_gen_mode == ctl->data) { struct net_device *dev; @@ -6515,7 +6537,9 @@ static int addrconf_sysctl_addr_gen_mode(const struct ctl_table *ctl, int write, idev->cnf.addr_gen_mode != new_val) { WRITE_ONCE(idev->cnf.addr_gen_mode, new_val); + netdev_lock_ops(idev->dev); addrconf_init_auto_addrs(idev->dev); + netdev_unlock_ops(idev->dev); } } } diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c index dbcea9fee626..62618a058b8f 100644 --- a/net/ipv6/calipso.c +++ b/net/ipv6/calipso.c @@ -1072,8 +1072,13 @@ static int calipso_sock_getattr(struct sock *sk, struct ipv6_opt_hdr *hop; int opt_len, len, ret_val = -ENOMSG, offset; unsigned char *opt; - struct ipv6_txoptions *txopts = txopt_get(inet6_sk(sk)); + struct ipv6_pinfo *pinfo = inet6_sk(sk); + struct ipv6_txoptions *txopts; + + if (!pinfo) + return -EAFNOSUPPORT; + txopts = txopt_get(pinfo); if (!txopts || !txopts->hopopt) goto done; @@ -1125,8 +1130,13 @@ static int calipso_sock_setattr(struct sock *sk, { int ret_val; struct ipv6_opt_hdr *old, *new; - struct ipv6_txoptions *txopts = txopt_get(inet6_sk(sk)); + struct ipv6_pinfo *pinfo = inet6_sk(sk); + struct ipv6_txoptions *txopts; + + if (!pinfo) + return -EAFNOSUPPORT; + txopts = txopt_get(pinfo); old = NULL; if (txopts) old = txopts->hopopt; @@ -1153,8 +1163,13 @@ static int calipso_sock_setattr(struct sock *sk, static void calipso_sock_delattr(struct sock *sk) { struct ipv6_opt_hdr *new_hop; - struct ipv6_txoptions *txopts = txopt_get(inet6_sk(sk)); + struct ipv6_pinfo *pinfo = inet6_sk(sk); + struct ipv6_txoptions *txopts; + + if (!pinfo) + return; + txopts = txopt_get(pinfo); if (!txopts || !txopts->hopopt) goto done; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index c3406a0d45bd..ab12b816ab94 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -412,12 +412,37 @@ static bool rt6_check_expired(const struct rt6_info *rt) return false; } +static struct fib6_info * +rt6_multipath_first_sibling_rcu(const struct fib6_info *rt) +{ + struct fib6_info *iter; + struct fib6_node *fn; + + fn = rcu_dereference(rt->fib6_node); + if (!fn) + goto out; + iter = rcu_dereference(fn->leaf); + if (!iter) + goto out; + + while (iter) { + if (iter->fib6_metric == rt->fib6_metric && + rt6_qualify_for_ecmp(iter)) + return iter; + iter = rcu_dereference(iter->fib6_next); + } + +out: + return NULL; +} + void fib6_select_path(const struct net *net, struct fib6_result *res, struct flowi6 *fl6, int oif, bool have_oif_match, const struct sk_buff *skb, int strict) { - struct fib6_info *match = res->f6i; + struct fib6_info *first, *match = res->f6i; struct fib6_info *sibling; + int hash; if (!match->nh && (!match->fib6_nsiblings || have_oif_match)) goto out; @@ -440,16 +465,25 @@ void fib6_select_path(const struct net *net, struct fib6_result *res, return; } - if (fl6->mp_hash <= atomic_read(&match->fib6_nh->fib_nh_upper_bound)) + first = rt6_multipath_first_sibling_rcu(match); + if (!first) goto out; - list_for_each_entry_rcu(sibling, &match->fib6_siblings, + hash = fl6->mp_hash; + if (hash <= atomic_read(&first->fib6_nh->fib_nh_upper_bound) && + rt6_score_route(first->fib6_nh, first->fib6_flags, oif, + strict) >= 0) { + match = first; + goto out; + } + + list_for_each_entry_rcu(sibling, &first->fib6_siblings, fib6_siblings) { const struct fib6_nh *nh = sibling->fib6_nh; int nh_upper_bound; nh_upper_bound = atomic_read(&nh->fib_nh_upper_bound); - if (fl6->mp_hash > nh_upper_bound) + if (hash > nh_upper_bound) continue; if (rt6_score_route(nh, sibling->fib6_flags, oif, strict) < 0) break; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index c2df81b7e950..a133e1c175ce 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2839,11 +2839,11 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, err = nft_netdev_register_hooks(ctx->net, &hook.list); if (err < 0) goto err_hooks; + + unregister = true; } } - unregister = true; - if (nla[NFTA_CHAIN_COUNTERS]) { if (!nft_is_base_chain(chain)) { err = -EOPNOTSUPP; diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 8bfac4185ac7..abb0c8ec6371 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -309,7 +309,8 @@ static bool nft_rhash_expr_needs_gc_run(const struct nft_set *set, nft_setelem_expr_foreach(expr, elem_expr, size) { if (expr->ops->gc && - expr->ops->gc(read_pnet(&set->net), expr)) + expr->ops->gc(read_pnet(&set->net), expr) && + set->flags & NFT_SET_EVAL) return true; } diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c index 681301b46aa4..0c63d1367cf7 100644 --- a/net/netfilter/nft_tunnel.c +++ b/net/netfilter/nft_tunnel.c @@ -335,13 +335,13 @@ static int nft_tunnel_obj_erspan_init(const struct nlattr *attr, static const struct nla_policy nft_tunnel_opts_geneve_policy[NFTA_TUNNEL_KEY_GENEVE_MAX + 1] = { [NFTA_TUNNEL_KEY_GENEVE_CLASS] = { .type = NLA_U16 }, [NFTA_TUNNEL_KEY_GENEVE_TYPE] = { .type = NLA_U8 }, - [NFTA_TUNNEL_KEY_GENEVE_DATA] = { .type = NLA_BINARY, .len = 128 }, + [NFTA_TUNNEL_KEY_GENEVE_DATA] = { .type = NLA_BINARY, .len = 127 }, }; static int nft_tunnel_obj_geneve_init(const struct nlattr *attr, struct nft_tunnel_opts *opts) { - struct geneve_opt *opt = (struct geneve_opt *)opts->u.data + opts->len; + struct geneve_opt *opt = (struct geneve_opt *)(opts->u.data + opts->len); struct nlattr *tb[NFTA_TUNNEL_KEY_GENEVE_MAX + 1]; int err, data_len; @@ -625,7 +625,7 @@ static int nft_tunnel_opts_dump(struct sk_buff *skb, if (!inner) goto failure; while (opts->len > offset) { - opt = (struct geneve_opt *)opts->u.data + offset; + opt = (struct geneve_opt *)(opts->u.data + offset); if (nla_put_be16(skb, NFTA_TUNNEL_KEY_GENEVE_CLASS, opt->opt_class) || nla_put_u8(skb, NFTA_TUNNEL_KEY_GENEVE_TYPE, diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 704c858cf209..61fea7baae5d 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -947,12 +947,6 @@ static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port, pskb_trim(skb, ovs_mac_header_len(key)); } - /* Need to set the pkt_type to involve the routing layer. The - * packet movement through the OVS datapath doesn't generally - * use routing, but this is needed for tunnel cases. - */ - skb->pkt_type = PACKET_OUTGOING; - if (likely(!mru || (skb->len <= mru + vport->dev->hard_header_len))) { ovs_vport_send(vport, skb, ovs_key_mac_proto(key)); diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index ae5dea7c48a8..2cef4b08befb 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -68,7 +68,7 @@ geneve_opt_policy[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX + 1] = { [TCA_TUNNEL_KEY_ENC_OPT_GENEVE_CLASS] = { .type = NLA_U16 }, [TCA_TUNNEL_KEY_ENC_OPT_GENEVE_TYPE] = { .type = NLA_U8 }, [TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA] = { .type = NLA_BINARY, - .len = 128 }, + .len = 127 }, }; static const struct nla_policy diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 03505673d523..099ff6a3e1f5 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -766,7 +766,7 @@ geneve_opt_policy[TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX + 1] = { [TCA_FLOWER_KEY_ENC_OPT_GENEVE_CLASS] = { .type = NLA_U16 }, [TCA_FLOWER_KEY_ENC_OPT_GENEVE_TYPE] = { .type = NLA_U8 }, [TCA_FLOWER_KEY_ENC_OPT_GENEVE_DATA] = { .type = NLA_BINARY, - .len = 128 }, + .len = 127 }, }; static const struct nla_policy diff --git a/net/sched/sch_skbprio.c b/net/sched/sch_skbprio.c index 20ff7386b74b..f485f62ab721 100644 --- a/net/sched/sch_skbprio.c +++ b/net/sched/sch_skbprio.c @@ -123,8 +123,6 @@ static int skbprio_enqueue(struct sk_buff *skb, struct Qdisc *sch, /* Check to update highest and lowest priorities. */ if (skb_queue_empty(lp_qdisc)) { if (q->lowest_prio == q->highest_prio) { - /* The incoming packet is the only packet in queue. */ - BUG_ON(sch->q.qlen != 1); q->lowest_prio = prio; q->highest_prio = prio; } else { @@ -156,7 +154,6 @@ static struct sk_buff *skbprio_dequeue(struct Qdisc *sch) /* Update highest priority field. */ if (skb_queue_empty(hpq)) { if (q->lowest_prio == q->highest_prio) { - BUG_ON(sch->q.qlen); q->highest_prio = 0; q->lowest_prio = SKBPRIO_MAX_PRIORITY - 1; } else { diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index 8e1e97be4df7..ee3eac338a9d 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -525,6 +525,8 @@ static int proc_sctp_do_auth(const struct ctl_table *ctl, int write, return ret; } +static DEFINE_MUTEX(sctp_sysctl_mutex); + static int proc_sctp_do_udp_port(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { @@ -549,6 +551,7 @@ static int proc_sctp_do_udp_port(const struct ctl_table *ctl, int write, if (new_value > max || new_value < min) return -EINVAL; + mutex_lock(&sctp_sysctl_mutex); net->sctp.udp_port = new_value; sctp_udp_sock_stop(net); if (new_value) { @@ -561,6 +564,7 @@ static int proc_sctp_do_udp_port(const struct ctl_table *ctl, int write, lock_sock(sk); sctp_sk(sk)->udp_port = htons(net->sctp.udp_port); release_sock(sk); + mutex_unlock(&sctp_sysctl_mutex); } return ret; diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 7e3db87ae433..fc6afbc8d680 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1551,7 +1551,11 @@ static int vsock_connect(struct socket *sock, struct sockaddr *addr, timeout = vsk->connect_timeout; prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); - while (sk->sk_state != TCP_ESTABLISHED && sk->sk_err == 0) { + /* If the socket is already closing or it is in an error state, there + * is no point in waiting. + */ + while (sk->sk_state != TCP_ESTABLISHED && + sk->sk_state != TCP_CLOSING && sk->sk_err == 0) { if (flags & O_NONBLOCK) { /* If we're not going to block, we schedule a timeout * function to generate a timeout on the connection diff --git a/tools/testing/selftests/drivers/net/hw/iou-zcrx.py b/tools/testing/selftests/drivers/net/hw/iou-zcrx.py index d301d9b356f7..9f271ab6ec04 100755 --- a/tools/testing/selftests/drivers/net/hw/iou-zcrx.py +++ b/tools/testing/selftests/drivers/net/hw/iou-zcrx.py @@ -27,7 +27,7 @@ def _set_flow_rule(cfg, chan): def test_zcrx(cfg) -> None: - cfg.require_v6() + cfg.require_ipver('6') combined_chans = _get_combined_channels(cfg) if combined_chans < 2: @@ -40,7 +40,7 @@ def test_zcrx(cfg) -> None: flow_rule_id = _set_flow_rule(cfg, combined_chans - 1) rx_cmd = f"{cfg.bin_remote} -s -p 9999 -i {cfg.ifname} -q {combined_chans - 1}" - tx_cmd = f"{cfg.bin_local} -c -h {cfg.remote_v6} -p 9999 -l 12840" + tx_cmd = f"{cfg.bin_local} -c -h {cfg.remote_addr_v['6']} -p 9999 -l 12840" with bkg(rx_cmd, host=cfg.remote, exit_wait=True): wait_port_listen(9999, proto="tcp", host=cfg.remote) cmd(tx_cmd) @@ -51,7 +51,7 @@ def test_zcrx(cfg) -> None: def test_zcrx_oneshot(cfg) -> None: - cfg.require_v6() + cfg.require_ipver('6') combined_chans = _get_combined_channels(cfg) if combined_chans < 2: @@ -64,7 +64,7 @@ def test_zcrx_oneshot(cfg) -> None: flow_rule_id = _set_flow_rule(cfg, combined_chans - 1) rx_cmd = f"{cfg.bin_remote} -s -p 9999 -i {cfg.ifname} -q {combined_chans - 1} -o 4" - tx_cmd = f"{cfg.bin_local} -c -h {cfg.remote_v6} -p 9999 -l 4096 -z 16384" + tx_cmd = f"{cfg.bin_local} -c -h {cfg.remote_addr_v['6']} -p 9999 -l 4096 -z 16384" with bkg(rx_cmd, host=cfg.remote, exit_wait=True): wait_port_listen(9999, proto="tcp", host=cfg.remote) cmd(tx_cmd) diff --git a/tools/testing/selftests/net/amt.sh b/tools/testing/selftests/net/amt.sh index d458b45c775b..3ef209cacb8e 100755 --- a/tools/testing/selftests/net/amt.sh +++ b/tools/testing/selftests/net/amt.sh @@ -194,15 +194,21 @@ test_remote_ip() send_mcast_torture4() { - ip netns exec "${SOURCE}" bash -c \ - 'cat /dev/urandom | head -c 1G | nc -w 1 -u 239.0.0.1 4001' + for i in `seq 10`; do + ip netns exec "${SOURCE}" bash -c \ + 'cat /dev/urandom | head -c 100M | nc -w 1 -u 239.0.0.1 4001' + echo -n "." + done } send_mcast_torture6() { - ip netns exec "${SOURCE}" bash -c \ - 'cat /dev/urandom | head -c 1G | nc -w 1 -u ff0e::5:6 6001' + for i in `seq 10`; do + ip netns exec "${SOURCE}" bash -c \ + 'cat /dev/urandom | head -c 100M | nc -w 1 -u ff0e::5:6 6001' + echo -n "." + done } check_features() @@ -278,10 +284,12 @@ wait $pid || err=$? if [ $err -eq 1 ]; then ERR=1 fi +printf "TEST: %-50s" "IPv4 amt traffic forwarding torture" send_mcast_torture4 -printf "TEST: %-60s [ OK ]\n" "IPv4 amt traffic forwarding torture" +printf " [ OK ]\n" +printf "TEST: %-50s" "IPv6 amt traffic forwarding torture" send_mcast_torture6 -printf "TEST: %-60s [ OK ]\n" "IPv6 amt traffic forwarding torture" +printf " [ OK ]\n" sleep 5 if [ "${ERR}" -eq 1 ]; then echo "Some tests failed." >&2 diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index 975be4fdbcdb..701905eeff66 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -222,6 +222,31 @@ setup_ns() NS_LIST+=("${ns_list[@]}") } +# Create netdevsim with given id and net namespace. +create_netdevsim() { + local id="$1" + local ns="$2" + + modprobe netdevsim &> /dev/null + udevadm settle + + echo "$id 1" | ip netns exec $ns tee /sys/bus/netdevsim/new_device >/dev/null + local dev=$(ip netns exec $ns ls /sys/bus/netdevsim/devices/netdevsim$id/net) + ip -netns $ns link set dev $dev name nsim$id + ip -netns $ns link set dev nsim$id up + + echo nsim$id +} + +# Remove netdevsim with given id. +cleanup_netdevsim() { + local id="$1" + + if [ -d "/sys/bus/netdevsim/devices/netdevsim$id/net" ]; then + echo "$id" > /sys/bus/netdevsim/del_device + fi +} + tc_rule_stats_get() { local dev=$1; shift diff --git a/tools/testing/selftests/net/netns-name.sh b/tools/testing/selftests/net/netns-name.sh index 0be1905d1f2f..38871bdef67f 100755 --- a/tools/testing/selftests/net/netns-name.sh +++ b/tools/testing/selftests/net/netns-name.sh @@ -7,10 +7,12 @@ set -o pipefail DEV=dummy-dev0 DEV2=dummy-dev1 ALT_NAME=some-alt-name +NSIM_ADDR=2025 RET_CODE=0 cleanup() { + cleanup_netdevsim $NSIM_ADDR cleanup_ns $NS $test_ns } @@ -25,12 +27,15 @@ setup_ns NS test_ns # # Test basic move without a rename +# Use netdevsim because it has extra asserts for notifiers. # -ip -netns $NS link add name $DEV type dummy || fail -ip -netns $NS link set dev $DEV netns $test_ns || + +nsim=$(create_netdevsim $NSIM_ADDR $NS) +ip -netns $NS link set dev $nsim netns $test_ns || fail "Can't perform a netns move" -ip -netns $test_ns link show dev $DEV >> /dev/null || fail "Device not found after move" -ip -netns $test_ns link del $DEV || fail +ip -netns $test_ns link show dev $nsim >> /dev/null || + fail "Device not found after move" +cleanup_netdevsim $NSIM_ADDR # # Test move with a conflict diff --git a/tools/testing/selftests/net/rtnetlink.py b/tools/testing/selftests/net/rtnetlink.py index 80950888800b..e9ad5e88da97 100755 --- a/tools/testing/selftests/net/rtnetlink.py +++ b/tools/testing/selftests/net/rtnetlink.py @@ -12,10 +12,10 @@ def dump_mcaddr_check(rtnl: RtnlAddrFamily) -> None: At least the loopback interface should have this address. """ - addresses = rtnl.getmaddrs({"ifa-family": socket.AF_INET}, dump=True) + addresses = rtnl.getmulticast({"ifa-family": socket.AF_INET}, dump=True) all_host_multicasts = [ - addr for addr in addresses if addr['ifa-multicast'] == IPV4_ALL_HOSTS_MULTICAST + addr for addr in addresses if addr['multicast'] == IPV4_ALL_HOSTS_MULTICAST ] ksft_ge(len(all_host_multicasts), 1, diff --git a/tools/testing/selftests/net/tcp_ao/self-connect.c b/tools/testing/selftests/net/tcp_ao/self-connect.c index 73b2f2276f3f..2c73bea698a6 100644 --- a/tools/testing/selftests/net/tcp_ao/self-connect.c +++ b/tools/testing/selftests/net/tcp_ao/self-connect.c @@ -16,6 +16,9 @@ static void __setup_lo_intf(const char *lo_intf, if (link_set_up(lo_intf)) test_error("Failed to bring %s up", lo_intf); + + if (ip_route_add(lo_intf, TEST_FAMILY, local_addr, local_addr)) + test_error("Failed to add a local route %s", lo_intf); } static void setup_lo_intf(const char *lo_intf) diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/nat.json b/tools/testing/selftests/tc-testing/tc-tests/actions/nat.json index ee2792998c89..4f21aeb8a3fb 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/nat.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/nat.json @@ -305,7 +305,7 @@ "cmdUnderTest": "$TC actions add action nat ingress default 10.10.10.1 index 12", "expExitCode": "0", "verifyCmd": "$TC actions get action nat index 12", - "matchPattern": "action order [0-9]+: nat ingress 0.0.0.0/32 10.10.10.1 pass.*index 12 ref", + "matchPattern": "action order [0-9]+: nat ingress 0.0.0.0/0 10.10.10.1 pass.*index 12 ref", "matchCount": "1", "teardown": [ "$TC actions flush action nat" @@ -332,7 +332,7 @@ "cmdUnderTest": "$TC actions add action nat ingress any 10.10.10.1 index 12", "expExitCode": "0", "verifyCmd": "$TC actions get action nat index 12", - "matchPattern": "action order [0-9]+: nat ingress 0.0.0.0/32 10.10.10.1 pass.*index 12 ref", + "matchPattern": "action order [0-9]+: nat ingress 0.0.0.0/0 10.10.10.1 pass.*index 12 ref", "matchCount": "1", "teardown": [ "$TC actions flush action nat" @@ -359,7 +359,7 @@ "cmdUnderTest": "$TC actions add action nat ingress all 10.10.10.1 index 12", "expExitCode": "0", "verifyCmd": "$TC actions get action nat index 12", - "matchPattern": "action order [0-9]+: nat ingress 0.0.0.0/32 10.10.10.1 pass.*index 12 ref", + "matchPattern": "action order [0-9]+: nat ingress 0.0.0.0/0 10.10.10.1 pass.*index 12 ref", "matchCount": "1", "teardown": [ "$TC actions flush action nat" @@ -548,7 +548,7 @@ "cmdUnderTest": "$TC actions add action nat egress default 20.20.20.1 pipe index 10", "expExitCode": "0", "verifyCmd": "$TC actions get action nat index 10", - "matchPattern": "action order [0-9]+: nat egress 0.0.0.0/32 20.20.20.1 pipe.*index 10 ref", + "matchPattern": "action order [0-9]+: nat egress 0.0.0.0/0 20.20.20.1 pipe.*index 10 ref", "matchCount": "1", "teardown": [ "$TC actions flush action nat" @@ -575,7 +575,7 @@ "cmdUnderTest": "$TC actions add action nat egress any 20.20.20.1 pipe index 10", "expExitCode": "0", "verifyCmd": "$TC actions get action nat index 10", - "matchPattern": "action order [0-9]+: nat egress 0.0.0.0/32 20.20.20.1 pipe.*index 10 ref", + "matchPattern": "action order [0-9]+: nat egress 0.0.0.0/0 20.20.20.1 pipe.*index 10 ref", "matchCount": "1", "teardown": [ "$TC actions flush action nat" @@ -602,7 +602,7 @@ "cmdUnderTest": "$TC actions add action nat egress all 20.20.20.1 pipe index 10", "expExitCode": "0", "verifyCmd": "$TC actions get action nat index 10", - "matchPattern": "action order [0-9]+: nat egress 0.0.0.0/32 20.20.20.1 pipe.*index 10 ref", + "matchPattern": "action order [0-9]+: nat egress 0.0.0.0/0 20.20.20.1 pipe.*index 10 ref", "matchCount": "1", "teardown": [ "$TC actions flush action nat" @@ -629,7 +629,7 @@ "cmdUnderTest": "$TC actions add action nat egress all 20.20.20.1 pipe index 10 cookie aa1bc2d3eeff112233445566778800a1", "expExitCode": "0", "verifyCmd": "$TC actions get action nat index 10", - "matchPattern": "action order [0-9]+: nat egress 0.0.0.0/32 20.20.20.1 pipe.*index 10 ref.*cookie aa1bc2d3eeff112233445566778800a1", + "matchPattern": "action order [0-9]+: nat egress 0.0.0.0/0 20.20.20.1 pipe.*index 10 ref.*cookie aa1bc2d3eeff112233445566778800a1", "matchCount": "1", "teardown": [ "$TC actions flush action nat" diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json index 9044ac054167..25454fd95537 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json +++ b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json @@ -126,5 +126,37 @@ "$TC qdisc del dev $DUMMY root handle 1: drr", "$IP addr del 10.10.10.10/24 dev $DUMMY" ] - } + }, + { + "id": "c024", + "name": "Test TBF with SKBPRIO - catch qlen corner cases", + "category": [ + "qdisc", + "tbf", + "skbprio" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.10.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY handle 1: root tbf rate 100bit burst 2000 limit 1000", + "$TC qdisc add dev $DUMMY parent 1: handle 10: skbprio limit 1", + "ping -c 1 -W 0.1 -Q 0x00 -s 1400 -I $DUMMY 10.10.10.1 > /dev/null || true", + "ping -c 1 -W 0.1 -Q 0x1c -s 1400 -I $DUMMY 10.10.10.1 > /dev/null || true", + "ping -c 1 -W 0.1 -Q 0x00 -s 1400 -I $DUMMY 10.10.10.1 > /dev/null || true", + "ping -c 1 -W 0.1 -Q 0x1c -s 1400 -I $DUMMY 10.10.10.1 > /dev/null || true", + "sleep 0.5" + ], + "cmdUnderTest": "$TC -s qdisc show dev $DUMMY", + "expExitCode": "0", + "verifyCmd": "$TC -s qdisc show dev $DUMMY | grep -A 5 'qdisc skbprio'", + "matchPattern": "dropped [1-9][0-9]*", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP addr del 10.10.10.10/24 dev $DUMMY || true" + ] + } ] |