summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2022-07-01 01:26:55 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2022-07-01 01:26:55 +0300
commit5e8379351dbde61ea383e514f0f9ecb2c047cf4e (patch)
treea6e20244de7ec91c1fd9ae6f7cb6353a28f3bc63
parent868f9f2f8e004bfe0d3935b1976f625b2924893b (diff)
parent58bf4db695287c4bb2a5fc9fc12c78fdd4c36894 (diff)
downloadlinux-5e8379351dbde61ea383e514f0f9ecb2c047cf4e.tar.xz
Merge tag 'net-5.19-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Jakub Kicinski: "Including fixes from netfilter. Current release - new code bugs: - clear msg_get_inq in __sys_recvfrom() and __copy_msghdr_from_user() - mptcp: - invoke MP_FAIL response only when needed - fix shutdown vs fallback race - consistent map handling on failure - octeon_ep: use bitwise AND Previous releases - regressions: - tipc: move bc link creation back to tipc_node_create, fix NPD Previous releases - always broken: - tcp: add a missing nf_reset_ct() in 3WHS handling to prevent socket buffered skbs from keeping refcount on the conntrack module - ipv6: take care of disable_policy when restoring routes - tun: make sure to always disable and unlink NAPI instances - phy: don't trigger state machine while in suspend - netfilter: nf_tables: avoid skb access on nf_stolen - asix: fix "can't send until first packet is send" issue - usb: asix: do not force pause frames support - nxp-nci: don't issue a zero length i2c_master_read() Misc: - ncsi: allow use of proper "mellanox" DT vendor prefix - act_api: add a message for user space if any actions were already flushed before the error was hit" * tag 'net-5.19-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (55 commits) net: dsa: felix: fix race between reading PSFP stats and port stats selftest: tun: add test for NAPI dismantle net: tun: avoid disabling NAPI twice net: sparx5: mdb add/del handle non-sparx5 devices net: sfp: fix memory leak in sfp_probe() mlxsw: spectrum_router: Fix rollback in tunnel next hop init net: rose: fix UAF bugs caused by timer handler net: usb: ax88179_178a: Fix packet receiving net: bonding: fix use-after-free after 802.3ad slave unbind ipv6: fix lockdep splat in in6_dump_addrs() net: phy: ax88772a: fix lost pause advertisement configuration net: phy: Don't trigger state machine while in suspend usbnet: fix memory allocation in helpers selftests net: fix kselftest net fatal error NFC: nxp-nci: don't print header length mismatch on i2c error NFC: nxp-nci: Don't issue a zero length i2c_master_read() net: tipc: fix possible refcount leak in tipc_sk_create() nfc: nfcmrvl: Fix irq_of_parse_and_map() return value net: ipv6: unexport __init-annotated seg6_hmac_net_init() ipv6/sit: fix ipip6_tunnel_get_prl return value ...
-rw-r--r--MAINTAINERS3
-rw-r--r--drivers/net/bonding/bond_3ad.c3
-rw-r--r--drivers/net/bonding/bond_alb.c2
-rw-r--r--drivers/net/dsa/bcm_sf2.c5
-rw-r--r--drivers/net/dsa/hirschmann/hellcreek_ptp.c1
-rw-r--r--drivers/net/dsa/ocelot/felix_vsc9959.c4
-rw-r--r--drivers/net/ethernet/marvell/octeon_ep/octep_regs_cn9k_pf.h2
-rw-r--r--drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c14
-rw-r--r--drivers/net/ethernet/microchip/sparx5/sparx5_switchdev.c6
-rw-r--r--drivers/net/ethernet/smsc/epic100.c4
-rw-r--r--drivers/net/phy/ax88796b.c6
-rw-r--r--drivers/net/phy/dp83822.c4
-rw-r--r--drivers/net/phy/phy.c23
-rw-r--r--drivers/net/phy/phy_device.c23
-rw-r--r--drivers/net/phy/sfp.c2
-rw-r--r--drivers/net/tun.c15
-rw-r--r--drivers/net/usb/asix.h3
-rw-r--r--drivers/net/usb/asix_common.c1
-rw-r--r--drivers/net/usb/ax88179_178a.c101
-rw-r--r--drivers/net/usb/usbnet.c4
-rw-r--r--drivers/nfc/nfcmrvl/i2c.c6
-rw-r--r--drivers/nfc/nfcmrvl/spi.c6
-rw-r--r--drivers/nfc/nxp-nci/i2c.c11
-rw-r--r--include/linux/netdevice.h2
-rw-r--r--include/linux/phy.h6
-rw-r--r--include/net/netfilter/nf_tables.h16
-rw-r--r--include/uapi/linux/mptcp.h9
-rw-r--r--net/bridge/br_netfilter_hooks.c21
-rw-r--r--net/ipv4/ip_tunnel_core.c2
-rw-r--r--net/ipv4/tcp_ipv4.c6
-rw-r--r--net/ipv6/addrconf.c8
-rw-r--r--net/ipv6/route.c9
-rw-r--r--net/ipv6/seg6_hmac.c1
-rw-r--r--net/ipv6/sit.c8
-rw-r--r--net/mptcp/options.c7
-rw-r--r--net/mptcp/pm.c10
-rw-r--r--net/mptcp/protocol.c84
-rw-r--r--net/mptcp/protocol.h24
-rw-r--r--net/mptcp/subflow.c127
-rw-r--r--net/ncsi/ncsi-manage.c3
-rw-r--r--net/netfilter/nf_tables_core.c24
-rw-r--r--net/netfilter/nf_tables_trace.c44
-rw-r--r--net/netfilter/nft_set_hash.c2
-rw-r--r--net/rose/rose_timer.c34
-rw-r--r--net/sched/act_api.c22
-rw-r--r--net/socket.c16
-rw-r--r--net/tipc/node.c41
-rw-r--r--net/tipc/socket.c1
-rw-r--r--tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c84
-rw-r--r--tools/testing/selftests/net/Makefile2
-rw-r--r--tools/testing/selftests/net/bpf/Makefile2
-rwxr-xr-xtools/testing/selftests/net/mptcp/diag.sh48
-rw-r--r--tools/testing/selftests/net/mptcp/mptcp_connect.c2
-rw-r--r--tools/testing/selftests/net/mptcp/mptcp_inq.c2
-rw-r--r--tools/testing/selftests/net/mptcp/mptcp_sockopt.c2
-rw-r--r--tools/testing/selftests/net/tun.c162
-rwxr-xr-xtools/testing/selftests/net/udpgso_bench.sh2
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/actions/gact.json77
58 files changed, 905 insertions, 254 deletions
diff --git a/MAINTAINERS b/MAINTAINERS
index fe5daf141501..d4d3f37f64eb 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -14397,9 +14397,8 @@ F: Documentation/devicetree/bindings/sound/nxp,tfa989x.yaml
F: sound/soc/codecs/tfa989x.c
NXP-NCI NFC DRIVER
-R: Charles Gorand <charles.gorand@effinnov.com>
L: linux-nfc@lists.01.org (subscribers-only)
-S: Supported
+S: Orphan
F: Documentation/devicetree/bindings/net/nfc/nxp,nci.yaml
F: drivers/nfc/nxp-nci
diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c
index a86b1f71762e..d7fb33c078e8 100644
--- a/drivers/net/bonding/bond_3ad.c
+++ b/drivers/net/bonding/bond_3ad.c
@@ -2228,7 +2228,8 @@ void bond_3ad_unbind_slave(struct slave *slave)
temp_aggregator->num_of_ports--;
if (__agg_active_ports(temp_aggregator) == 0) {
select_new_active_agg = temp_aggregator->is_active;
- ad_clear_agg(temp_aggregator);
+ if (temp_aggregator->num_of_ports == 0)
+ ad_clear_agg(temp_aggregator);
if (select_new_active_agg) {
slave_info(bond->dev, slave->dev, "Removing an active aggregator\n");
/* select new active aggregator */
diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index 303c8d32d451..007d43e46dcb 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -1302,12 +1302,12 @@ int bond_alb_initialize(struct bonding *bond, int rlb_enabled)
return res;
if (rlb_enabled) {
- bond->alb_info.rlb_enabled = 1;
res = rlb_initialize(bond);
if (res) {
tlb_deinitialize(bond);
return res;
}
+ bond->alb_info.rlb_enabled = 1;
} else {
bond->alb_info.rlb_enabled = 0;
}
diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index 87e81c636339..be0edfa093d0 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -878,6 +878,11 @@ static void bcm_sf2_sw_mac_link_up(struct dsa_switch *ds, int port,
if (duplex == DUPLEX_FULL)
reg |= DUPLX_MODE;
+ if (tx_pause)
+ reg |= TXFLOW_CNTL;
+ if (rx_pause)
+ reg |= RXFLOW_CNTL;
+
core_writel(priv, reg, offset);
}
diff --git a/drivers/net/dsa/hirschmann/hellcreek_ptp.c b/drivers/net/dsa/hirschmann/hellcreek_ptp.c
index 2572c6087bb5..b28baab6d56a 100644
--- a/drivers/net/dsa/hirschmann/hellcreek_ptp.c
+++ b/drivers/net/dsa/hirschmann/hellcreek_ptp.c
@@ -300,6 +300,7 @@ static int hellcreek_led_setup(struct hellcreek *hellcreek)
const char *label, *state;
int ret = -EINVAL;
+ of_node_get(hellcreek->dev->of_node);
leds = of_find_node_by_name(hellcreek->dev->of_node, "leds");
if (!leds) {
dev_err(hellcreek->dev, "No LEDs specified in device tree!\n");
diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c
index 570d0204b7be..9c27b9b0128d 100644
--- a/drivers/net/dsa/ocelot/felix_vsc9959.c
+++ b/drivers/net/dsa/ocelot/felix_vsc9959.c
@@ -1886,6 +1886,8 @@ static void vsc9959_psfp_sgi_table_del(struct ocelot *ocelot,
static void vsc9959_psfp_counters_get(struct ocelot *ocelot, u32 index,
struct felix_stream_filter_counters *counters)
{
+ mutex_lock(&ocelot->stats_lock);
+
ocelot_rmw(ocelot, SYS_STAT_CFG_STAT_VIEW(index),
SYS_STAT_CFG_STAT_VIEW_M,
SYS_STAT_CFG);
@@ -1900,6 +1902,8 @@ static void vsc9959_psfp_counters_get(struct ocelot *ocelot, u32 index,
SYS_STAT_CFG_STAT_VIEW(index) |
SYS_STAT_CFG_STAT_CLEAR_SHOT(0x10),
SYS_STAT_CFG);
+
+ mutex_unlock(&ocelot->stats_lock);
}
static int vsc9959_psfp_filter_add(struct ocelot *ocelot, int port,
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_regs_cn9k_pf.h b/drivers/net/ethernet/marvell/octeon_ep/octep_regs_cn9k_pf.h
index cc51149790ff..3d5d39a52fe6 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_regs_cn9k_pf.h
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_regs_cn9k_pf.h
@@ -52,7 +52,7 @@
#define CN93_SDP_EPF_RINFO_SRN(val) ((val) & 0xFF)
#define CN93_SDP_EPF_RINFO_RPVF(val) (((val) >> 32) & 0xF)
-#define CN93_SDP_EPF_RINFO_NVFS(val) (((val) >> 48) && 0xFF)
+#define CN93_SDP_EPF_RINFO_NVFS(val) (((val) >> 48) & 0xFF)
/* SDP Function select */
#define CN93_SDP_FUNC_SEL_EPF_BIT_POS 8
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 9dbb573d53ea..0d8a0068e4ca 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -4415,6 +4415,8 @@ static int mlxsw_sp_nexthop4_init(struct mlxsw_sp *mlxsw_sp,
return 0;
err_nexthop_neigh_init:
+ list_del(&nh->router_list_node);
+ mlxsw_sp_nexthop_counter_free(mlxsw_sp, nh);
mlxsw_sp_nexthop_remove(mlxsw_sp, nh);
return err;
}
@@ -6740,6 +6742,7 @@ static int mlxsw_sp_nexthop6_init(struct mlxsw_sp *mlxsw_sp,
const struct fib6_info *rt)
{
struct net_device *dev = rt->fib6_nh->fib_nh_dev;
+ int err;
nh->nhgi = nh_grp->nhgi;
nh->nh_weight = rt->fib6_nh->fib_nh_weight;
@@ -6755,7 +6758,16 @@ static int mlxsw_sp_nexthop6_init(struct mlxsw_sp *mlxsw_sp,
return 0;
nh->ifindex = dev->ifindex;
- return mlxsw_sp_nexthop_type_init(mlxsw_sp, nh, dev);
+ err = mlxsw_sp_nexthop_type_init(mlxsw_sp, nh, dev);
+ if (err)
+ goto err_nexthop_type_init;
+
+ return 0;
+
+err_nexthop_type_init:
+ list_del(&nh->router_list_node);
+ mlxsw_sp_nexthop_counter_free(mlxsw_sp, nh);
+ return err;
}
static void mlxsw_sp_nexthop6_fini(struct mlxsw_sp *mlxsw_sp,
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_switchdev.c b/drivers/net/ethernet/microchip/sparx5/sparx5_switchdev.c
index 3429660cd2e5..5edc8b7176c8 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_switchdev.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_switchdev.c
@@ -396,6 +396,9 @@ static int sparx5_handle_port_mdb_add(struct net_device *dev,
u32 mact_entry;
int res, err;
+ if (!sparx5_netdevice_check(dev))
+ return -EOPNOTSUPP;
+
if (netif_is_bridge_master(v->obj.orig_dev)) {
sparx5_mact_learn(spx5, PGID_CPU, v->addr, v->vid);
return 0;
@@ -466,6 +469,9 @@ static int sparx5_handle_port_mdb_del(struct net_device *dev,
u32 mact_entry, res, pgid_entry[3];
int err;
+ if (!sparx5_netdevice_check(dev))
+ return -EOPNOTSUPP;
+
if (netif_is_bridge_master(v->obj.orig_dev)) {
sparx5_mact_forget(spx5, v->addr, v->vid);
return 0;
diff --git a/drivers/net/ethernet/smsc/epic100.c b/drivers/net/ethernet/smsc/epic100.c
index a0654e88444c..0329caf63279 100644
--- a/drivers/net/ethernet/smsc/epic100.c
+++ b/drivers/net/ethernet/smsc/epic100.c
@@ -1515,14 +1515,14 @@ static void epic_remove_one(struct pci_dev *pdev)
struct net_device *dev = pci_get_drvdata(pdev);
struct epic_private *ep = netdev_priv(dev);
+ unregister_netdev(dev);
dma_free_coherent(&pdev->dev, TX_TOTAL_SIZE, ep->tx_ring,
ep->tx_ring_dma);
dma_free_coherent(&pdev->dev, RX_TOTAL_SIZE, ep->rx_ring,
ep->rx_ring_dma);
- unregister_netdev(dev);
pci_iounmap(pdev, ep->ioaddr);
- pci_release_regions(pdev);
free_netdev(dev);
+ pci_release_regions(pdev);
pci_disable_device(pdev);
/* pci_power_off(pdev, -1); */
}
diff --git a/drivers/net/phy/ax88796b.c b/drivers/net/phy/ax88796b.c
index 457896337505..0f1e617a26c9 100644
--- a/drivers/net/phy/ax88796b.c
+++ b/drivers/net/phy/ax88796b.c
@@ -88,8 +88,10 @@ static void asix_ax88772a_link_change_notify(struct phy_device *phydev)
/* Reset PHY, otherwise MII_LPA will provide outdated information.
* This issue is reproducible only with some link partner PHYs
*/
- if (phydev->state == PHY_NOLINK && phydev->drv->soft_reset)
- phydev->drv->soft_reset(phydev);
+ if (phydev->state == PHY_NOLINK) {
+ phy_init_hw(phydev);
+ phy_start_aneg(phydev);
+ }
}
static struct phy_driver asix_driver[] = {
diff --git a/drivers/net/phy/dp83822.c b/drivers/net/phy/dp83822.c
index e6ad3a494d32..8549e0e356c9 100644
--- a/drivers/net/phy/dp83822.c
+++ b/drivers/net/phy/dp83822.c
@@ -229,9 +229,7 @@ static int dp83822_config_intr(struct phy_device *phydev)
if (misr_status < 0)
return misr_status;
- misr_status |= (DP83822_RX_ERR_HF_INT_EN |
- DP83822_FALSE_CARRIER_HF_INT_EN |
- DP83822_LINK_STAT_INT_EN |
+ misr_status |= (DP83822_LINK_STAT_INT_EN |
DP83822_ENERGY_DET_INT_EN |
DP83822_LINK_QUAL_INT_EN);
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index ef62f357b76d..8d3ee3a6495b 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -31,6 +31,7 @@
#include <linux/io.h>
#include <linux/uaccess.h>
#include <linux/atomic.h>
+#include <linux/suspend.h>
#include <net/netlink.h>
#include <net/genetlink.h>
#include <net/sock.h>
@@ -976,6 +977,28 @@ static irqreturn_t phy_interrupt(int irq, void *phy_dat)
struct phy_driver *drv = phydev->drv;
irqreturn_t ret;
+ /* Wakeup interrupts may occur during a system sleep transition.
+ * Postpone handling until the PHY has resumed.
+ */
+ if (IS_ENABLED(CONFIG_PM_SLEEP) && phydev->irq_suspended) {
+ struct net_device *netdev = phydev->attached_dev;
+
+ if (netdev) {
+ struct device *parent = netdev->dev.parent;
+
+ if (netdev->wol_enabled)
+ pm_system_wakeup();
+ else if (device_may_wakeup(&netdev->dev))
+ pm_wakeup_dev_event(&netdev->dev, 0, true);
+ else if (parent && device_may_wakeup(parent))
+ pm_wakeup_dev_event(parent, 0, true);
+ }
+
+ phydev->irq_rerun = 1;
+ disable_irq_nosync(irq);
+ return IRQ_HANDLED;
+ }
+
mutex_lock(&phydev->lock);
ret = drv->handle_interrupt(phydev);
mutex_unlock(&phydev->lock);
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 431a8719c635..46acddd865a7 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -278,6 +278,15 @@ static __maybe_unused int mdio_bus_phy_suspend(struct device *dev)
if (phydev->mac_managed_pm)
return 0;
+ /* Wakeup interrupts may occur during the system sleep transition when
+ * the PHY is inaccessible. Set flag to postpone handling until the PHY
+ * has resumed. Wait for concurrent interrupt handler to complete.
+ */
+ if (phy_interrupt_is_valid(phydev)) {
+ phydev->irq_suspended = 1;
+ synchronize_irq(phydev->irq);
+ }
+
/* We must stop the state machine manually, otherwise it stops out of
* control, possibly with the phydev->lock held. Upon resume, netdev
* may call phy routines that try to grab the same lock, and that may
@@ -315,6 +324,20 @@ static __maybe_unused int mdio_bus_phy_resume(struct device *dev)
if (ret < 0)
return ret;
no_resume:
+ if (phy_interrupt_is_valid(phydev)) {
+ phydev->irq_suspended = 0;
+ synchronize_irq(phydev->irq);
+
+ /* Rerun interrupts which were postponed by phy_interrupt()
+ * because they occurred during the system sleep transition.
+ */
+ if (phydev->irq_rerun) {
+ phydev->irq_rerun = 0;
+ enable_irq(phydev->irq);
+ irq_wake_thread(phydev->irq, phydev);
+ }
+ }
+
if (phydev->attached_dev && phydev->adjust_link)
phy_start_machine(phydev);
diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c
index 9a5d5a10560f..e7b0e12cc75b 100644
--- a/drivers/net/phy/sfp.c
+++ b/drivers/net/phy/sfp.c
@@ -2516,7 +2516,7 @@ static int sfp_probe(struct platform_device *pdev)
platform_set_drvdata(pdev, sfp);
- err = devm_add_action(sfp->dev, sfp_cleanup, sfp);
+ err = devm_add_action_or_reset(sfp->dev, sfp_cleanup, sfp);
if (err < 0)
return err;
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 87a635aac008..259b2b84b2b3 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -273,6 +273,12 @@ static void tun_napi_init(struct tun_struct *tun, struct tun_file *tfile,
}
}
+static void tun_napi_enable(struct tun_file *tfile)
+{
+ if (tfile->napi_enabled)
+ napi_enable(&tfile->napi);
+}
+
static void tun_napi_disable(struct tun_file *tfile)
{
if (tfile->napi_enabled)
@@ -634,7 +640,8 @@ static void __tun_detach(struct tun_file *tfile, bool clean)
tun = rtnl_dereference(tfile->tun);
if (tun && clean) {
- tun_napi_disable(tfile);
+ if (!tfile->detached)
+ tun_napi_disable(tfile);
tun_napi_del(tfile);
}
@@ -653,8 +660,10 @@ static void __tun_detach(struct tun_file *tfile, bool clean)
if (clean) {
RCU_INIT_POINTER(tfile->tun, NULL);
sock_put(&tfile->sk);
- } else
+ } else {
tun_disable_queue(tun, tfile);
+ tun_napi_disable(tfile);
+ }
synchronize_net();
tun_flow_delete_by_queue(tun, tun->numqueues + 1);
@@ -727,6 +736,7 @@ static void tun_detach_all(struct net_device *dev)
sock_put(&tfile->sk);
}
list_for_each_entry_safe(tfile, tmp, &tun->disabled, next) {
+ tun_napi_del(tfile);
tun_enable_queue(tfile);
tun_queue_purge(tfile);
xdp_rxq_info_unreg(&tfile->xdp_rxq);
@@ -807,6 +817,7 @@ static int tun_attach(struct tun_struct *tun, struct file *file,
if (tfile->detached) {
tun_enable_queue(tfile);
+ tun_napi_enable(tfile);
} else {
sock_hold(&tfile->sk);
tun_napi_init(tun, tfile, napi, napi_frags);
diff --git a/drivers/net/usb/asix.h b/drivers/net/usb/asix.h
index 2c81236c6c7c..45d3cc5cc355 100644
--- a/drivers/net/usb/asix.h
+++ b/drivers/net/usb/asix.h
@@ -126,8 +126,7 @@
AX_MEDIUM_RE)
#define AX88772_MEDIUM_DEFAULT \
- (AX_MEDIUM_FD | AX_MEDIUM_RFC | \
- AX_MEDIUM_TFC | AX_MEDIUM_PS | \
+ (AX_MEDIUM_FD | AX_MEDIUM_PS | \
AX_MEDIUM_AC | AX_MEDIUM_RE)
/* AX88772 & AX88178 RX_CTL values */
diff --git a/drivers/net/usb/asix_common.c b/drivers/net/usb/asix_common.c
index 632fa6c1d5e3..b4a1b7abcfc9 100644
--- a/drivers/net/usb/asix_common.c
+++ b/drivers/net/usb/asix_common.c
@@ -431,6 +431,7 @@ void asix_adjust_link(struct net_device *netdev)
asix_write_medium_mode(dev, mode, 0);
phy_print_status(phydev);
+ usbnet_link_change(dev, phydev->link, 0);
}
int asix_write_gpio(struct usbnet *dev, u16 value, int sleep, int in_pm)
diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c
index 4704ed6f00ef..ac2d400d1d6c 100644
--- a/drivers/net/usb/ax88179_178a.c
+++ b/drivers/net/usb/ax88179_178a.c
@@ -1472,6 +1472,42 @@ static int ax88179_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
* are bundled into this buffer and where we can find an array of
* per-packet metadata (which contains elements encoded into u16).
*/
+
+ /* SKB contents for current firmware:
+ * <packet 1> <padding>
+ * ...
+ * <packet N> <padding>
+ * <per-packet metadata entry 1> <dummy header>
+ * ...
+ * <per-packet metadata entry N> <dummy header>
+ * <padding2> <rx_hdr>
+ *
+ * where:
+ * <packet N> contains pkt_len bytes:
+ * 2 bytes of IP alignment pseudo header
+ * packet received
+ * <per-packet metadata entry N> contains 4 bytes:
+ * pkt_len and fields AX_RXHDR_*
+ * <padding> 0-7 bytes to terminate at
+ * 8 bytes boundary (64-bit).
+ * <padding2> 4 bytes to make rx_hdr terminate at
+ * 8 bytes boundary (64-bit)
+ * <dummy-header> contains 4 bytes:
+ * pkt_len=0 and AX_RXHDR_DROP_ERR
+ * <rx-hdr> contains 4 bytes:
+ * pkt_cnt and hdr_off (offset of
+ * <per-packet metadata entry 1>)
+ *
+ * pkt_cnt is number of entrys in the per-packet metadata.
+ * In current firmware there is 2 entrys per packet.
+ * The first points to the packet and the
+ * second is a dummy header.
+ * This was done probably to align fields in 64-bit and
+ * maintain compatibility with old firmware.
+ * This code assumes that <dummy header> and <padding2> are
+ * optional.
+ */
+
if (skb->len < 4)
return 0;
skb_trim(skb, skb->len - 4);
@@ -1485,51 +1521,66 @@ static int ax88179_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
/* Make sure that the bounds of the metadata array are inside the SKB
* (and in front of the counter at the end).
*/
- if (pkt_cnt * 2 + hdr_off > skb->len)
+ if (pkt_cnt * 4 + hdr_off > skb->len)
return 0;
pkt_hdr = (u32 *)(skb->data + hdr_off);
/* Packets must not overlap the metadata array */
skb_trim(skb, hdr_off);
- for (; ; pkt_cnt--, pkt_hdr++) {
+ for (; pkt_cnt > 0; pkt_cnt--, pkt_hdr++) {
+ u16 pkt_len_plus_padd;
u16 pkt_len;
le32_to_cpus(pkt_hdr);
pkt_len = (*pkt_hdr >> 16) & 0x1fff;
+ pkt_len_plus_padd = (pkt_len + 7) & 0xfff8;
- if (pkt_len > skb->len)
+ /* Skip dummy header used for alignment
+ */
+ if (pkt_len == 0)
+ continue;
+
+ if (pkt_len_plus_padd > skb->len)
return 0;
/* Check CRC or runt packet */
- if (((*pkt_hdr & (AX_RXHDR_CRC_ERR | AX_RXHDR_DROP_ERR)) == 0) &&
- pkt_len >= 2 + ETH_HLEN) {
- bool last = (pkt_cnt == 0);
-
- if (last) {
- ax_skb = skb;
- } else {
- ax_skb = skb_clone(skb, GFP_ATOMIC);
- if (!ax_skb)
- return 0;
- }
- ax_skb->len = pkt_len;
- /* Skip IP alignment pseudo header */
- skb_pull(ax_skb, 2);
- skb_set_tail_pointer(ax_skb, ax_skb->len);
- ax_skb->truesize = pkt_len + sizeof(struct sk_buff);
- ax88179_rx_checksum(ax_skb, pkt_hdr);
+ if ((*pkt_hdr & (AX_RXHDR_CRC_ERR | AX_RXHDR_DROP_ERR)) ||
+ pkt_len < 2 + ETH_HLEN) {
+ dev->net->stats.rx_errors++;
+ skb_pull(skb, pkt_len_plus_padd);
+ continue;
+ }
- if (last)
- return 1;
+ /* last packet */
+ if (pkt_len_plus_padd == skb->len) {
+ skb_trim(skb, pkt_len);
- usbnet_skb_return(dev, ax_skb);
+ /* Skip IP alignment pseudo header */
+ skb_pull(skb, 2);
+
+ skb->truesize = SKB_TRUESIZE(pkt_len_plus_padd);
+ ax88179_rx_checksum(skb, pkt_hdr);
+ return 1;
}
- /* Trim this packet away from the SKB */
- if (!skb_pull(skb, (pkt_len + 7) & 0xFFF8))
+ ax_skb = skb_clone(skb, GFP_ATOMIC);
+ if (!ax_skb)
return 0;
+ skb_trim(ax_skb, pkt_len);
+
+ /* Skip IP alignment pseudo header */
+ skb_pull(ax_skb, 2);
+
+ skb->truesize = pkt_len_plus_padd +
+ SKB_DATA_ALIGN(sizeof(struct sk_buff));
+ ax88179_rx_checksum(ax_skb, pkt_hdr);
+ usbnet_skb_return(dev, ax_skb);
+
+ skb_pull(skb, pkt_len_plus_padd);
}
+
+ return 0;
}
static struct sk_buff *
diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index 1cb6dab3e2d0..e2135ab87a6e 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -2004,7 +2004,7 @@ static int __usbnet_read_cmd(struct usbnet *dev, u8 cmd, u8 reqtype,
cmd, reqtype, value, index, size);
if (size) {
- buf = kmalloc(size, GFP_KERNEL);
+ buf = kmalloc(size, GFP_NOIO);
if (!buf)
goto out;
}
@@ -2036,7 +2036,7 @@ static int __usbnet_write_cmd(struct usbnet *dev, u8 cmd, u8 reqtype,
cmd, reqtype, value, index, size);
if (data) {
- buf = kmemdup(data, size, GFP_KERNEL);
+ buf = kmemdup(data, size, GFP_NOIO);
if (!buf)
goto out;
} else {
diff --git a/drivers/nfc/nfcmrvl/i2c.c b/drivers/nfc/nfcmrvl/i2c.c
index ceef81d93ac9..01329b91d59d 100644
--- a/drivers/nfc/nfcmrvl/i2c.c
+++ b/drivers/nfc/nfcmrvl/i2c.c
@@ -167,9 +167,9 @@ static int nfcmrvl_i2c_parse_dt(struct device_node *node,
pdata->irq_polarity = IRQF_TRIGGER_RISING;
ret = irq_of_parse_and_map(node, 0);
- if (ret < 0) {
- pr_err("Unable to get irq, error: %d\n", ret);
- return ret;
+ if (!ret) {
+ pr_err("Unable to get irq\n");
+ return -EINVAL;
}
pdata->irq = ret;
diff --git a/drivers/nfc/nfcmrvl/spi.c b/drivers/nfc/nfcmrvl/spi.c
index a38e2fcdfd39..ad3359a4942c 100644
--- a/drivers/nfc/nfcmrvl/spi.c
+++ b/drivers/nfc/nfcmrvl/spi.c
@@ -115,9 +115,9 @@ static int nfcmrvl_spi_parse_dt(struct device_node *node,
}
ret = irq_of_parse_and_map(node, 0);
- if (ret < 0) {
- pr_err("Unable to get irq, error: %d\n", ret);
- return ret;
+ if (!ret) {
+ pr_err("Unable to get irq\n");
+ return -EINVAL;
}
pdata->irq = ret;
diff --git a/drivers/nfc/nxp-nci/i2c.c b/drivers/nfc/nxp-nci/i2c.c
index 7e451c10985d..ae2ba08d8ac3 100644
--- a/drivers/nfc/nxp-nci/i2c.c
+++ b/drivers/nfc/nxp-nci/i2c.c
@@ -122,7 +122,9 @@ static int nxp_nci_i2c_fw_read(struct nxp_nci_i2c_phy *phy,
skb_put_data(*skb, &header, NXP_NCI_FW_HDR_LEN);
r = i2c_master_recv(client, skb_put(*skb, frame_len), frame_len);
- if (r != frame_len) {
+ if (r < 0) {
+ goto fw_read_exit_free_skb;
+ } else if (r != frame_len) {
nfc_err(&client->dev,
"Invalid frame length: %u (expected %zu)\n",
r, frame_len);
@@ -162,8 +164,13 @@ static int nxp_nci_i2c_nci_read(struct nxp_nci_i2c_phy *phy,
skb_put_data(*skb, (void *)&header, NCI_CTRL_HDR_SIZE);
+ if (!header.plen)
+ return 0;
+
r = i2c_master_recv(client, skb_put(*skb, header.plen), header.plen);
- if (r != header.plen) {
+ if (r < 0) {
+ goto nci_read_exit_free_skb;
+ } else if (r != header.plen) {
nfc_err(&client->dev,
"Invalid frame payload length: %u (expected %u)\n",
r, header.plen);
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index f615a66c89e9..2563d30736e9 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1671,7 +1671,7 @@ enum netdev_priv_flags {
IFF_FAILOVER_SLAVE = 1<<28,
IFF_L3MDEV_RX_HANDLER = 1<<29,
IFF_LIVE_RENAME_OK = 1<<30,
- IFF_TX_SKB_NO_LINEAR = 1<<31,
+ IFF_TX_SKB_NO_LINEAR = BIT_ULL(31),
IFF_CHANGE_PROTO_DOWN = BIT_ULL(32),
};
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 508f1149665b..b09f7d36cff2 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -572,6 +572,10 @@ struct macsec_ops;
* @mdix_ctrl: User setting of crossover
* @pma_extable: Cached value of PMA/PMD Extended Abilities Register
* @interrupts: Flag interrupts have been enabled
+ * @irq_suspended: Flag indicating PHY is suspended and therefore interrupt
+ * handling shall be postponed until PHY has resumed
+ * @irq_rerun: Flag indicating interrupts occurred while PHY was suspended,
+ * requiring a rerun of the interrupt handler after resume
* @interface: enum phy_interface_t value
* @skb: Netlink message for cable diagnostics
* @nest: Netlink nest used for cable diagnostics
@@ -626,6 +630,8 @@ struct phy_device {
/* Interrupts are enabled */
unsigned interrupts:1;
+ unsigned irq_suspended:1;
+ unsigned irq_rerun:1;
enum phy_state state;
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 279ae0fff7ad..5c4e5a96a984 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -1338,24 +1338,28 @@ void nft_unregister_flowtable_type(struct nf_flowtable_type *type);
/**
* struct nft_traceinfo - nft tracing information and state
*
+ * @trace: other struct members are initialised
+ * @nf_trace: copy of skb->nf_trace before rule evaluation
+ * @type: event type (enum nft_trace_types)
+ * @skbid: hash of skb to be used as trace id
+ * @packet_dumped: packet headers sent in a previous traceinfo message
* @pkt: pktinfo currently processed
* @basechain: base chain currently processed
* @chain: chain currently processed
* @rule: rule that was evaluated
* @verdict: verdict given by rule
- * @type: event type (enum nft_trace_types)
- * @packet_dumped: packet headers sent in a previous traceinfo message
- * @trace: other struct members are initialised
*/
struct nft_traceinfo {
+ bool trace;
+ bool nf_trace;
+ bool packet_dumped;
+ enum nft_trace_types type:8;
+ u32 skbid;
const struct nft_pktinfo *pkt;
const struct nft_base_chain *basechain;
const struct nft_chain *chain;
const struct nft_rule_dp *rule;
const struct nft_verdict *verdict;
- enum nft_trace_types type;
- bool packet_dumped;
- bool trace;
};
void nft_trace_init(struct nft_traceinfo *info, const struct nft_pktinfo *pkt,
diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h
index 921963589904..dfe19bf13f4c 100644
--- a/include/uapi/linux/mptcp.h
+++ b/include/uapi/linux/mptcp.h
@@ -2,16 +2,17 @@
#ifndef _UAPI_MPTCP_H
#define _UAPI_MPTCP_H
+#ifndef __KERNEL__
+#include <netinet/in.h> /* for sockaddr_in and sockaddr_in6 */
+#include <sys/socket.h> /* for struct sockaddr */
+#endif
+
#include <linux/const.h>
#include <linux/types.h>
#include <linux/in.h> /* for sockaddr_in */
#include <linux/in6.h> /* for sockaddr_in6 */
#include <linux/socket.h> /* for sockaddr_storage and sa_family */
-#ifndef __KERNEL__
-#include <sys/socket.h> /* for struct sockaddr */
-#endif
-
#define MPTCP_SUBFLOW_FLAG_MCAP_REM _BITUL(0)
#define MPTCP_SUBFLOW_FLAG_MCAP_LOC _BITUL(1)
#define MPTCP_SUBFLOW_FLAG_JOIN_REM _BITUL(2)
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index 4fd882686b04..ff4779036649 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -1012,9 +1012,24 @@ int br_nf_hook_thresh(unsigned int hook, struct net *net,
return okfn(net, sk, skb);
ops = nf_hook_entries_get_hook_ops(e);
- for (i = 0; i < e->num_hook_entries &&
- ops[i]->priority <= NF_BR_PRI_BRNF; i++)
- ;
+ for (i = 0; i < e->num_hook_entries; i++) {
+ /* These hooks have already been called */
+ if (ops[i]->priority < NF_BR_PRI_BRNF)
+ continue;
+
+ /* These hooks have not been called yet, run them. */
+ if (ops[i]->priority > NF_BR_PRI_BRNF)
+ break;
+
+ /* take a closer look at NF_BR_PRI_BRNF. */
+ if (ops[i]->hook == br_nf_pre_routing) {
+ /* This hook diverted the skb to this function,
+ * hooks after this have not been run yet.
+ */
+ i++;
+ break;
+ }
+ }
nf_hook_state_init(&state, hook, NFPROTO_BRIDGE, indev, outdev,
sk, net, okfn);
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index 6b2dc7b2b612..cc1caab4a654 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -410,7 +410,7 @@ int skb_tunnel_check_pmtu(struct sk_buff *skb, struct dst_entry *encap_dst,
u32 mtu = dst_mtu(encap_dst) - headroom;
if ((skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) ||
- (!skb_is_gso(skb) && (skb->len - skb_mac_header_len(skb)) <= mtu))
+ (!skb_is_gso(skb) && (skb->len - skb_network_offset(skb)) <= mtu))
return 0;
skb_dst_update_pmtu_no_confirm(skb, mtu);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index fe8f23b95d32..da5a3c44c4fb 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1964,7 +1964,10 @@ process:
struct sock *nsk;
sk = req->rsk_listener;
- drop_reason = tcp_inbound_md5_hash(sk, skb,
+ if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb))
+ drop_reason = SKB_DROP_REASON_XFRM_POLICY;
+ else
+ drop_reason = tcp_inbound_md5_hash(sk, skb,
&iph->saddr, &iph->daddr,
AF_INET, dif, sdif);
if (unlikely(drop_reason)) {
@@ -2016,6 +2019,7 @@ process:
}
goto discard_and_relse;
}
+ nf_reset_ct(skb);
if (nsk == sk) {
reqsk_put(req);
tcp_v4_restore_cb(skb);
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 1b1932502e9e..49cc6587dd77 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1109,10 +1109,6 @@ ipv6_add_addr(struct inet6_dev *idev, struct ifa6_config *cfg,
goto out;
}
- if (net->ipv6.devconf_all->disable_policy ||
- idev->cnf.disable_policy)
- f6i->dst_nopolicy = true;
-
neigh_parms_data_state_setall(idev->nd_parms);
ifa->addr = *cfg->pfx;
@@ -5172,9 +5168,9 @@ next:
fillargs->event = RTM_GETMULTICAST;
/* multicast address */
- for (ifmca = rcu_dereference(idev->mc_list);
+ for (ifmca = rtnl_dereference(idev->mc_list);
ifmca;
- ifmca = rcu_dereference(ifmca->next), ip_idx++) {
+ ifmca = rtnl_dereference(ifmca->next), ip_idx++) {
if (ip_idx < s_ip_idx)
continue;
err = inet6_fill_ifmcaddr(skb, ifmca, fillargs);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index d25dc83bac62..828355710c57 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -4569,8 +4569,15 @@ struct fib6_info *addrconf_f6i_alloc(struct net *net,
}
f6i = ip6_route_info_create(&cfg, gfp_flags, NULL);
- if (!IS_ERR(f6i))
+ if (!IS_ERR(f6i)) {
f6i->dst_nocount = true;
+
+ if (!anycast &&
+ (net->ipv6.devconf_all->disable_policy ||
+ idev->cnf.disable_policy))
+ f6i->dst_nopolicy = true;
+ }
+
return f6i;
}
diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c
index 6de01185cc68..d43c50a7310d 100644
--- a/net/ipv6/seg6_hmac.c
+++ b/net/ipv6/seg6_hmac.c
@@ -406,7 +406,6 @@ int __net_init seg6_hmac_net_init(struct net *net)
return rhashtable_init(&sdata->hmac_infos, &rht_params);
}
-EXPORT_SYMBOL(seg6_hmac_net_init);
void seg6_hmac_exit(void)
{
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index c0b138c20992..6bcd5e419a08 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -323,8 +323,6 @@ static int ipip6_tunnel_get_prl(struct net_device *dev, struct ip_tunnel_prl __u
kcalloc(cmax, sizeof(*kp), GFP_KERNEL_ACCOUNT | __GFP_NOWARN) :
NULL;
- rcu_read_lock();
-
ca = min(t->prl_count, cmax);
if (!kp) {
@@ -341,7 +339,7 @@ static int ipip6_tunnel_get_prl(struct net_device *dev, struct ip_tunnel_prl __u
}
}
- c = 0;
+ rcu_read_lock();
for_each_prl_rcu(t->prl) {
if (c >= cmax)
break;
@@ -353,7 +351,7 @@ static int ipip6_tunnel_get_prl(struct net_device *dev, struct ip_tunnel_prl __u
if (kprl.addr != htonl(INADDR_ANY))
break;
}
-out:
+
rcu_read_unlock();
len = sizeof(*kp) * c;
@@ -362,7 +360,7 @@ out:
ret = -EFAULT;
kfree(kp);
-
+out:
return ret;
}
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index be3b918a6d15..aead331866a0 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -765,6 +765,7 @@ static noinline bool mptcp_established_options_rst(struct sock *sk, struct sk_bu
opts->suboptions |= OPTION_MPTCP_RST;
opts->reset_transient = subflow->reset_transient;
opts->reset_reason = subflow->reset_reason;
+ MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPRSTTX);
return true;
}
@@ -788,6 +789,7 @@ static bool mptcp_established_options_fastclose(struct sock *sk,
opts->rcvr_key = msk->remote_key;
pr_debug("FASTCLOSE key=%llu", opts->rcvr_key);
+ MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFASTCLOSETX);
return true;
}
@@ -809,6 +811,7 @@ static bool mptcp_established_options_mp_fail(struct sock *sk,
opts->fail_seq = subflow->map_seq;
pr_debug("MP_FAIL fail_seq=%llu", opts->fail_seq);
+ MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFAILTX);
return true;
}
@@ -833,13 +836,11 @@ bool mptcp_established_options(struct sock *sk, struct sk_buff *skb,
mptcp_established_options_mp_fail(sk, &opt_size, remaining, opts)) {
*size += opt_size;
remaining -= opt_size;
- MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFASTCLOSETX);
}
/* MP_RST can be used with MP_FASTCLOSE and MP_FAIL if there is room */
if (mptcp_established_options_rst(sk, skb, &opt_size, remaining, opts)) {
*size += opt_size;
remaining -= opt_size;
- MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPRSTTX);
}
return true;
}
@@ -966,7 +967,7 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk,
goto reset;
subflow->mp_capable = 0;
pr_fallback(msk);
- __mptcp_do_fallback(msk);
+ mptcp_do_fallback(ssk);
return false;
}
diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 59a85220edc9..45e2a48397b9 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -299,23 +299,21 @@ void mptcp_pm_mp_fail_received(struct sock *sk, u64 fail_seq)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
struct mptcp_sock *msk = mptcp_sk(subflow->conn);
- struct sock *s = (struct sock *)msk;
pr_debug("fail_seq=%llu", fail_seq);
if (!READ_ONCE(msk->allow_infinite_fallback))
return;
- if (!READ_ONCE(subflow->mp_fail_response_expect)) {
+ if (!subflow->fail_tout) {
pr_debug("send MP_FAIL response and infinite map");
subflow->send_mp_fail = 1;
- MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFAILTX);
subflow->send_infinite_map = 1;
- } else if (!sock_flag(sk, SOCK_DEAD)) {
+ tcp_send_ack(sk);
+ } else {
pr_debug("MP_FAIL response received");
-
- sk_stop_timer(s, &s->sk_timer);
+ WRITE_ONCE(subflow->fail_tout, 0);
}
}
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 17e13396024a..e475212f2618 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -500,7 +500,7 @@ static void mptcp_set_timeout(struct sock *sk)
__mptcp_set_timeout(sk, tout);
}
-static bool tcp_can_send_ack(const struct sock *ssk)
+static inline bool tcp_can_send_ack(const struct sock *ssk)
{
return !((1 << inet_sk_state_load(ssk)) &
(TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_TIME_WAIT | TCPF_CLOSE | TCPF_LISTEN));
@@ -1245,7 +1245,7 @@ static void mptcp_update_infinite_map(struct mptcp_sock *msk,
MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_INFINITEMAPTX);
mptcp_subflow_ctx(ssk)->send_infinite_map = 0;
pr_fallback(msk);
- __mptcp_do_fallback(msk);
+ mptcp_do_fallback(ssk);
}
static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
@@ -2175,21 +2175,6 @@ static void mptcp_retransmit_timer(struct timer_list *t)
sock_put(sk);
}
-static struct mptcp_subflow_context *
-mp_fail_response_expect_subflow(struct mptcp_sock *msk)
-{
- struct mptcp_subflow_context *subflow, *ret = NULL;
-
- mptcp_for_each_subflow(msk, subflow) {
- if (READ_ONCE(subflow->mp_fail_response_expect)) {
- ret = subflow;
- break;
- }
- }
-
- return ret;
-}
-
static void mptcp_timeout_timer(struct timer_list *t)
{
struct sock *sk = from_timer(sk, t, sk_timer);
@@ -2346,6 +2331,11 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
kfree_rcu(subflow, rcu);
} else {
/* otherwise tcp will dispose of the ssk and subflow ctx */
+ if (ssk->sk_state == TCP_LISTEN) {
+ tcp_set_state(ssk, TCP_CLOSE);
+ mptcp_subflow_queue_clean(ssk);
+ inet_csk_listen_stop(ssk);
+ }
__tcp_close(ssk, 0);
/* close acquired an extra ref */
@@ -2518,27 +2508,50 @@ reset_timer:
mptcp_reset_timer(sk);
}
+/* schedule the timeout timer for the relevant event: either close timeout
+ * or mp_fail timeout. The close timeout takes precedence on the mp_fail one
+ */
+void mptcp_reset_timeout(struct mptcp_sock *msk, unsigned long fail_tout)
+{
+ struct sock *sk = (struct sock *)msk;
+ unsigned long timeout, close_timeout;
+
+ if (!fail_tout && !sock_flag(sk, SOCK_DEAD))
+ return;
+
+ close_timeout = inet_csk(sk)->icsk_mtup.probe_timestamp - tcp_jiffies32 + jiffies + TCP_TIMEWAIT_LEN;
+
+ /* the close timeout takes precedence on the fail one, and here at least one of
+ * them is active
+ */
+ timeout = sock_flag(sk, SOCK_DEAD) ? close_timeout : fail_tout;
+
+ sk_reset_timer(sk, &sk->sk_timer, timeout);
+}
+
static void mptcp_mp_fail_no_response(struct mptcp_sock *msk)
{
- struct mptcp_subflow_context *subflow;
- struct sock *ssk;
+ struct sock *ssk = msk->first;
bool slow;
- subflow = mp_fail_response_expect_subflow(msk);
- if (subflow) {
- pr_debug("MP_FAIL doesn't respond, reset the subflow");
+ if (!ssk)
+ return;
- ssk = mptcp_subflow_tcp_sock(subflow);
- slow = lock_sock_fast(ssk);
- mptcp_subflow_reset(ssk);
- unlock_sock_fast(ssk, slow);
- }
+ pr_debug("MP_FAIL doesn't respond, reset the subflow");
+
+ slow = lock_sock_fast(ssk);
+ mptcp_subflow_reset(ssk);
+ WRITE_ONCE(mptcp_subflow_ctx(ssk)->fail_tout, 0);
+ unlock_sock_fast(ssk, slow);
+
+ mptcp_reset_timeout(msk, 0);
}
static void mptcp_worker(struct work_struct *work)
{
struct mptcp_sock *msk = container_of(work, struct mptcp_sock, work);
struct sock *sk = &msk->sk.icsk_inet.sk;
+ unsigned long fail_tout;
int state;
lock_sock(sk);
@@ -2575,7 +2588,9 @@ static void mptcp_worker(struct work_struct *work)
if (test_and_clear_bit(MPTCP_WORK_RTX, &msk->flags))
__mptcp_retrans(sk);
- mptcp_mp_fail_no_response(msk);
+ fail_tout = msk->first ? READ_ONCE(mptcp_subflow_ctx(msk->first)->fail_tout) : 0;
+ if (fail_tout && time_after(jiffies, fail_tout))
+ mptcp_mp_fail_no_response(msk);
unlock:
release_sock(sk);
@@ -2822,6 +2837,7 @@ static void __mptcp_destroy_sock(struct sock *sk)
static void mptcp_close(struct sock *sk, long timeout)
{
struct mptcp_subflow_context *subflow;
+ struct mptcp_sock *msk = mptcp_sk(sk);
bool do_cancel_work = false;
lock_sock(sk);
@@ -2840,10 +2856,16 @@ static void mptcp_close(struct sock *sk, long timeout)
cleanup:
/* orphan all the subflows */
inet_csk(sk)->icsk_mtup.probe_timestamp = tcp_jiffies32;
- mptcp_for_each_subflow(mptcp_sk(sk), subflow) {
+ mptcp_for_each_subflow(msk, subflow) {
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
bool slow = lock_sock_fast_nested(ssk);
+ /* since the close timeout takes precedence on the fail one,
+ * cancel the latter
+ */
+ if (ssk == msk->first)
+ subflow->fail_tout = 0;
+
sock_orphan(ssk);
unlock_sock_fast(ssk, slow);
}
@@ -2852,13 +2874,13 @@ cleanup:
sock_hold(sk);
pr_debug("msk=%p state=%d", sk, sk->sk_state);
if (mptcp_sk(sk)->token)
- mptcp_event(MPTCP_EVENT_CLOSED, mptcp_sk(sk), NULL, GFP_KERNEL);
+ mptcp_event(MPTCP_EVENT_CLOSED, msk, NULL, GFP_KERNEL);
if (sk->sk_state == TCP_CLOSE) {
__mptcp_destroy_sock(sk);
do_cancel_work = true;
} else {
- sk_reset_timer(sk, &sk->sk_timer, jiffies + TCP_TIMEWAIT_LEN);
+ mptcp_reset_timeout(msk, 0);
}
release_sock(sk);
if (do_cancel_work)
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 200f89f6d62f..c14d70c036d0 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -306,6 +306,7 @@ struct mptcp_sock {
u32 setsockopt_seq;
char ca_name[TCP_CA_NAME_MAX];
+ struct mptcp_sock *dl_next;
};
#define mptcp_data_lock(sk) spin_lock_bh(&(sk)->sk_lock.slock)
@@ -468,7 +469,6 @@ struct mptcp_subflow_context {
local_id_valid : 1, /* local_id is correctly initialized */
valid_csum_seen : 1; /* at least one csum validated */
enum mptcp_data_avail data_avail;
- bool mp_fail_response_expect;
u32 remote_nonce;
u64 thmac;
u32 local_nonce;
@@ -482,6 +482,7 @@ struct mptcp_subflow_context {
u8 stale_count;
long delegated_status;
+ unsigned long fail_tout;
);
@@ -608,6 +609,7 @@ void mptcp_close_ssk(struct sock *sk, struct sock *ssk,
struct mptcp_subflow_context *subflow);
void mptcp_subflow_send_ack(struct sock *ssk);
void mptcp_subflow_reset(struct sock *ssk);
+void mptcp_subflow_queue_clean(struct sock *ssk);
void mptcp_sock_graft(struct sock *sk, struct socket *parent);
struct socket *__mptcp_nmpc_socket(const struct mptcp_sock *msk);
@@ -662,6 +664,7 @@ void mptcp_get_options(const struct sk_buff *skb,
void mptcp_finish_connect(struct sock *sk);
void __mptcp_set_connected(struct sock *sk);
+void mptcp_reset_timeout(struct mptcp_sock *msk, unsigned long fail_tout);
static inline bool mptcp_is_fully_established(struct sock *sk)
{
return inet_sk_state_load(sk) == TCP_ESTABLISHED &&
@@ -926,12 +929,25 @@ static inline void __mptcp_do_fallback(struct mptcp_sock *msk)
set_bit(MPTCP_FALLBACK_DONE, &msk->flags);
}
-static inline void mptcp_do_fallback(struct sock *sk)
+static inline void mptcp_do_fallback(struct sock *ssk)
{
- struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
- struct mptcp_sock *msk = mptcp_sk(subflow->conn);
+ struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
+ struct sock *sk = subflow->conn;
+ struct mptcp_sock *msk;
+ msk = mptcp_sk(sk);
__mptcp_do_fallback(msk);
+ if (READ_ONCE(msk->snd_data_fin_enable) && !(ssk->sk_shutdown & SEND_SHUTDOWN)) {
+ gfp_t saved_allocation = ssk->sk_allocation;
+
+ /* we are in a atomic (BH) scope, override ssk default for data
+ * fin allocation
+ */
+ ssk->sk_allocation = GFP_ATOMIC;
+ ssk->sk_shutdown |= SEND_SHUTDOWN;
+ tcp_shutdown(ssk, SEND_SHUTDOWN);
+ ssk->sk_allocation = saved_allocation;
+ }
}
#define pr_fallback(a) pr_debug("%s:fallback to TCP (msk=%p)", __func__, a)
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 8841e8cd9ad8..63e8892ec807 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -843,7 +843,8 @@ enum mapping_status {
MAPPING_INVALID,
MAPPING_EMPTY,
MAPPING_DATA_FIN,
- MAPPING_DUMMY
+ MAPPING_DUMMY,
+ MAPPING_BAD_CSUM
};
static void dbg_bad_map(struct mptcp_subflow_context *subflow, u32 ssn)
@@ -958,11 +959,7 @@ static enum mapping_status validate_data_csum(struct sock *ssk, struct sk_buff *
subflow->map_data_csum);
if (unlikely(csum)) {
MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DATACSUMERR);
- if (subflow->mp_join || subflow->valid_csum_seen) {
- subflow->send_mp_fail = 1;
- MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPFAILTX);
- }
- return subflow->mp_join ? MAPPING_INVALID : MAPPING_DUMMY;
+ return MAPPING_BAD_CSUM;
}
subflow->valid_csum_seen = 1;
@@ -974,7 +971,6 @@ static enum mapping_status get_mapping_status(struct sock *ssk,
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
bool csum_reqd = READ_ONCE(msk->csum_enabled);
- struct sock *sk = (struct sock *)msk;
struct mptcp_ext *mpext;
struct sk_buff *skb;
u16 data_len;
@@ -1016,9 +1012,6 @@ static enum mapping_status get_mapping_status(struct sock *ssk,
pr_debug("infinite mapping received");
MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_INFINITEMAPRX);
subflow->map_data_len = 0;
- if (!sock_flag(ssk, SOCK_DEAD))
- sk_stop_timer(sk, &sk->sk_timer);
-
return MAPPING_INVALID;
}
@@ -1165,6 +1158,33 @@ static bool subflow_can_fallback(struct mptcp_subflow_context *subflow)
return !subflow->fully_established;
}
+static void mptcp_subflow_fail(struct mptcp_sock *msk, struct sock *ssk)
+{
+ struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
+ unsigned long fail_tout;
+
+ /* greceful failure can happen only on the MPC subflow */
+ if (WARN_ON_ONCE(ssk != READ_ONCE(msk->first)))
+ return;
+
+ /* since the close timeout take precedence on the fail one,
+ * no need to start the latter when the first is already set
+ */
+ if (sock_flag((struct sock *)msk, SOCK_DEAD))
+ return;
+
+ /* we don't need extreme accuracy here, use a zero fail_tout as special
+ * value meaning no fail timeout at all;
+ */
+ fail_tout = jiffies + TCP_RTO_MAX;
+ if (!fail_tout)
+ fail_tout = 1;
+ WRITE_ONCE(subflow->fail_tout, fail_tout);
+ tcp_send_ack(ssk);
+
+ mptcp_reset_timeout(msk, subflow->fail_tout);
+}
+
static bool subflow_check_data_avail(struct sock *ssk)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
@@ -1184,10 +1204,8 @@ static bool subflow_check_data_avail(struct sock *ssk)
status = get_mapping_status(ssk, msk);
trace_subflow_check_data_avail(status, skb_peek(&ssk->sk_receive_queue));
- if (unlikely(status == MAPPING_INVALID))
- goto fallback;
-
- if (unlikely(status == MAPPING_DUMMY))
+ if (unlikely(status == MAPPING_INVALID || status == MAPPING_DUMMY ||
+ status == MAPPING_BAD_CSUM))
goto fallback;
if (status != MAPPING_OK)
@@ -1229,22 +1247,17 @@ no_data:
fallback:
if (!__mptcp_check_fallback(msk)) {
/* RFC 8684 section 3.7. */
- if (subflow->send_mp_fail) {
+ if (status == MAPPING_BAD_CSUM &&
+ (subflow->mp_join || subflow->valid_csum_seen)) {
+ subflow->send_mp_fail = 1;
+
if (!READ_ONCE(msk->allow_infinite_fallback)) {
- ssk->sk_err = EBADMSG;
- tcp_set_state(ssk, TCP_CLOSE);
subflow->reset_transient = 0;
subflow->reset_reason = MPTCP_RST_EMIDDLEBOX;
- tcp_send_active_reset(ssk, GFP_ATOMIC);
- while ((skb = skb_peek(&ssk->sk_receive_queue)))
- sk_eat_skb(ssk, skb);
- } else if (!sock_flag(ssk, SOCK_DEAD)) {
- WRITE_ONCE(subflow->mp_fail_response_expect, true);
- sk_reset_timer((struct sock *)msk,
- &((struct sock *)msk)->sk_timer,
- jiffies + TCP_RTO_MAX);
+ goto reset;
}
- WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_NODATA);
+ mptcp_subflow_fail(msk, ssk);
+ WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_DATA_AVAIL);
return true;
}
@@ -1252,16 +1265,20 @@ fallback:
/* fatal protocol error, close the socket.
* subflow_error_report() will introduce the appropriate barriers
*/
- ssk->sk_err = EBADMSG;
- tcp_set_state(ssk, TCP_CLOSE);
subflow->reset_transient = 0;
subflow->reset_reason = MPTCP_RST_EMPTCP;
+
+reset:
+ ssk->sk_err = EBADMSG;
+ tcp_set_state(ssk, TCP_CLOSE);
+ while ((skb = skb_peek(&ssk->sk_receive_queue)))
+ sk_eat_skb(ssk, skb);
tcp_send_active_reset(ssk, GFP_ATOMIC);
WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_NODATA);
return false;
}
- __mptcp_do_fallback(msk);
+ mptcp_do_fallback(ssk);
}
skb = skb_peek(&ssk->sk_receive_queue);
@@ -1706,6 +1723,58 @@ static void subflow_state_change(struct sock *sk)
}
}
+void mptcp_subflow_queue_clean(struct sock *listener_ssk)
+{
+ struct request_sock_queue *queue = &inet_csk(listener_ssk)->icsk_accept_queue;
+ struct mptcp_sock *msk, *next, *head = NULL;
+ struct request_sock *req;
+
+ /* build a list of all unaccepted mptcp sockets */
+ spin_lock_bh(&queue->rskq_lock);
+ for (req = queue->rskq_accept_head; req; req = req->dl_next) {
+ struct mptcp_subflow_context *subflow;
+ struct sock *ssk = req->sk;
+ struct mptcp_sock *msk;
+
+ if (!sk_is_mptcp(ssk))
+ continue;
+
+ subflow = mptcp_subflow_ctx(ssk);
+ if (!subflow || !subflow->conn)
+ continue;
+
+ /* skip if already in list */
+ msk = mptcp_sk(subflow->conn);
+ if (msk->dl_next || msk == head)
+ continue;
+
+ msk->dl_next = head;
+ head = msk;
+ }
+ spin_unlock_bh(&queue->rskq_lock);
+ if (!head)
+ return;
+
+ /* can't acquire the msk socket lock under the subflow one,
+ * or will cause ABBA deadlock
+ */
+ release_sock(listener_ssk);
+
+ for (msk = head; msk; msk = next) {
+ struct sock *sk = (struct sock *)msk;
+ bool slow;
+
+ slow = lock_sock_fast_nested(sk);
+ next = msk->dl_next;
+ msk->first = NULL;
+ msk->dl_next = NULL;
+ unlock_sock_fast(sk, slow);
+ }
+
+ /* we are still under the listener msk socket lock */
+ lock_sock_nested(listener_ssk, SINGLE_DEPTH_NESTING);
+}
+
static int subflow_ulp_init(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c
index 78814417d753..80713febfac6 100644
--- a/net/ncsi/ncsi-manage.c
+++ b/net/ncsi/ncsi-manage.c
@@ -1803,7 +1803,8 @@ struct ncsi_dev *ncsi_register_dev(struct net_device *dev,
pdev = to_platform_device(dev->dev.parent);
if (pdev) {
np = pdev->dev.of_node;
- if (np && of_get_property(np, "mlx,multi-host", NULL))
+ if (np && (of_get_property(np, "mellanox,multi-host", NULL) ||
+ of_get_property(np, "mlx,multi-host", NULL)))
ndp->mlx_multi_host = true;
}
diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c
index 53f40e473855..3ddce24ac76d 100644
--- a/net/netfilter/nf_tables_core.c
+++ b/net/netfilter/nf_tables_core.c
@@ -25,9 +25,7 @@ static noinline void __nft_trace_packet(struct nft_traceinfo *info,
const struct nft_chain *chain,
enum nft_trace_types type)
{
- const struct nft_pktinfo *pkt = info->pkt;
-
- if (!info->trace || !pkt->skb->nf_trace)
+ if (!info->trace || !info->nf_trace)
return;
info->chain = chain;
@@ -42,11 +40,24 @@ static inline void nft_trace_packet(struct nft_traceinfo *info,
enum nft_trace_types type)
{
if (static_branch_unlikely(&nft_trace_enabled)) {
+ const struct nft_pktinfo *pkt = info->pkt;
+
+ info->nf_trace = pkt->skb->nf_trace;
info->rule = rule;
__nft_trace_packet(info, chain, type);
}
}
+static inline void nft_trace_copy_nftrace(struct nft_traceinfo *info)
+{
+ if (static_branch_unlikely(&nft_trace_enabled)) {
+ const struct nft_pktinfo *pkt = info->pkt;
+
+ if (info->trace)
+ info->nf_trace = pkt->skb->nf_trace;
+ }
+}
+
static void nft_bitwise_fast_eval(const struct nft_expr *expr,
struct nft_regs *regs)
{
@@ -85,6 +96,7 @@ static noinline void __nft_trace_verdict(struct nft_traceinfo *info,
const struct nft_chain *chain,
const struct nft_regs *regs)
{
+ const struct nft_pktinfo *pkt = info->pkt;
enum nft_trace_types type;
switch (regs->verdict.code) {
@@ -92,8 +104,13 @@ static noinline void __nft_trace_verdict(struct nft_traceinfo *info,
case NFT_RETURN:
type = NFT_TRACETYPE_RETURN;
break;
+ case NF_STOLEN:
+ type = NFT_TRACETYPE_RULE;
+ /* can't access skb->nf_trace; use copy */
+ break;
default:
type = NFT_TRACETYPE_RULE;
+ info->nf_trace = pkt->skb->nf_trace;
break;
}
@@ -254,6 +271,7 @@ next_rule:
switch (regs.verdict.code) {
case NFT_BREAK:
regs.verdict.code = NFT_CONTINUE;
+ nft_trace_copy_nftrace(&info);
continue;
case NFT_CONTINUE:
nft_trace_packet(&info, chain, rule,
diff --git a/net/netfilter/nf_tables_trace.c b/net/netfilter/nf_tables_trace.c
index 5041725423c2..1163ba9c1401 100644
--- a/net/netfilter/nf_tables_trace.c
+++ b/net/netfilter/nf_tables_trace.c
@@ -7,7 +7,7 @@
#include <linux/module.h>
#include <linux/static_key.h>
#include <linux/hash.h>
-#include <linux/jhash.h>
+#include <linux/siphash.h>
#include <linux/if_vlan.h>
#include <linux/init.h>
#include <linux/skbuff.h>
@@ -25,22 +25,6 @@
DEFINE_STATIC_KEY_FALSE(nft_trace_enabled);
EXPORT_SYMBOL_GPL(nft_trace_enabled);
-static int trace_fill_id(struct sk_buff *nlskb, struct sk_buff *skb)
-{
- __be32 id;
-
- /* using skb address as ID results in a limited number of
- * values (and quick reuse).
- *
- * So we attempt to use as many skb members that will not
- * change while skb is with netfilter.
- */
- id = (__be32)jhash_2words(hash32_ptr(skb), skb_get_hash(skb),
- skb->skb_iif);
-
- return nla_put_be32(nlskb, NFTA_TRACE_ID, id);
-}
-
static int trace_fill_header(struct sk_buff *nlskb, u16 type,
const struct sk_buff *skb,
int off, unsigned int len)
@@ -186,6 +170,7 @@ void nft_trace_notify(struct nft_traceinfo *info)
struct nlmsghdr *nlh;
struct sk_buff *skb;
unsigned int size;
+ u32 mark = 0;
u16 event;
if (!nfnetlink_has_listeners(nft_net(pkt), NFNLGRP_NFTRACE))
@@ -229,7 +214,7 @@ void nft_trace_notify(struct nft_traceinfo *info)
if (nla_put_be32(skb, NFTA_TRACE_TYPE, htonl(info->type)))
goto nla_put_failure;
- if (trace_fill_id(skb, pkt->skb))
+ if (nla_put_u32(skb, NFTA_TRACE_ID, info->skbid))
goto nla_put_failure;
if (nla_put_string(skb, NFTA_TRACE_CHAIN, info->chain->name))
@@ -249,16 +234,24 @@ void nft_trace_notify(struct nft_traceinfo *info)
case NFT_TRACETYPE_RULE:
if (nft_verdict_dump(skb, NFTA_TRACE_VERDICT, info->verdict))
goto nla_put_failure;
+
+ /* pkt->skb undefined iff NF_STOLEN, disable dump */
+ if (info->verdict->code == NF_STOLEN)
+ info->packet_dumped = true;
+ else
+ mark = pkt->skb->mark;
+
break;
case NFT_TRACETYPE_POLICY:
+ mark = pkt->skb->mark;
+
if (nla_put_be32(skb, NFTA_TRACE_POLICY,
htonl(info->basechain->policy)))
goto nla_put_failure;
break;
}
- if (pkt->skb->mark &&
- nla_put_be32(skb, NFTA_TRACE_MARK, htonl(pkt->skb->mark)))
+ if (mark && nla_put_be32(skb, NFTA_TRACE_MARK, htonl(mark)))
goto nla_put_failure;
if (!info->packet_dumped) {
@@ -283,9 +276,20 @@ void nft_trace_init(struct nft_traceinfo *info, const struct nft_pktinfo *pkt,
const struct nft_verdict *verdict,
const struct nft_chain *chain)
{
+ static siphash_key_t trace_key __read_mostly;
+ struct sk_buff *skb = pkt->skb;
+
info->basechain = nft_base_chain(chain);
info->trace = true;
+ info->nf_trace = pkt->skb->nf_trace;
info->packet_dumped = false;
info->pkt = pkt;
info->verdict = verdict;
+
+ net_get_random_once(&trace_key, sizeof(trace_key));
+
+ info->skbid = (u32)siphash_3u32(hash32_ptr(skb),
+ skb_get_hash(skb),
+ skb->skb_iif,
+ &trace_key);
}
diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c
index df40314de21f..76de6c8d9865 100644
--- a/net/netfilter/nft_set_hash.c
+++ b/net/netfilter/nft_set_hash.c
@@ -143,6 +143,7 @@ static bool nft_rhash_update(struct nft_set *set, const u32 *key,
/* Another cpu may race to insert the element with the same key */
if (prev) {
nft_set_elem_destroy(set, he, true);
+ atomic_dec(&set->nelems);
he = prev;
}
@@ -152,6 +153,7 @@ out:
err2:
nft_set_elem_destroy(set, he, true);
+ atomic_dec(&set->nelems);
err1:
return false;
}
diff --git a/net/rose/rose_timer.c b/net/rose/rose_timer.c
index b3138fc2e552..f06ddbed3fed 100644
--- a/net/rose/rose_timer.c
+++ b/net/rose/rose_timer.c
@@ -31,89 +31,89 @@ static void rose_idletimer_expiry(struct timer_list *);
void rose_start_heartbeat(struct sock *sk)
{
- del_timer(&sk->sk_timer);
+ sk_stop_timer(sk, &sk->sk_timer);
sk->sk_timer.function = rose_heartbeat_expiry;
sk->sk_timer.expires = jiffies + 5 * HZ;
- add_timer(&sk->sk_timer);
+ sk_reset_timer(sk, &sk->sk_timer, sk->sk_timer.expires);
}
void rose_start_t1timer(struct sock *sk)
{
struct rose_sock *rose = rose_sk(sk);
- del_timer(&rose->timer);
+ sk_stop_timer(sk, &rose->timer);
rose->timer.function = rose_timer_expiry;
rose->timer.expires = jiffies + rose->t1;
- add_timer(&rose->timer);
+ sk_reset_timer(sk, &rose->timer, rose->timer.expires);
}
void rose_start_t2timer(struct sock *sk)
{
struct rose_sock *rose = rose_sk(sk);
- del_timer(&rose->timer);
+ sk_stop_timer(sk, &rose->timer);
rose->timer.function = rose_timer_expiry;
rose->timer.expires = jiffies + rose->t2;
- add_timer(&rose->timer);
+ sk_reset_timer(sk, &rose->timer, rose->timer.expires);
}
void rose_start_t3timer(struct sock *sk)
{
struct rose_sock *rose = rose_sk(sk);
- del_timer(&rose->timer);
+ sk_stop_timer(sk, &rose->timer);
rose->timer.function = rose_timer_expiry;
rose->timer.expires = jiffies + rose->t3;
- add_timer(&rose->timer);
+ sk_reset_timer(sk, &rose->timer, rose->timer.expires);
}
void rose_start_hbtimer(struct sock *sk)
{
struct rose_sock *rose = rose_sk(sk);
- del_timer(&rose->timer);
+ sk_stop_timer(sk, &rose->timer);
rose->timer.function = rose_timer_expiry;
rose->timer.expires = jiffies + rose->hb;
- add_timer(&rose->timer);
+ sk_reset_timer(sk, &rose->timer, rose->timer.expires);
}
void rose_start_idletimer(struct sock *sk)
{
struct rose_sock *rose = rose_sk(sk);
- del_timer(&rose->idletimer);
+ sk_stop_timer(sk, &rose->idletimer);
if (rose->idle > 0) {
rose->idletimer.function = rose_idletimer_expiry;
rose->idletimer.expires = jiffies + rose->idle;
- add_timer(&rose->idletimer);
+ sk_reset_timer(sk, &rose->idletimer, rose->idletimer.expires);
}
}
void rose_stop_heartbeat(struct sock *sk)
{
- del_timer(&sk->sk_timer);
+ sk_stop_timer(sk, &sk->sk_timer);
}
void rose_stop_timer(struct sock *sk)
{
- del_timer(&rose_sk(sk)->timer);
+ sk_stop_timer(sk, &rose_sk(sk)->timer);
}
void rose_stop_idletimer(struct sock *sk)
{
- del_timer(&rose_sk(sk)->idletimer);
+ sk_stop_timer(sk, &rose_sk(sk)->idletimer);
}
static void rose_heartbeat_expiry(struct timer_list *t)
@@ -130,6 +130,7 @@ static void rose_heartbeat_expiry(struct timer_list *t)
(sk->sk_state == TCP_LISTEN && sock_flag(sk, SOCK_DEAD))) {
bh_unlock_sock(sk);
rose_destroy_socket(sk);
+ sock_put(sk);
return;
}
break;
@@ -152,6 +153,7 @@ static void rose_heartbeat_expiry(struct timer_list *t)
rose_start_heartbeat(sk);
bh_unlock_sock(sk);
+ sock_put(sk);
}
static void rose_timer_expiry(struct timer_list *t)
@@ -181,6 +183,7 @@ static void rose_timer_expiry(struct timer_list *t)
break;
}
bh_unlock_sock(sk);
+ sock_put(sk);
}
static void rose_idletimer_expiry(struct timer_list *t)
@@ -205,4 +208,5 @@ static void rose_idletimer_expiry(struct timer_list *t)
sock_set_flag(sk, SOCK_DEAD);
}
bh_unlock_sock(sk);
+ sock_put(sk);
}
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index da9733da9868..817065aa2833 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -588,7 +588,8 @@ static int tcf_idr_release_unsafe(struct tc_action *p)
}
static int tcf_del_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb,
- const struct tc_action_ops *ops)
+ const struct tc_action_ops *ops,
+ struct netlink_ext_ack *extack)
{
struct nlattr *nest;
int n_i = 0;
@@ -604,20 +605,25 @@ static int tcf_del_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb,
if (nla_put_string(skb, TCA_KIND, ops->kind))
goto nla_put_failure;
+ ret = 0;
mutex_lock(&idrinfo->lock);
idr_for_each_entry_ul(idr, p, tmp, id) {
if (IS_ERR(p))
continue;
ret = tcf_idr_release_unsafe(p);
- if (ret == ACT_P_DELETED) {
+ if (ret == ACT_P_DELETED)
module_put(ops->owner);
- n_i++;
- } else if (ret < 0) {
- mutex_unlock(&idrinfo->lock);
- goto nla_put_failure;
- }
+ else if (ret < 0)
+ break;
+ n_i++;
}
mutex_unlock(&idrinfo->lock);
+ if (ret < 0) {
+ if (n_i)
+ NL_SET_ERR_MSG(extack, "Unable to flush all TC actions");
+ else
+ goto nla_put_failure;
+ }
ret = nla_put_u32(skb, TCA_FCNT, n_i);
if (ret)
@@ -638,7 +644,7 @@ int tcf_generic_walker(struct tc_action_net *tn, struct sk_buff *skb,
struct tcf_idrinfo *idrinfo = tn->idrinfo;
if (type == RTM_DELACTION) {
- return tcf_del_walker(idrinfo, skb, ops);
+ return tcf_del_walker(idrinfo, skb, ops, extack);
} else if (type == RTM_GETACTION) {
return tcf_dump_walker(idrinfo, skb, cb);
} else {
diff --git a/net/socket.c b/net/socket.c
index 2bc8773d9dc5..96300cdc0625 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2149,10 +2149,13 @@ SYSCALL_DEFINE4(send, int, fd, void __user *, buff, size_t, len,
int __sys_recvfrom(int fd, void __user *ubuf, size_t size, unsigned int flags,
struct sockaddr __user *addr, int __user *addr_len)
{
+ struct sockaddr_storage address;
+ struct msghdr msg = {
+ /* Save some cycles and don't copy the address if not needed */
+ .msg_name = addr ? (struct sockaddr *)&address : NULL,
+ };
struct socket *sock;
struct iovec iov;
- struct msghdr msg;
- struct sockaddr_storage address;
int err, err2;
int fput_needed;
@@ -2163,14 +2166,6 @@ int __sys_recvfrom(int fd, void __user *ubuf, size_t size, unsigned int flags,
if (!sock)
goto out;
- msg.msg_control = NULL;
- msg.msg_controllen = 0;
- /* Save some cycles and don't copy the address if not needed */
- msg.msg_name = addr ? (struct sockaddr *)&address : NULL;
- /* We assume all kernel code knows the size of sockaddr_storage */
- msg.msg_namelen = 0;
- msg.msg_iocb = NULL;
- msg.msg_flags = 0;
if (sock->file->f_flags & O_NONBLOCK)
flags |= MSG_DONTWAIT;
err = sock_recvmsg(sock, &msg, flags);
@@ -2375,6 +2370,7 @@ int __copy_msghdr_from_user(struct msghdr *kmsg,
return -EFAULT;
kmsg->msg_control_is_user = true;
+ kmsg->msg_get_inq = 0;
kmsg->msg_control_user = msg.msg_control;
kmsg->msg_controllen = msg.msg_controllen;
kmsg->msg_flags = msg.msg_flags;
diff --git a/net/tipc/node.c b/net/tipc/node.c
index 6ef95ce565bd..b48d97cbbe29 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -472,8 +472,8 @@ struct tipc_node *tipc_node_create(struct net *net, u32 addr, u8 *peer_id,
bool preliminary)
{
struct tipc_net *tn = net_generic(net, tipc_net_id);
+ struct tipc_link *l, *snd_l = tipc_bc_sndlink(net);
struct tipc_node *n, *temp_node;
- struct tipc_link *l;
unsigned long intv;
int bearer_id;
int i;
@@ -488,6 +488,16 @@ struct tipc_node *tipc_node_create(struct net *net, u32 addr, u8 *peer_id,
goto exit;
/* A preliminary node becomes "real" now, refresh its data */
tipc_node_write_lock(n);
+ if (!tipc_link_bc_create(net, tipc_own_addr(net), addr, peer_id, U16_MAX,
+ tipc_link_min_win(snd_l), tipc_link_max_win(snd_l),
+ n->capabilities, &n->bc_entry.inputq1,
+ &n->bc_entry.namedq, snd_l, &n->bc_entry.link)) {
+ pr_warn("Broadcast rcv link refresh failed, no memory\n");
+ tipc_node_write_unlock_fast(n);
+ tipc_node_put(n);
+ n = NULL;
+ goto exit;
+ }
n->preliminary = false;
n->addr = addr;
hlist_del_rcu(&n->hash);
@@ -567,7 +577,16 @@ update:
n->signature = INVALID_NODE_SIG;
n->active_links[0] = INVALID_BEARER_ID;
n->active_links[1] = INVALID_BEARER_ID;
- n->bc_entry.link = NULL;
+ if (!preliminary &&
+ !tipc_link_bc_create(net, tipc_own_addr(net), addr, peer_id, U16_MAX,
+ tipc_link_min_win(snd_l), tipc_link_max_win(snd_l),
+ n->capabilities, &n->bc_entry.inputq1,
+ &n->bc_entry.namedq, snd_l, &n->bc_entry.link)) {
+ pr_warn("Broadcast rcv link creation failed, no memory\n");
+ kfree(n);
+ n = NULL;
+ goto exit;
+ }
tipc_node_get(n);
timer_setup(&n->timer, tipc_node_timeout, 0);
/* Start a slow timer anyway, crypto needs it */
@@ -1155,7 +1174,7 @@ void tipc_node_check_dest(struct net *net, u32 addr,
bool *respond, bool *dupl_addr)
{
struct tipc_node *n;
- struct tipc_link *l, *snd_l;
+ struct tipc_link *l;
struct tipc_link_entry *le;
bool addr_match = false;
bool sign_match = false;
@@ -1175,22 +1194,6 @@ void tipc_node_check_dest(struct net *net, u32 addr,
return;
tipc_node_write_lock(n);
- if (unlikely(!n->bc_entry.link)) {
- snd_l = tipc_bc_sndlink(net);
- if (!tipc_link_bc_create(net, tipc_own_addr(net),
- addr, peer_id, U16_MAX,
- tipc_link_min_win(snd_l),
- tipc_link_max_win(snd_l),
- n->capabilities,
- &n->bc_entry.inputq1,
- &n->bc_entry.namedq, snd_l,
- &n->bc_entry.link)) {
- pr_warn("Broadcast rcv link creation failed, no mem\n");
- tipc_node_write_unlock_fast(n);
- tipc_node_put(n);
- return;
- }
- }
le = &n->links[b->identity];
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 17f8c523e33b..43509c7e90fc 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -502,6 +502,7 @@ static int tipc_sk_create(struct net *net, struct socket *sock,
sock_init_data(sock, sk);
tipc_set_sk_state(sk, TIPC_OPEN);
if (tipc_sk_insert(tsk)) {
+ sk_free(sk);
pr_warn("Socket create failed; port number exhausted\n");
return -EINVAL;
}
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c b/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c
index af293ea1542c..e172d89e92e1 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c
@@ -4,6 +4,7 @@
* Tests for sockmap/sockhash holding kTLS sockets.
*/
+#include <netinet/tcp.h>
#include "test_progs.h"
#define MAX_TEST_NAME 80
@@ -92,9 +93,78 @@ close_srv:
close(srv);
}
+static void test_sockmap_ktls_update_fails_when_sock_has_ulp(int family, int map)
+{
+ struct sockaddr_storage addr = {};
+ socklen_t len = sizeof(addr);
+ struct sockaddr_in6 *v6;
+ struct sockaddr_in *v4;
+ int err, s, zero = 0;
+
+ switch (family) {
+ case AF_INET:
+ v4 = (struct sockaddr_in *)&addr;
+ v4->sin_family = AF_INET;
+ break;
+ case AF_INET6:
+ v6 = (struct sockaddr_in6 *)&addr;
+ v6->sin6_family = AF_INET6;
+ break;
+ default:
+ PRINT_FAIL("unsupported socket family %d", family);
+ return;
+ }
+
+ s = socket(family, SOCK_STREAM, 0);
+ if (!ASSERT_GE(s, 0, "socket"))
+ return;
+
+ err = bind(s, (struct sockaddr *)&addr, len);
+ if (!ASSERT_OK(err, "bind"))
+ goto close;
+
+ err = getsockname(s, (struct sockaddr *)&addr, &len);
+ if (!ASSERT_OK(err, "getsockname"))
+ goto close;
+
+ err = connect(s, (struct sockaddr *)&addr, len);
+ if (!ASSERT_OK(err, "connect"))
+ goto close;
+
+ /* save sk->sk_prot and set it to tls_prots */
+ err = setsockopt(s, IPPROTO_TCP, TCP_ULP, "tls", strlen("tls"));
+ if (!ASSERT_OK(err, "setsockopt(TCP_ULP)"))
+ goto close;
+
+ /* sockmap update should not affect saved sk_prot */
+ err = bpf_map_update_elem(map, &zero, &s, BPF_ANY);
+ if (!ASSERT_ERR(err, "sockmap update elem"))
+ goto close;
+
+ /* call sk->sk_prot->setsockopt to dispatch to saved sk_prot */
+ err = setsockopt(s, IPPROTO_TCP, TCP_NODELAY, &zero, sizeof(zero));
+ ASSERT_OK(err, "setsockopt(TCP_NODELAY)");
+
+close:
+ close(s);
+}
+
+static const char *fmt_test_name(const char *subtest_name, int family,
+ enum bpf_map_type map_type)
+{
+ const char *map_type_str = BPF_MAP_TYPE_SOCKMAP ? "SOCKMAP" : "SOCKHASH";
+ const char *family_str = AF_INET ? "IPv4" : "IPv6";
+ static char test_name[MAX_TEST_NAME];
+
+ snprintf(test_name, MAX_TEST_NAME,
+ "sockmap_ktls %s %s %s",
+ subtest_name, family_str, map_type_str);
+
+ return test_name;
+}
+
static void run_tests(int family, enum bpf_map_type map_type)
{
- char test_name[MAX_TEST_NAME];
int map;
map = bpf_map_create(map_type, NULL, sizeof(int), sizeof(int), 1, NULL);
@@ -103,14 +173,10 @@ static void run_tests(int family, enum bpf_map_type map_type)
return;
}
- snprintf(test_name, MAX_TEST_NAME,
- "sockmap_ktls disconnect_after_delete %s %s",
- family == AF_INET ? "IPv4" : "IPv6",
- map_type == BPF_MAP_TYPE_SOCKMAP ? "SOCKMAP" : "SOCKHASH");
- if (!test__start_subtest(test_name))
- return;
-
- test_sockmap_ktls_disconnect_after_delete(family, map);
+ if (test__start_subtest(fmt_test_name("disconnect_after_delete", family, map_type)))
+ test_sockmap_ktls_disconnect_after_delete(family, map);
+ if (test__start_subtest(fmt_test_name("update_fails_when_sock_has_ulp", family, map_type)))
+ test_sockmap_ktls_update_fails_when_sock_has_ulp(family, map);
close(map);
}
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 7ea54af55490..ddad703ace34 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -54,7 +54,7 @@ TEST_GEN_FILES += ipsec
TEST_GEN_FILES += ioam6_parser
TEST_GEN_FILES += gro
TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
-TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls
+TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls tun
TEST_GEN_FILES += toeplitz
TEST_GEN_FILES += cmsg_sender
TEST_GEN_FILES += stress_reuseport_listen
diff --git a/tools/testing/selftests/net/bpf/Makefile b/tools/testing/selftests/net/bpf/Makefile
index 8a69c91fcca0..8ccaf8732eb2 100644
--- a/tools/testing/selftests/net/bpf/Makefile
+++ b/tools/testing/selftests/net/bpf/Makefile
@@ -2,7 +2,7 @@
CLANG ?= clang
CCINCLUDE += -I../../bpf
-CCINCLUDE += -I../../../lib
+CCINCLUDE += -I../../../../lib
CCINCLUDE += -I../../../../../usr/include/
TEST_CUSTOM_PROGS = $(OUTPUT)/bpf/nat6to4.o
diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh
index 9dd43d7d957b..515859a5168b 100755
--- a/tools/testing/selftests/net/mptcp/diag.sh
+++ b/tools/testing/selftests/net/mptcp/diag.sh
@@ -61,6 +61,39 @@ chk_msk_nr()
__chk_nr "grep -c token:" $*
}
+wait_msk_nr()
+{
+ local condition="grep -c token:"
+ local expected=$1
+ local timeout=20
+ local msg nr
+ local max=0
+ local i=0
+
+ shift 1
+ msg=$*
+
+ while [ $i -lt $timeout ]; do
+ nr=$(ss -inmHMN $ns | $condition)
+ [ $nr == $expected ] && break;
+ [ $nr -gt $max ] && max=$nr
+ i=$((i + 1))
+ sleep 1
+ done
+
+ printf "%-50s" "$msg"
+ if [ $i -ge $timeout ]; then
+ echo "[ fail ] timeout while expecting $expected max $max last $nr"
+ ret=$test_cnt
+ elif [ $nr != $expected ]; then
+ echo "[ fail ] expected $expected found $nr"
+ ret=$test_cnt
+ else
+ echo "[ ok ]"
+ fi
+ test_cnt=$((test_cnt+1))
+}
+
chk_msk_fallback_nr()
{
__chk_nr "grep -c fallback" $*
@@ -146,7 +179,7 @@ ip -n $ns link set dev lo up
echo "a" | \
timeout ${timeout_test} \
ip netns exec $ns \
- ./mptcp_connect -p 10000 -l -t ${timeout_poll} \
+ ./mptcp_connect -p 10000 -l -t ${timeout_poll} -w 20 \
0.0.0.0 >/dev/null &
wait_local_port_listen $ns 10000
chk_msk_nr 0 "no msk on netns creation"
@@ -155,7 +188,7 @@ chk_msk_listen 10000
echo "b" | \
timeout ${timeout_test} \
ip netns exec $ns \
- ./mptcp_connect -p 10000 -r 0 -t ${timeout_poll} \
+ ./mptcp_connect -p 10000 -r 0 -t ${timeout_poll} -w 20 \
127.0.0.1 >/dev/null &
wait_connected $ns 10000
chk_msk_nr 2 "after MPC handshake "
@@ -167,13 +200,13 @@ flush_pids
echo "a" | \
timeout ${timeout_test} \
ip netns exec $ns \
- ./mptcp_connect -p 10001 -l -s TCP -t ${timeout_poll} \
+ ./mptcp_connect -p 10001 -l -s TCP -t ${timeout_poll} -w 20 \
0.0.0.0 >/dev/null &
wait_local_port_listen $ns 10001
echo "b" | \
timeout ${timeout_test} \
ip netns exec $ns \
- ./mptcp_connect -p 10001 -r 0 -t ${timeout_poll} \
+ ./mptcp_connect -p 10001 -r 0 -t ${timeout_poll} -w 20 \
127.0.0.1 >/dev/null &
wait_connected $ns 10001
chk_msk_fallback_nr 1 "check fallback"
@@ -184,7 +217,7 @@ for I in `seq 1 $NR_CLIENTS`; do
echo "a" | \
timeout ${timeout_test} \
ip netns exec $ns \
- ./mptcp_connect -p $((I+10001)) -l -w 10 \
+ ./mptcp_connect -p $((I+10001)) -l -w 20 \
-t ${timeout_poll} 0.0.0.0 >/dev/null &
done
wait_local_port_listen $ns $((NR_CLIENTS + 10001))
@@ -193,12 +226,11 @@ for I in `seq 1 $NR_CLIENTS`; do
echo "b" | \
timeout ${timeout_test} \
ip netns exec $ns \
- ./mptcp_connect -p $((I+10001)) -w 10 \
+ ./mptcp_connect -p $((I+10001)) -w 20 \
-t ${timeout_poll} 127.0.0.1 >/dev/null &
done
-sleep 1.5
-chk_msk_nr $((NR_CLIENTS*2)) "many msk socket present"
+wait_msk_nr $((NR_CLIENTS*2)) "many msk socket present"
flush_pids
exit $ret
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c
index 8628aa61b763..e2ea6c126c99 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c
@@ -265,7 +265,7 @@ static void sock_test_tcpulp(int sock, int proto, unsigned int line)
static int sock_listen_mptcp(const char * const listenaddr,
const char * const port)
{
- int sock;
+ int sock = -1;
struct addrinfo hints = {
.ai_protocol = IPPROTO_TCP,
.ai_socktype = SOCK_STREAM,
diff --git a/tools/testing/selftests/net/mptcp/mptcp_inq.c b/tools/testing/selftests/net/mptcp/mptcp_inq.c
index 29f75e2a1116..8672d898f8cd 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_inq.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_inq.c
@@ -88,7 +88,7 @@ static void xgetaddrinfo(const char *node, const char *service,
static int sock_listen_mptcp(const char * const listenaddr,
const char * const port)
{
- int sock;
+ int sock = -1;
struct addrinfo hints = {
.ai_protocol = IPPROTO_TCP,
.ai_socktype = SOCK_STREAM,
diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
index ac9a4d9c1764..ae61f39556ca 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
@@ -136,7 +136,7 @@ static void xgetaddrinfo(const char *node, const char *service,
static int sock_listen_mptcp(const char * const listenaddr,
const char * const port)
{
- int sock;
+ int sock = -1;
struct addrinfo hints = {
.ai_protocol = IPPROTO_TCP,
.ai_socktype = SOCK_STREAM,
diff --git a/tools/testing/selftests/net/tun.c b/tools/testing/selftests/net/tun.c
new file mode 100644
index 000000000000..fa83918b62d1
--- /dev/null
+++ b/tools/testing/selftests/net/tun.c
@@ -0,0 +1,162 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+
+#include <errno.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <linux/if.h>
+#include <linux/if_tun.h>
+#include <linux/netlink.h>
+#include <linux/rtnetlink.h>
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+
+#include "../kselftest_harness.h"
+
+static int tun_attach(int fd, char *dev)
+{
+ struct ifreq ifr;
+
+ memset(&ifr, 0, sizeof(ifr));
+ strcpy(ifr.ifr_name, dev);
+ ifr.ifr_flags = IFF_ATTACH_QUEUE;
+
+ return ioctl(fd, TUNSETQUEUE, (void *) &ifr);
+}
+
+static int tun_detach(int fd, char *dev)
+{
+ struct ifreq ifr;
+
+ memset(&ifr, 0, sizeof(ifr));
+ strcpy(ifr.ifr_name, dev);
+ ifr.ifr_flags = IFF_DETACH_QUEUE;
+
+ return ioctl(fd, TUNSETQUEUE, (void *) &ifr);
+}
+
+static int tun_alloc(char *dev)
+{
+ struct ifreq ifr;
+ int fd, err;
+
+ fd = open("/dev/net/tun", O_RDWR);
+ if (fd < 0) {
+ fprintf(stderr, "can't open tun: %s\n", strerror(errno));
+ return fd;
+ }
+
+ memset(&ifr, 0, sizeof(ifr));
+ strcpy(ifr.ifr_name, dev);
+ ifr.ifr_flags = IFF_TAP | IFF_NAPI | IFF_MULTI_QUEUE;
+
+ err = ioctl(fd, TUNSETIFF, (void *) &ifr);
+ if (err < 0) {
+ fprintf(stderr, "can't TUNSETIFF: %s\n", strerror(errno));
+ close(fd);
+ return err;
+ }
+ strcpy(dev, ifr.ifr_name);
+ return fd;
+}
+
+static int tun_delete(char *dev)
+{
+ struct {
+ struct nlmsghdr nh;
+ struct ifinfomsg ifm;
+ unsigned char data[64];
+ } req;
+ struct rtattr *rta;
+ int ret, rtnl;
+
+ rtnl = socket(AF_NETLINK, SOCK_DGRAM, NETLINK_ROUTE);
+ if (rtnl < 0) {
+ fprintf(stderr, "can't open rtnl: %s\n", strerror(errno));
+ return 1;
+ }
+
+ memset(&req, 0, sizeof(req));
+ req.nh.nlmsg_len = NLMSG_ALIGN(NLMSG_LENGTH(sizeof(req.ifm)));
+ req.nh.nlmsg_flags = NLM_F_REQUEST;
+ req.nh.nlmsg_type = RTM_DELLINK;
+
+ req.ifm.ifi_family = AF_UNSPEC;
+
+ rta = (struct rtattr *)(((char *)&req) + NLMSG_ALIGN(req.nh.nlmsg_len));
+ rta->rta_type = IFLA_IFNAME;
+ rta->rta_len = RTA_LENGTH(IFNAMSIZ);
+ req.nh.nlmsg_len += rta->rta_len;
+ memcpy(RTA_DATA(rta), dev, IFNAMSIZ);
+
+ ret = send(rtnl, &req, req.nh.nlmsg_len, 0);
+ if (ret < 0)
+ fprintf(stderr, "can't send: %s\n", strerror(errno));
+ ret = (unsigned int)ret != req.nh.nlmsg_len;
+
+ close(rtnl);
+ return ret;
+}
+
+FIXTURE(tun)
+{
+ char ifname[IFNAMSIZ];
+ int fd, fd2;
+};
+
+FIXTURE_SETUP(tun)
+{
+ memset(self->ifname, 0, sizeof(self->ifname));
+
+ self->fd = tun_alloc(self->ifname);
+ ASSERT_GE(self->fd, 0);
+
+ self->fd2 = tun_alloc(self->ifname);
+ ASSERT_GE(self->fd2, 0);
+}
+
+FIXTURE_TEARDOWN(tun)
+{
+ if (self->fd >= 0)
+ close(self->fd);
+ if (self->fd2 >= 0)
+ close(self->fd2);
+}
+
+TEST_F(tun, delete_detach_close) {
+ EXPECT_EQ(tun_delete(self->ifname), 0);
+ EXPECT_EQ(tun_detach(self->fd, self->ifname), -1);
+ EXPECT_EQ(errno, 22);
+}
+
+TEST_F(tun, detach_delete_close) {
+ EXPECT_EQ(tun_detach(self->fd, self->ifname), 0);
+ EXPECT_EQ(tun_delete(self->ifname), 0);
+}
+
+TEST_F(tun, detach_close_delete) {
+ EXPECT_EQ(tun_detach(self->fd, self->ifname), 0);
+ close(self->fd);
+ self->fd = -1;
+ EXPECT_EQ(tun_delete(self->ifname), 0);
+}
+
+TEST_F(tun, reattach_delete_close) {
+ EXPECT_EQ(tun_detach(self->fd, self->ifname), 0);
+ EXPECT_EQ(tun_attach(self->fd, self->ifname), 0);
+ EXPECT_EQ(tun_delete(self->ifname), 0);
+}
+
+TEST_F(tun, reattach_close_delete) {
+ EXPECT_EQ(tun_detach(self->fd, self->ifname), 0);
+ EXPECT_EQ(tun_attach(self->fd, self->ifname), 0);
+ close(self->fd);
+ self->fd = -1;
+ EXPECT_EQ(tun_delete(self->ifname), 0);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/net/udpgso_bench.sh b/tools/testing/selftests/net/udpgso_bench.sh
index 80b5d352702e..dc932fd65363 100755
--- a/tools/testing/selftests/net/udpgso_bench.sh
+++ b/tools/testing/selftests/net/udpgso_bench.sh
@@ -120,7 +120,7 @@ run_all() {
run_udp "${ipv4_args}"
echo "ipv6"
- run_tcp "${ipv4_args}"
+ run_tcp "${ipv6_args}"
run_udp "${ipv6_args}"
}
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json b/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json
index b24494c6f546..c652e8c1157d 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json
@@ -609,5 +609,82 @@
"teardown": [
"$TC actions flush action gact"
]
+ },
+ {
+ "id": "7f52",
+ "name": "Try to flush action which is referenced by filter",
+ "category": [
+ "actions",
+ "gact"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ [
+ "$TC actions flush action gact",
+ 0,
+ 1,
+ 255
+ ],
+ "$TC qdisc add dev $DEV1 ingress",
+ "$TC actions add action pass index 1",
+ "$TC filter add dev $DEV1 protocol all ingress prio 1 handle 0x1234 matchall action gact index 1"
+ ],
+ "cmdUnderTest": "$TC actions flush action gact",
+ "expExitCode": "1",
+ "verifyCmd": "$TC actions ls action gact",
+ "matchPattern": "total acts 1.*action order [0-9]*: gact action pass.*index 1 ref 2 bind 1",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 ingress",
+ [
+ "sleep 1; $TC actions flush action gact",
+ 0,
+ 1
+ ]
+ ]
+ },
+ {
+ "id": "ae1e",
+ "name": "Try to flush actions when last one is referenced by filter",
+ "category": [
+ "actions",
+ "gact"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ [
+ "$TC actions flush action gact",
+ 0,
+ 1,
+ 255
+ ],
+ "$TC qdisc add dev $DEV1 ingress",
+ [
+ "$TC actions add action pass index 1",
+ 0,
+ 1,
+ 255
+ ],
+ "$TC actions add action reclassify index 2",
+ "$TC actions add action drop index 3",
+ "$TC filter add dev $DEV1 protocol all ingress prio 1 handle 0x1234 matchall action gact index 3"
+ ],
+ "cmdUnderTest": "$TC actions flush action gact",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions ls action gact",
+ "matchPattern": "total acts 1.*action order [0-9]*: gact action drop.*index 3 ref 2 bind 1",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 ingress",
+ [
+ "sleep 1; $TC actions flush action gact",
+ 0,
+ 1
+ ]
+ ]
}
]