diff --git a/Documentation/networking/bonding.rst b/Documentation/networking/bonding.rst
index adc4bf4f3c5017c4f78647e03ef61101e7f1a689..28925e19622dfa429e8651bdfb391ca001b4f783 100644
--- a/Documentation/networking/bonding.rst
+++ b/Documentation/networking/bonding.rst
@@ -776,10 +776,11 @@ peer_notif_delay
Specify the delay, in milliseconds, between each peer
notification (gratuitous ARP and unsolicited IPv6 Neighbor
Advertisement) when they are issued after a failover event.
- This delay should be a multiple of the link monitor interval
- (arp_interval or miimon, whichever is active). The default
- value is 0 which means to match the value of the link monitor
- interval.
+ This delay should be a multiple of the MII link monitor interval
+ (miimon).
+
+ The valid range is 0 - 300000. The default value is 0, which means
+ to match the value of the MII link monitor interval.
prio
Slave priority. A higher number means higher priority.
diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst
index a164ff074356e48970ef08fb7f2588c6843e156c..5b75c3f7a137b3dbde03903cb2a6a61c0f2facea 100644
--- a/Documentation/networking/index.rst
+++ b/Documentation/networking/index.rst
@@ -116,8 +116,8 @@ Contents:
udplite
vrf
vxlan
- x25-iface
x25
+ x25-iface
xfrm_device
xfrm_proc
xfrm_sync
diff --git a/Documentation/networking/x25-iface.rst b/Documentation/networking/x25-iface.rst
index f34e9ec6493729d96745c914879a75cd48abb97f..285cefcfce8761fd3f1e37f3b0a03dd7b53f4e33 100644
--- a/Documentation/networking/x25-iface.rst
+++ b/Documentation/networking/x25-iface.rst
@@ -1,8 +1,7 @@
.. SPDX-License-Identifier: GPL-2.0
-============================-
X.25 Device Driver Interface
-============================-
+============================
Version 1.1
diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index c2d080fc4fc4ea67bd81476c485af69f72c7c4bd..27cbe148f0db5f82e988af3773fff1e3fce0997d 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -84,6 +84,11 @@ static int bond_fill_slave_info(struct sk_buff *skb,
return -EMSGSIZE;
}
+/* Limit the max delay range to 300s */
+static struct netlink_range_validation delay_range = {
+ .max = 300000,
+};
+
static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = {
[IFLA_BOND_MODE] = { .type = NLA_U8 },
[IFLA_BOND_ACTIVE_SLAVE] = { .type = NLA_U32 },
@@ -114,7 +119,7 @@ static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = {
[IFLA_BOND_AD_ACTOR_SYSTEM] = { .type = NLA_BINARY,
.len = ETH_ALEN },
[IFLA_BOND_TLB_DYNAMIC_LB] = { .type = NLA_U8 },
- [IFLA_BOND_PEER_NOTIF_DELAY] = { .type = NLA_U32 },
+ [IFLA_BOND_PEER_NOTIF_DELAY] = NLA_POLICY_FULL_RANGE(NLA_U32, &delay_range),
[IFLA_BOND_MISSED_MAX] = { .type = NLA_U8 },
[IFLA_BOND_NS_IP6_TARGET] = { .type = NLA_NESTED },
};
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index 0498fc6731f898f6a238498d42a0f0ade6c67856..f3f27f0bd2a6cdd52d8c97e10a9b047af9f2da00 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -169,6 +169,12 @@ static const struct bond_opt_value bond_num_peer_notif_tbl[] = {
{ NULL, -1, 0}
};
+static const struct bond_opt_value bond_peer_notif_delay_tbl[] = {
+ { "off", 0, 0},
+ { "maxval", 300000, BOND_VALFLAG_MAX},
+ { NULL, -1, 0}
+};
+
static const struct bond_opt_value bond_primary_reselect_tbl[] = {
{ "always", BOND_PRI_RESELECT_ALWAYS, BOND_VALFLAG_DEFAULT},
{ "better", BOND_PRI_RESELECT_BETTER, 0},
@@ -488,7 +494,7 @@ static const struct bond_option bond_opts[BOND_OPT_LAST] = {
.id = BOND_OPT_PEER_NOTIF_DELAY,
.name = "peer_notif_delay",
.desc = "Delay between each peer notification on failover event, in milliseconds",
- .values = bond_intmax_tbl,
+ .values = bond_peer_notif_delay_tbl,
.set = bond_option_peer_notif_delay_set
}
};
diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c
index 57ce74315eba4cbf0e18806f72d001b9f2e10f5b..caa00c72aeebaac083b22e11fb8b4094e8e62eab 100644
--- a/drivers/net/ethernet/google/gve/gve_main.c
+++ b/drivers/net/ethernet/google/gve/gve_main.c
@@ -294,19 +294,6 @@ static int gve_napi_poll_dqo(struct napi_struct *napi, int budget)
bool reschedule = false;
int work_done = 0;
- /* Clear PCI MSI-X Pending Bit Array (PBA)
- *
- * This bit is set if an interrupt event occurs while the vector is
- * masked. If this bit is set and we reenable the interrupt, it will
- * fire again. Since we're just about to poll the queue state, we don't
- * need it to fire again.
- *
- * Under high softirq load, it's possible that the interrupt condition
- * is triggered twice before we got the chance to process it.
- */
- gve_write_irq_doorbell_dqo(priv, block,
- GVE_ITR_NO_UPDATE_DQO | GVE_ITR_CLEAR_PBA_BIT_DQO);
-
if (block->tx)
reschedule |= gve_tx_poll_dqo(block, /*do_clean=*/true);
diff --git a/drivers/net/ethernet/mediatek/mtk_wed.c b/drivers/net/ethernet/mediatek/mtk_wed.c
index 4c205afbd2309628eda5fe356fe4b7abb27eb660..985cff910f30c55a411340898da7ceca803f0fb6 100644
--- a/drivers/net/ethernet/mediatek/mtk_wed.c
+++ b/drivers/net/ethernet/mediatek/mtk_wed.c
@@ -654,7 +654,7 @@ __mtk_wed_detach(struct mtk_wed_device *dev)
BIT(hw->index), BIT(hw->index));
}
- if (!hw_list[!hw->index]->wed_dev &&
+ if ((!hw_list[!hw->index] || !hw_list[!hw->index]->wed_dev) &&
hw->eth->dma_dev != hw->eth->dev)
mtk_eth_set_dma_device(hw->eth, hw->eth->dev);
diff --git a/drivers/net/ethernet/mscc/vsc7514_regs.c b/drivers/net/ethernet/mscc/vsc7514_regs.c
index ef6fd3f6be3098f5ef84e5867d48663702f6bcc7..5595bfe84bbbbe975de9b39a5d8f2d8c5df1af05 100644
--- a/drivers/net/ethernet/mscc/vsc7514_regs.c
+++ b/drivers/net/ethernet/mscc/vsc7514_regs.c
@@ -307,15 +307,15 @@ static const u32 vsc7514_sys_regmap[] = {
REG(SYS_COUNT_DROP_YELLOW_PRIO_4, 0x000218),
REG(SYS_COUNT_DROP_YELLOW_PRIO_5, 0x00021c),
REG(SYS_COUNT_DROP_YELLOW_PRIO_6, 0x000220),
- REG(SYS_COUNT_DROP_YELLOW_PRIO_7, 0x000214),
- REG(SYS_COUNT_DROP_GREEN_PRIO_0, 0x000218),
- REG(SYS_COUNT_DROP_GREEN_PRIO_1, 0x00021c),
- REG(SYS_COUNT_DROP_GREEN_PRIO_2, 0x000220),
- REG(SYS_COUNT_DROP_GREEN_PRIO_3, 0x000224),
- REG(SYS_COUNT_DROP_GREEN_PRIO_4, 0x000228),
- REG(SYS_COUNT_DROP_GREEN_PRIO_5, 0x00022c),
- REG(SYS_COUNT_DROP_GREEN_PRIO_6, 0x000230),
- REG(SYS_COUNT_DROP_GREEN_PRIO_7, 0x000234),
+ REG(SYS_COUNT_DROP_YELLOW_PRIO_7, 0x000224),
+ REG(SYS_COUNT_DROP_GREEN_PRIO_0, 0x000228),
+ REG(SYS_COUNT_DROP_GREEN_PRIO_1, 0x00022c),
+ REG(SYS_COUNT_DROP_GREEN_PRIO_2, 0x000230),
+ REG(SYS_COUNT_DROP_GREEN_PRIO_3, 0x000234),
+ REG(SYS_COUNT_DROP_GREEN_PRIO_4, 0x000238),
+ REG(SYS_COUNT_DROP_GREEN_PRIO_5, 0x00023c),
+ REG(SYS_COUNT_DROP_GREEN_PRIO_6, 0x000240),
+ REG(SYS_COUNT_DROP_GREEN_PRIO_7, 0x000244),
REG(SYS_RESET_CFG, 0x000508),
REG(SYS_CMID, 0x00050c),
REG(SYS_VLAN_ETYPE_CFG, 0x000510),
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
index 4538f334df576677686bf01bac3197bfb8825a2f..d3c5306f1c41f7aca6f6a9170f7946a3abfe6cd0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
@@ -181,6 +181,7 @@ enum power_event {
#define GMAC4_LPI_CTRL_STATUS 0xd0
#define GMAC4_LPI_TIMER_CTRL 0xd4
#define GMAC4_LPI_ENTRY_TIMER 0xd8
+#define GMAC4_MAC_ONEUS_TIC_COUNTER 0xdc
/* LPI control and status defines */
#define GMAC4_LPI_CTRL_STATUS_LPITCSE BIT(21) /* LPI Tx Clock Stop Enable */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index afaec3fb9ab663bb009a02e12e8067df9ea98069..03b1c5a97826ec35a593aa6880fae858267099bd 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -25,6 +25,7 @@ static void dwmac4_core_init(struct mac_device_info *hw,
struct stmmac_priv *priv = netdev_priv(dev);
void __iomem *ioaddr = hw->pcsr;
u32 value = readl(ioaddr + GMAC_CONFIG);
+ u32 clk_rate;
value |= GMAC_CORE_INIT;
@@ -47,6 +48,10 @@ static void dwmac4_core_init(struct mac_device_info *hw,
writel(value, ioaddr + GMAC_CONFIG);
+ /* Configure LPI 1us counter to number of CSR clock ticks in 1us - 1 */
+ clk_rate = clk_get_rate(priv->plat->stmmac_clk);
+ writel((clk_rate / 1000000) - 1, ioaddr + GMAC4_MAC_ONEUS_TIC_COUNTER);
+
/* Enable GMAC interrupts */
value = GMAC_INT_DEFAULT_ENABLE;
diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c
index 460b3d4f2245f2adf8c757bfa52b732ba6c1e7eb..ab5133eb1d51783efdab2542265b4e0293e59af9 100644
--- a/drivers/net/ipvlan/ipvlan_core.c
+++ b/drivers/net/ipvlan/ipvlan_core.c
@@ -436,6 +436,9 @@ static int ipvlan_process_v4_outbound(struct sk_buff *skb)
goto err;
}
skb_dst_set(skb, &rt->dst);
+
+ memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
+
err = ip_local_out(net, skb->sk, skb);
if (unlikely(net_xmit_eval(err)))
dev->stats.tx_errors++;
@@ -474,6 +477,9 @@ static int ipvlan_process_v6_outbound(struct sk_buff *skb)
goto err;
}
skb_dst_set(skb, dst);
+
+ memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
+
err = ip6_local_out(net, skb->sk, skb);
if (unlikely(net_xmit_eval(err)))
dev->stats.tx_errors++;
diff --git a/drivers/net/mdio/mdio-mvusb.c b/drivers/net/mdio/mdio-mvusb.c
index 68fc55906e788581347ed6b0729c8287860cde1b..554837c21e73c060705e33fcad908cda77b908c0 100644
--- a/drivers/net/mdio/mdio-mvusb.c
+++ b/drivers/net/mdio/mdio-mvusb.c
@@ -67,6 +67,7 @@ static int mvusb_mdio_probe(struct usb_interface *interface,
struct device *dev = &interface->dev;
struct mvusb_mdio *mvusb;
struct mii_bus *mdio;
+ int ret;
mdio = devm_mdiobus_alloc_size(dev, sizeof(*mvusb));
if (!mdio)
@@ -87,7 +88,15 @@ static int mvusb_mdio_probe(struct usb_interface *interface,
mdio->write = mvusb_mdio_write;
usb_set_intfdata(interface, mvusb);
- return of_mdiobus_register(mdio, dev->of_node);
+ ret = of_mdiobus_register(mdio, dev->of_node);
+ if (ret)
+ goto put_dev;
+
+ return 0;
+
+put_dev:
+ usb_put_dev(mvusb->udev);
+ return ret;
}
static void mvusb_mdio_disconnect(struct usb_interface *interface)
diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c
index 539cd43eae8d3e532ab551e317f855f429690fa5..f19d48c94fe0e9ccd66c3a7c451268af7d713248 100644
--- a/drivers/net/pcs/pcs-xpcs.c
+++ b/drivers/net/pcs/pcs-xpcs.c
@@ -1203,7 +1203,7 @@ static const struct xpcs_compat synopsys_xpcs_compat[DW_XPCS_INTERFACE_MAX] = {
[DW_XPCS_2500BASEX] = {
.supported = xpcs_2500basex_features,
.interface = xpcs_2500basex_interfaces,
- .num_interfaces = ARRAY_SIZE(xpcs_2500basex_features),
+ .num_interfaces = ARRAY_SIZE(xpcs_2500basex_interfaces),
.an_mode = DW_2500BASEX,
},
};
diff --git a/drivers/net/phy/bcm-phy-lib.h b/drivers/net/phy/bcm-phy-lib.h
index 9902fb1820997ea1fd46c1e50c82442707e5cebe..729db441797a0e8c8059c33e08fe998e0e18c188 100644
--- a/drivers/net/phy/bcm-phy-lib.h
+++ b/drivers/net/phy/bcm-phy-lib.h
@@ -40,6 +40,11 @@ static inline int bcm_phy_write_exp_sel(struct phy_device *phydev,
return bcm_phy_write_exp(phydev, reg | MII_BCM54XX_EXP_SEL_ER, val);
}
+static inline int bcm_phy_read_exp_sel(struct phy_device *phydev, u16 reg)
+{
+ return bcm_phy_read_exp(phydev, reg | MII_BCM54XX_EXP_SEL_ER);
+}
+
int bcm54xx_auxctl_write(struct phy_device *phydev, u16 regnum, u16 val);
int bcm54xx_auxctl_read(struct phy_device *phydev, u16 regnum);
diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c
index 06be71ecd2f8e7b1043b50a5767fecf0af05bc9a..f8c17a253f8b37b8b1590d1c7f22cf6616fc57fc 100644
--- a/drivers/net/phy/bcm7xxx.c
+++ b/drivers/net/phy/bcm7xxx.c
@@ -486,7 +486,7 @@ static int bcm7xxx_16nm_ephy_afe_config(struct phy_device *phydev)
bcm_phy_write_misc(phydev, 0x0038, 0x0002, 0xede0);
/* Read CORE_EXPA9 */
- tmp = bcm_phy_read_exp(phydev, 0x00a9);
+ tmp = bcm_phy_read_exp_sel(phydev, 0x00a9);
/* CORE_EXPA9[6:1] is rcalcode[5:0] */
rcalcode = (tmp & 0x7e) / 2;
/* Correct RCAL code + 1 is -1% rprogr, LP: +16 */
diff --git a/drivers/net/tap.c b/drivers/net/tap.c
index ce993cc75bf3106cd7fe71ab9d4188c6ac09af27..d30d730ed5a71b8cc31880acc0f82d4b0f65f739 100644
--- a/drivers/net/tap.c
+++ b/drivers/net/tap.c
@@ -742,7 +742,7 @@ static ssize_t tap_get_user(struct tap_queue *q, void *msg_control,
/* Move network header to the right position for VLAN tagged packets */
if (eth_type_vlan(skb->protocol) &&
- __vlan_get_protocol(skb, skb->protocol, &depth) != 0)
+ vlan_get_protocol_and_depth(skb, skb->protocol, &depth) != 0)
skb_set_network_header(skb, depth);
/* copy skb_ubuf_info for callback when skb has no error */
@@ -1197,7 +1197,7 @@ static int tap_get_user_xdp(struct tap_queue *q, struct xdp_buff *xdp)
/* Move network header to the right position for VLAN tagged packets */
if (eth_type_vlan(skb->protocol) &&
- __vlan_get_protocol(skb, skb->protocol, &depth) != 0)
+ vlan_get_protocol_and_depth(skb, skb->protocol, &depth) != 0)
skb_set_network_header(skb, depth);
rcu_read_lock();
diff --git a/include/linux/dim.h b/include/linux/dim.h
index 6c5733981563eadf5f06c59c5dc97df961692b02..f343bc9aa2ec95adaa3ea685c38dd596758d88b5 100644
--- a/include/linux/dim.h
+++ b/include/linux/dim.h
@@ -236,8 +236,9 @@ void dim_park_tired(struct dim *dim);
*
* Calculate the delta between two samples (in data rates).
* Takes into consideration counter wrap-around.
+ * Returned boolean indicates whether curr_stats are reliable.
*/
-void dim_calc_stats(struct dim_sample *start, struct dim_sample *end,
+bool dim_calc_stats(struct dim_sample *start, struct dim_sample *end,
struct dim_stats *curr_stats);
/**
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 0f40f379d75cb1e80aaff132842a8d1b968ad087..6ba71957851e22829ec9f18cd29bea2d92dfa583 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -637,6 +637,23 @@ static inline __be16 vlan_get_protocol(const struct sk_buff *skb)
return __vlan_get_protocol(skb, skb->protocol, NULL);
}
+/* This version of __vlan_get_protocol() also pulls mac header in skb->head */
+static inline __be16 vlan_get_protocol_and_depth(struct sk_buff *skb,
+ __be16 type, int *depth)
+{
+ int maclen;
+
+ type = __vlan_get_protocol(skb, type, &maclen);
+
+ if (type) {
+ if (!pskb_may_pull(skb, maclen))
+ type = 0;
+ else if (depth)
+ *depth = maclen;
+ }
+ return type;
+}
+
/* A getter for the SKB protocol field which will handle VLAN tags consistently
* whether VLAN acceleration is enabled or not.
*/
diff --git a/include/net/bonding.h b/include/net/bonding.h
index a60a24923b559972d72320588fe05de50ca4195e..0efef2a952b79efe3e2c7fee998b9ea63c864747 100644
--- a/include/net/bonding.h
+++ b/include/net/bonding.h
@@ -233,7 +233,7 @@ struct bonding {
*/
spinlock_t mode_lock;
spinlock_t stats_lock;
- u8 send_peer_notif;
+ u32 send_peer_notif;
u8 igmp_retrans;
#ifdef CONFIG_PROC_FS
struct proc_dir_entry *proc_entry;
diff --git a/include/net/sock.h b/include/net/sock.h
index 8b7ed7167243db4eeb13793a8c465c9392623888..656ea89f60ff90d600d16f40302000db64057c64 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2718,7 +2718,7 @@ static inline void sock_recv_cmsgs(struct msghdr *msg, struct sock *sk,
__sock_recv_cmsgs(msg, sk, skb);
else if (unlikely(sock_flag(sk, SOCK_TIMESTAMP)))
sock_write_timestamp(sk, skb->tstamp);
- else if (unlikely(sk->sk_stamp == SK_DEFAULT_STAMP))
+ else if (unlikely(sock_read_timestamp(sk) == SK_DEFAULT_STAMP))
sock_write_timestamp(sk, 0);
}
diff --git a/lib/dim/dim.c b/lib/dim/dim.c
index 38045d6d05381ebb89d73369b0c60766505ef9be..e89aaf07bde502ec4def08d1775f925c62de7838 100644
--- a/lib/dim/dim.c
+++ b/lib/dim/dim.c
@@ -54,7 +54,7 @@ void dim_park_tired(struct dim *dim)
}
EXPORT_SYMBOL(dim_park_tired);
-void dim_calc_stats(struct dim_sample *start, struct dim_sample *end,
+bool dim_calc_stats(struct dim_sample *start, struct dim_sample *end,
struct dim_stats *curr_stats)
{
/* u32 holds up to 71 minutes, should be enough */
@@ -66,7 +66,7 @@ void dim_calc_stats(struct dim_sample *start, struct dim_sample *end,
start->comp_ctr);
if (!delta_us)
- return;
+ return false;
curr_stats->ppms = DIV_ROUND_UP(npkts * USEC_PER_MSEC, delta_us);
curr_stats->bpms = DIV_ROUND_UP(nbytes * USEC_PER_MSEC, delta_us);
@@ -79,5 +79,6 @@ void dim_calc_stats(struct dim_sample *start, struct dim_sample *end,
else
curr_stats->cpe_ratio = 0;
+ return true;
}
EXPORT_SYMBOL(dim_calc_stats);
diff --git a/lib/dim/net_dim.c b/lib/dim/net_dim.c
index 53f6b9c6e9366200906c8e49a98d2e37161fa51b..4e32f7aaac86ca81c46188a1aeb1320b020fc215 100644
--- a/lib/dim/net_dim.c
+++ b/lib/dim/net_dim.c
@@ -227,7 +227,8 @@ void net_dim(struct dim *dim, struct dim_sample end_sample)
dim->start_sample.event_ctr);
if (nevents < DIM_NEVENTS)
break;
- dim_calc_stats(&dim->start_sample, &end_sample, &curr_stats);
+ if (!dim_calc_stats(&dim->start_sample, &end_sample, &curr_stats))
+ break;
if (net_dim_decision(&curr_stats, dim)) {
dim->state = DIM_APPLY_NEW_PROFILE;
schedule_work(&dim->work);
diff --git a/lib/dim/rdma_dim.c b/lib/dim/rdma_dim.c
index 15462d54758d3b77c66cf6e6e1afe6d3fca2f9f2..88f77948670782327b6fd717108e070ef33042ed 100644
--- a/lib/dim/rdma_dim.c
+++ b/lib/dim/rdma_dim.c
@@ -88,7 +88,8 @@ void rdma_dim(struct dim *dim, u64 completions)
nevents = curr_sample->event_ctr - dim->start_sample.event_ctr;
if (nevents < DIM_NEVENTS)
break;
- dim_calc_stats(&dim->start_sample, curr_sample, &curr_stats);
+ if (!dim_calc_stats(&dim->start_sample, curr_sample, &curr_stats))
+ break;
if (rdma_dim_decision(&curr_stats, dim)) {
dim->state = DIM_APPLY_NEW_PROFILE;
schedule_work(&dim->work);
diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c
index 57744704ff692ae4dd573ec025cf29935785900e..84d6dd5e5b1a23a2fddad3e0573ebf7b1924204c 100644
--- a/net/bridge/br_forward.c
+++ b/net/bridge/br_forward.c
@@ -42,7 +42,7 @@ int br_dev_queue_push_xmit(struct net *net, struct sock *sk, struct sk_buff *skb
eth_type_vlan(skb->protocol)) {
int depth;
- if (!__vlan_get_protocol(skb, skb->protocol, &depth))
+ if (!vlan_get_protocol_and_depth(skb, skb->protocol, &depth))
goto drop;
skb_set_network_header(skb, depth);
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 5662dff3d381a92b271d9cba38a28a6a8478c114..176eb58347461b160890ce2d6b2d3cbc7412e321 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -807,18 +807,21 @@ __poll_t datagram_poll(struct file *file, struct socket *sock,
{
struct sock *sk = sock->sk;
__poll_t mask;
+ u8 shutdown;
sock_poll_wait(file, sock, wait);
mask = 0;
/* exceptional events? */
- if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue))
+ if (READ_ONCE(sk->sk_err) ||
+ !skb_queue_empty_lockless(&sk->sk_error_queue))
mask |= EPOLLERR |
(sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0);
- if (sk->sk_shutdown & RCV_SHUTDOWN)
+ shutdown = READ_ONCE(sk->sk_shutdown);
+ if (shutdown & RCV_SHUTDOWN)
mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM;
- if (sk->sk_shutdown == SHUTDOWN_MASK)
+ if (shutdown == SHUTDOWN_MASK)
mask |= EPOLLHUP;
/* readable? */
@@ -827,10 +830,12 @@ __poll_t datagram_poll(struct file *file, struct socket *sock,
/* Connection-based need to check for termination and startup */
if (connection_based(sk)) {
- if (sk->sk_state == TCP_CLOSE)
+ int state = READ_ONCE(sk->sk_state);
+
+ if (state == TCP_CLOSE)
mask |= EPOLLHUP;
/* connection hasn't started yet? */
- if (sk->sk_state == TCP_SYN_SENT)
+ if (state == TCP_SYN_SENT)
return mask;
}
diff --git a/net/core/dev.c b/net/core/dev.c
index 735096d42c1d13999597a882370ca439e9389e24..b3c13e0419356b943e90b1f46dd7e035c6ec1a9c 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3335,7 +3335,7 @@ __be16 skb_network_protocol(struct sk_buff *skb, int *depth)
type = eth->h_proto;
}
- return __vlan_get_protocol(skb, type, depth);
+ return vlan_get_protocol_and_depth(skb, type, depth);
}
/* openvswitch calls this on rx path, so we need a different check.
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 26a586007d8b1ae39ab7a09eecf8575e04dadfeb..515ec5cdc79c1da535e490b4341397e34ce1b5fb 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5298,7 +5298,7 @@ bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off)
u32 csum_end = (u32)start + (u32)off + sizeof(__sum16);
u32 csum_start = skb_headroom(skb) + (u32)start;
- if (unlikely(csum_start > U16_MAX || csum_end > skb_headlen(skb))) {
+ if (unlikely(csum_start >= U16_MAX || csum_end > skb_headlen(skb))) {
net_warn_ratelimited("bad partial csum: csum=%u/%u headroom=%u headlen=%u\n",
start, off, skb_headroom(skb), skb_headlen(skb));
return false;
@@ -5306,7 +5306,7 @@ bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off)
skb->ip_summed = CHECKSUM_PARTIAL;
skb->csum_start = csum_start;
skb->csum_offset = off;
- skb_set_transport_header(skb, start);
+ skb->transport_header = csum_start;
return true;
}
EXPORT_SYMBOL_GPL(skb_partial_csum_set);
diff --git a/net/core/stream.c b/net/core/stream.c
index 434446ab14c578b2d4c4c0ff8467c7129f7c66d8..f5c4e47df16505571d575ff367b31d9ef6998bd6 100644
--- a/net/core/stream.c
+++ b/net/core/stream.c
@@ -73,8 +73,8 @@ int sk_stream_wait_connect(struct sock *sk, long *timeo_p)
add_wait_queue(sk_sleep(sk), &wait);
sk->sk_write_pending++;
done = sk_wait_event(sk, timeo_p,
- !sk->sk_err &&
- !((1 << sk->sk_state) &
+ !READ_ONCE(sk->sk_err) &&
+ !((1 << READ_ONCE(sk->sk_state)) &
~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)), &wait);
remove_wait_queue(sk_sleep(sk), &wait);
sk->sk_write_pending--;
@@ -87,9 +87,9 @@ EXPORT_SYMBOL(sk_stream_wait_connect);
* sk_stream_closing - Return 1 if we still have things to send in our buffers.
* @sk: socket to verify
*/
-static inline int sk_stream_closing(struct sock *sk)
+static int sk_stream_closing(const struct sock *sk)
{
- return (1 << sk->sk_state) &
+ return (1 << READ_ONCE(sk->sk_state)) &
(TCPF_FIN_WAIT1 | TCPF_CLOSING | TCPF_LAST_ACK);
}
@@ -142,8 +142,8 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p)
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
sk->sk_write_pending++;
- sk_wait_event(sk, ¤t_timeo, sk->sk_err ||
- (sk->sk_shutdown & SEND_SHUTDOWN) ||
+ sk_wait_event(sk, ¤t_timeo, READ_ONCE(sk->sk_err) ||
+ (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) ||
(sk_stream_memory_free(sk) &&
!vm_wait), &wait);
sk->sk_write_pending--;
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 940062e08f574fbfeed42f72fa8a4b5ce763110c..c4aab3aacbd89e35520583ab5e17b4e15e53b87e 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -894,7 +894,7 @@ int inet_shutdown(struct socket *sock, int how)
EPOLLHUP, even on eg. unconnected UDP sockets -- RR */
fallthrough;
default:
- sk->sk_shutdown |= how;
+ WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | how);
if (sk->sk_prot->shutdown)
sk->sk_prot->shutdown(sk, how);
break;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 20db115c38c492c010733d5a0a3efbb7dbbea13e..4d6392c16b7a5a9a853c27e3a4b258d000738304 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -498,6 +498,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
__poll_t mask;
struct sock *sk = sock->sk;
const struct tcp_sock *tp = tcp_sk(sk);
+ u8 shutdown;
int state;
sock_poll_wait(file, sock, wait);
@@ -540,9 +541,10 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
* NOTE. Check for TCP_CLOSE is added. The goal is to prevent
* blocking on fresh not-connected or disconnected socket. --ANK
*/
- if (sk->sk_shutdown == SHUTDOWN_MASK || state == TCP_CLOSE)
+ shutdown = READ_ONCE(sk->sk_shutdown);
+ if (shutdown == SHUTDOWN_MASK || state == TCP_CLOSE)
mask |= EPOLLHUP;
- if (sk->sk_shutdown & RCV_SHUTDOWN)
+ if (shutdown & RCV_SHUTDOWN)
mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP;
/* Connected or passive Fast Open socket? */
@@ -559,7 +561,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
if (tcp_stream_is_readable(sk, target))
mask |= EPOLLIN | EPOLLRDNORM;
- if (!(sk->sk_shutdown & SEND_SHUTDOWN)) {
+ if (!(shutdown & SEND_SHUTDOWN)) {
if (__sk_stream_is_writeable(sk, 1)) {
mask |= EPOLLOUT | EPOLLWRNORM;
} else { /* send SIGIO later */
@@ -2867,7 +2869,7 @@ void __tcp_close(struct sock *sk, long timeout)
int data_was_unread = 0;
int state;
- sk->sk_shutdown = SHUTDOWN_MASK;
+ WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK);
if (sk->sk_state == TCP_LISTEN) {
tcp_set_state(sk, TCP_CLOSE);
@@ -3119,7 +3121,7 @@ int tcp_disconnect(struct sock *sk, int flags)
inet_bhash2_reset_saddr(sk);
- sk->sk_shutdown = 0;
+ WRITE_ONCE(sk->sk_shutdown, 0);
sock_reset_flag(sk, SOCK_DONE);
tp->srtt_us = 0;
tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
@@ -4649,7 +4651,7 @@ void tcp_done(struct sock *sk)
if (req)
reqsk_fastopen_remove(sk, req, false);
- sk->sk_shutdown = SHUTDOWN_MASK;
+ WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK);
if (!sock_flag(sk, SOCK_DEAD))
sk->sk_state_change(sk);
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index ebf91751193706ccec1bb9cfac48be28b5e28337..2e9547467edbecbae7a8e01ab780de37064f6df3 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -168,7 +168,7 @@ static int tcp_msg_wait_data(struct sock *sk, struct sk_psock *psock,
sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
ret = sk_wait_event(sk, &timeo,
!list_empty(&psock->ingress_msg) ||
- !skb_queue_empty(&sk->sk_receive_queue), &wait);
+ !skb_queue_empty_lockless(&sk->sk_receive_queue), &wait);
sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
remove_wait_queue(sk_sleep(sk), &wait);
return ret;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index a057330d6f59d693cdf634dbd22f1243f8171f58..61b6710f337a3a5c24b3f399cc77a404b7e012f9 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4362,7 +4362,7 @@ void tcp_fin(struct sock *sk)
inet_csk_schedule_ack(sk);
- sk->sk_shutdown |= RCV_SHUTDOWN;
+ WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | RCV_SHUTDOWN);
sock_set_flag(sk, SOCK_DONE);
switch (sk->sk_state) {
@@ -6599,7 +6599,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
break;
tcp_set_state(sk, TCP_FIN_WAIT2);
- sk->sk_shutdown |= SEND_SHUTDOWN;
+ WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | SEND_SHUTDOWN);
sk_dst_confirm(sk);
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index da7fe94bea2eb8b6d1fe84bfdb8d1fa7cf5f6879..9ffbc667be6cf4c13d2f731e003510efeed8ee29 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -583,7 +583,8 @@ static int llc_ui_wait_for_disc(struct sock *sk, long timeout)
add_wait_queue(sk_sleep(sk), &wait);
while (1) {
- if (sk_wait_event(sk, &timeout, sk->sk_state == TCP_CLOSE, &wait))
+ if (sk_wait_event(sk, &timeout,
+ READ_ONCE(sk->sk_state) == TCP_CLOSE, &wait))
break;
rc = -ERESTARTSYS;
if (signal_pending(current))
@@ -603,7 +604,8 @@ static bool llc_ui_wait_for_conn(struct sock *sk, long timeout)
add_wait_queue(sk_sleep(sk), &wait);
while (1) {
- if (sk_wait_event(sk, &timeout, sk->sk_state != TCP_SYN_SENT, &wait))
+ if (sk_wait_event(sk, &timeout,
+ READ_ONCE(sk->sk_state) != TCP_SYN_SENT, &wait))
break;
if (signal_pending(current) || !timeout)
break;
@@ -622,7 +624,7 @@ static int llc_ui_wait_for_busy_core(struct sock *sk, long timeout)
while (1) {
rc = 0;
if (sk_wait_event(sk, &timeout,
- (sk->sk_shutdown & RCV_SHUTDOWN) ||
+ (READ_ONCE(sk->sk_shutdown) & RCV_SHUTDOWN) ||
(!llc_data_accept_state(llc->state) &&
!llc->remote_busy_flag &&
!llc->p_flag), &wait))
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index f0783e42108bab59cbf59e4296898ed3bffaf44c..5f76ae86a6561f6decc21c6d35e5311e7488c921 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -711,9 +711,11 @@ void nf_conntrack_destroy(struct nf_conntrack *nfct)
rcu_read_lock();
ct_hook = rcu_dereference(nf_ct_hook);
- BUG_ON(ct_hook == NULL);
- ct_hook->destroy(nfct);
+ if (ct_hook)
+ ct_hook->destroy(nfct);
rcu_read_unlock();
+
+ WARN_ON(!ct_hook);
}
EXPORT_SYMBOL(nf_conntrack_destroy);
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 57f6724c99a76763e212a53b4e29c969d3efa469..169e16fc2bceb1b611da209bd6b1250b125f1baf 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -1218,11 +1218,12 @@ static int __init nf_conntrack_standalone_init(void)
nf_conntrack_htable_size_user = nf_conntrack_htable_size;
#endif
+ nf_conntrack_init_end();
+
ret = register_pernet_subsys(&nf_conntrack_net_ops);
if (ret < 0)
goto out_pernet;
- nf_conntrack_init_end();
return 0;
out_pernet:
diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c
index c3563f0be26925836a48e699bd5d828edf51883a..680fe557686e42d3421a445b6c5472bd4056a65a 100644
--- a/net/netfilter/nft_chain_filter.c
+++ b/net/netfilter/nft_chain_filter.c
@@ -344,6 +344,12 @@ static void nft_netdev_event(unsigned long event, struct net_device *dev,
return;
}
+ /* UNREGISTER events are also happening on netns exit.
+ *
+ * Although nf_tables core releases all tables/chains, only this event
+ * handler provides guarantee that hook->ops.dev is still accessible,
+ * so we cannot skip exiting net namespaces.
+ */
__nft_release_basechain(ctx);
}
@@ -362,9 +368,6 @@ static int nf_tables_netdev_event(struct notifier_block *this,
event != NETDEV_CHANGENAME)
return NOTIFY_DONE;
- if (!check_net(ctx.net))
- return NOTIFY_DONE;
-
nft_net = nft_pernet(ctx.net);
mutex_lock(&nft_net->commit_mutex);
list_for_each_entry(table, &nft_net->tables, list) {
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 7ef8b9a1e30c5a87687899dfcfc014fc033bf572..c87804112d0c6e8010ef1257eb68da3cd48a3969 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1990,7 +1990,7 @@ static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
skb_free_datagram(sk, skb);
- if (nlk->cb_running &&
+ if (READ_ONCE(nlk->cb_running) &&
atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf / 2) {
ret = netlink_dump(sk);
if (ret) {
@@ -2302,7 +2302,7 @@ static int netlink_dump(struct sock *sk)
if (cb->done)
cb->done(cb);
- nlk->cb_running = false;
+ WRITE_ONCE(nlk->cb_running, false);
module = cb->module;
skb = cb->skb;
mutex_unlock(nlk->cb_mutex);
@@ -2365,7 +2365,7 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
goto error_put;
}
- nlk->cb_running = true;
+ WRITE_ONCE(nlk->cb_running, true);
nlk->dump_done_errno = INT_MAX;
mutex_unlock(nlk->cb_mutex);
@@ -2703,7 +2703,7 @@ static int netlink_native_seq_show(struct seq_file *seq, void *v)
nlk->groups ? (u32)nlk->groups[0] : 0,
sk_rmem_alloc_get(s),
sk_wmem_alloc_get(s),
- nlk->cb_running,
+ READ_ONCE(nlk->cb_running),
refcount_read(&s->sk_refcnt),
atomic_read(&s->sk_drops),
sock_i_ino(s)
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 640d94e34635b51709d51be27635d23b3c184d0c..94c6a1ffa459aab491d92fb4fd96d58fb0e00094 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1934,10 +1934,8 @@ static void packet_parse_headers(struct sk_buff *skb, struct socket *sock)
/* Move network header to the right position for VLAN tagged packets */
if (likely(skb->dev->type == ARPHRD_ETHER) &&
eth_type_vlan(skb->protocol) &&
- __vlan_get_protocol(skb, skb->protocol, &depth) != 0) {
- if (pskb_may_pull(skb, depth))
- skb_set_network_header(skb, depth);
- }
+ vlan_get_protocol_and_depth(skb, skb->protocol, &depth) != 0)
+ skb_set_network_header(skb, depth);
skb_probe_transport_header(skb);
}
diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c
index 31db7438857c9f81fd336bfce74c5c92b7d275c6..dbdf03e8aa5b55f29d71e9f7c28169cac358740f 100644
--- a/net/smc/smc_close.c
+++ b/net/smc/smc_close.c
@@ -67,8 +67,8 @@ static void smc_close_stream_wait(struct smc_sock *smc, long timeout)
rc = sk_wait_event(sk, &timeout,
!smc_tx_prepared_sends(&smc->conn) ||
- sk->sk_err == ECONNABORTED ||
- sk->sk_err == ECONNRESET ||
+ READ_ONCE(sk->sk_err) == ECONNABORTED ||
+ READ_ONCE(sk->sk_err) == ECONNRESET ||
smc->conn.killed,
&wait);
if (rc)
diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c
index 4380d32f5a5f96205d486dea4ff763435bc2e95d..9a2f3638d161d2ff7d7261835a5b13be63b11701 100644
--- a/net/smc/smc_rx.c
+++ b/net/smc/smc_rx.c
@@ -267,9 +267,9 @@ int smc_rx_wait(struct smc_sock *smc, long *timeo,
sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
add_wait_queue(sk_sleep(sk), &wait);
rc = sk_wait_event(sk, timeo,
- sk->sk_err ||
+ READ_ONCE(sk->sk_err) ||
cflags->peer_conn_abort ||
- sk->sk_shutdown & RCV_SHUTDOWN ||
+ READ_ONCE(sk->sk_shutdown) & RCV_SHUTDOWN ||
conn->killed ||
fcrit(conn),
&wait);
diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c
index f4b6a71ac488a40e1a36abe4562017fff7e98739..45128443f1f10ff8bea1dc65214c1db3beefc135 100644
--- a/net/smc/smc_tx.c
+++ b/net/smc/smc_tx.c
@@ -113,8 +113,8 @@ static int smc_tx_wait(struct smc_sock *smc, int flags)
break; /* at least 1 byte of free & no urgent data */
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
sk_wait_event(sk, &timeo,
- sk->sk_err ||
- (sk->sk_shutdown & SEND_SHUTDOWN) ||
+ READ_ONCE(sk->sk_err) ||
+ (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) ||
smc_cdc_rxed_any_close(conn) ||
(atomic_read(&conn->sndbuf_space) &&
!conn->urg_tx_pend),
diff --git a/net/socket.c b/net/socket.c
index a7b4b37d86df7a9232d582a14863c05b5fd34b68..b7e01d0fe0824d1f277c1fe70f68f09a10319832 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2911,7 +2911,7 @@ static int do_recvmmsg(int fd, struct mmsghdr __user *mmsg,
* error to return on the next call or if the
* app asks about it using getsockopt(SO_ERROR).
*/
- sock->sk->sk_err = -err;
+ WRITE_ONCE(sock->sk->sk_err, -err);
}
out_put:
fput_light(sock->file, fput_needed);
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 37edfe10f8c6ffea553a54b24b9513bd2e18d694..dd73d71c02a99df7acd7ce3fb0d4a96d1778171d 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -314,9 +314,9 @@ static void tsk_rej_rx_queue(struct sock *sk, int error)
tipc_sk_respond(sk, skb, error);
}
-static bool tipc_sk_connected(struct sock *sk)
+static bool tipc_sk_connected(const struct sock *sk)
{
- return sk->sk_state == TIPC_ESTABLISHED;
+ return READ_ONCE(sk->sk_state) == TIPC_ESTABLISHED;
}
/* tipc_sk_type_connectionless - check if the socket is datagram socket
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index b32c112984dd9567fd9d07cc6850f234c1914a43..f2e7302a4d96b9f7ddd4ddf9afb6cac5672886e6 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -111,7 +111,8 @@ int wait_on_pending_writer(struct sock *sk, long *timeo)
break;
}
- if (sk_wait_event(sk, timeo, !sk->sk_write_pending, &wait))
+ if (sk_wait_event(sk, timeo,
+ !READ_ONCE(sk->sk_write_pending), &wait))
break;
}
remove_wait_queue(sk_sleep(sk), &wait);
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index fb31e8a4409ed979e4443e7d3d392a5e0f2c424b..cc695c9f09ec24297bf214092ab170646306339b 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -603,7 +603,7 @@ static void unix_release_sock(struct sock *sk, int embrion)
/* Clear state */
unix_state_lock(sk);
sock_orphan(sk);
- sk->sk_shutdown = SHUTDOWN_MASK;
+ WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK);
path = u->path;
u->path.dentry = NULL;
u->path.mnt = NULL;
@@ -628,7 +628,7 @@ static void unix_release_sock(struct sock *sk, int embrion)
if (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) {
unix_state_lock(skpair);
/* No more writes */
- skpair->sk_shutdown = SHUTDOWN_MASK;
+ WRITE_ONCE(skpair->sk_shutdown, SHUTDOWN_MASK);
if (!skb_queue_empty(&sk->sk_receive_queue) || embrion)
WRITE_ONCE(skpair->sk_err, ECONNRESET);
unix_state_unlock(skpair);
@@ -1442,7 +1442,7 @@ static long unix_wait_for_peer(struct sock *other, long timeo)
sched = !sock_flag(other, SOCK_DEAD) &&
!(other->sk_shutdown & RCV_SHUTDOWN) &&
- unix_recvq_full(other);
+ unix_recvq_full_lockless(other);
unix_state_unlock(other);
@@ -3008,7 +3008,7 @@ static int unix_shutdown(struct socket *sock, int mode)
++mode;
unix_state_lock(sk);
- sk->sk_shutdown |= mode;
+ WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | mode);
other = unix_peer(sk);
if (other)
sock_hold(other);
@@ -3028,7 +3028,7 @@ static int unix_shutdown(struct socket *sock, int mode)
if (mode&SEND_SHUTDOWN)
peer_mode |= RCV_SHUTDOWN;
unix_state_lock(other);
- other->sk_shutdown |= peer_mode;
+ WRITE_ONCE(other->sk_shutdown, other->sk_shutdown | peer_mode);
unix_state_unlock(other);
other->sk_state_change(other);
if (peer_mode == SHUTDOWN_MASK)
@@ -3160,16 +3160,18 @@ static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wa
{
struct sock *sk = sock->sk;
__poll_t mask;
+ u8 shutdown;
sock_poll_wait(file, sock, wait);
mask = 0;
+ shutdown = READ_ONCE(sk->sk_shutdown);
/* exceptional events? */
if (READ_ONCE(sk->sk_err))
mask |= EPOLLERR;
- if (sk->sk_shutdown == SHUTDOWN_MASK)
+ if (shutdown == SHUTDOWN_MASK)
mask |= EPOLLHUP;
- if (sk->sk_shutdown & RCV_SHUTDOWN)
+ if (shutdown & RCV_SHUTDOWN)
mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM;
/* readable? */
@@ -3203,9 +3205,11 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock,
struct sock *sk = sock->sk, *other;
unsigned int writable;
__poll_t mask;
+ u8 shutdown;
sock_poll_wait(file, sock, wait);
mask = 0;
+ shutdown = READ_ONCE(sk->sk_shutdown);
/* exceptional events? */
if (READ_ONCE(sk->sk_err) ||
@@ -3213,9 +3217,9 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock,
mask |= EPOLLERR |
(sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0);
- if (sk->sk_shutdown & RCV_SHUTDOWN)
+ if (shutdown & RCV_SHUTDOWN)
mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM;
- if (sk->sk_shutdown == SHUTDOWN_MASK)
+ if (shutdown == SHUTDOWN_MASK)
mask |= EPOLLHUP;
/* readable? */
diff --git a/tools/testing/selftests/drivers/net/bonding/bond_options.sh b/tools/testing/selftests/drivers/net/bonding/bond_options.sh
index db29a3146a8611ab5891e615dc1925916c4a6074..607ba5c38977f20dfb5b2133ce3c0a71b31cf59b 100755
--- a/tools/testing/selftests/drivers/net/bonding/bond_options.sh
+++ b/tools/testing/selftests/drivers/net/bonding/bond_options.sh
@@ -6,6 +6,7 @@
ALL_TESTS="
prio
arp_validate
+ num_grat_arp
"
REQUIRE_MZ=no
@@ -255,6 +256,55 @@ arp_validate()
arp_validate_ns "active-backup"
}
+garp_test()
+{
+ local param="$1"
+ local active_slave exp_num real_num i
+ RET=0
+
+ # create bond
+ bond_reset "${param}"
+
+ bond_check_connection
+ [ $RET -ne 0 ] && log_test "num_grat_arp" "$retmsg"
+
+
+ # Add tc rules to count GARP number
+ for i in $(seq 0 2); do
+ tc -n ${g_ns} filter add dev s$i ingress protocol arp pref 1 handle 101 \
+ flower skip_hw arp_op request arp_sip ${s_ip4} arp_tip ${s_ip4} action pass
+ done
+
+ # Do failover
+ active_slave=$(cmd_jq "ip -n ${s_ns} -d -j link show bond0" ".[].linkinfo.info_data.active_slave")
+ ip -n ${s_ns} link set ${active_slave} down
+
+ exp_num=$(echo "${param}" | cut -f6 -d ' ')
+ sleep $((exp_num + 2))
+
+ active_slave=$(cmd_jq "ip -n ${s_ns} -d -j link show bond0" ".[].linkinfo.info_data.active_slave")
+
+ # check result
+ real_num=$(tc_rule_handle_stats_get "dev s${active_slave#eth} ingress" 101 ".packets" "-n ${g_ns}")
+ if [ "${real_num}" -ne "${exp_num}" ]; then
+ echo "$real_num garp packets sent on active slave ${active_slave}"
+ RET=1
+ fi
+
+ for i in $(seq 0 2); do
+ tc -n ${g_ns} filter del dev s$i ingress
+ done
+}
+
+num_grat_arp()
+{
+ local val
+ for val in 10 20 30 50; do
+ garp_test "mode active-backup miimon 100 num_grat_arp $val peer_notify_delay 1000"
+ log_test "num_grat_arp" "active-backup miimon num_grat_arp $val"
+ done
+}
+
trap cleanup EXIT
setup_prepare
diff --git a/tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh b/tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh
index 4045ca97fb22d986369bd80b722561cfedd0e013..69ab99a560434a7a7ddd6a99662896d72e94c3ca 100644
--- a/tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh
+++ b/tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh
@@ -61,6 +61,8 @@ server_create()
ip -n ${g_ns} link set s${i} up
ip -n ${g_ns} link set s${i} master br0
ip -n ${s_ns} link set eth${i} master bond0
+
+ tc -n ${g_ns} qdisc add dev s${i} clsact
done
ip -n ${s_ns} link set bond0 up
diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 057c3d0ad62054f767bb2785232bbb25d8f1cf24..9ddb68dd6a089a42239554e4bd670000290f5b49 100755
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -791,8 +791,9 @@ tc_rule_handle_stats_get()
local id=$1; shift
local handle=$1; shift
local selector=${1:-.packets}; shift
+ local netns=${1:-""}; shift
- tc -j -s filter show $id \
+ tc $netns -j -s filter show $id \
| jq ".[] | select(.options.handle == $handle) | \
.options.actions[0].stats$selector"
}
diff --git a/tools/testing/selftests/netfilter/nft_flowtable.sh b/tools/testing/selftests/netfilter/nft_flowtable.sh
index 7060bae04ec87d9ecd59d6643becb6452fdf22d5..a32f490f753996bff69c44e92269b5cec0056575 100755
--- a/tools/testing/selftests/netfilter/nft_flowtable.sh
+++ b/tools/testing/selftests/netfilter/nft_flowtable.sh
@@ -188,6 +188,26 @@ if [ $? -ne 0 ]; then
exit $ksft_skip
fi
+ip netns exec $ns2 nft -f - <<EOF
+table inet filter {
+ counter ip4dscp0 { }
+ counter ip4dscp3 { }
+
+ chain input {
+ type filter hook input priority 0; policy accept;
+ meta l4proto tcp goto {
+ ip dscp cs3 counter name ip4dscp3 accept
+ ip dscp 0 counter name ip4dscp0 accept
+ }
+ }
+}
+EOF
+
+if [ $? -ne 0 ]; then
+ echo "SKIP: Could not load nft ruleset"
+ exit $ksft_skip
+fi
+
# test basic connectivity
if ! ip netns exec $ns1 ping -c 1 -q 10.0.2.99 > /dev/null; then
echo "ERROR: $ns1 cannot reach ns2" 1>&2
@@ -255,6 +275,60 @@ check_counters()
fi
}
+check_dscp()
+{
+ local what=$1
+ local ok=1
+
+ local counter=$(ip netns exec $ns2 nft reset counter inet filter ip4dscp3 | grep packets)
+
+ local pc4=${counter%*bytes*}
+ local pc4=${pc4#*packets}
+
+ local counter=$(ip netns exec $ns2 nft reset counter inet filter ip4dscp0 | grep packets)
+ local pc4z=${counter%*bytes*}
+ local pc4z=${pc4z#*packets}
+
+ case "$what" in
+ "dscp_none")
+ if [ $pc4 -gt 0 ] || [ $pc4z -eq 0 ]; then
+ echo "FAIL: dscp counters do not match, expected dscp3 == 0, dscp0 > 0, but got $pc4,$pc4z" 1>&2
+ ret=1
+ ok=0
+ fi
+ ;;
+ "dscp_fwd")
+ if [ $pc4 -eq 0 ] || [ $pc4z -eq 0 ]; then
+ echo "FAIL: dscp counters do not match, expected dscp3 and dscp0 > 0 but got $pc4,$pc4z" 1>&2
+ ret=1
+ ok=0
+ fi
+ ;;
+ "dscp_ingress")
+ if [ $pc4 -eq 0 ] || [ $pc4z -gt 0 ]; then
+ echo "FAIL: dscp counters do not match, expected dscp3 > 0, dscp0 == 0 but got $pc4,$pc4z" 1>&2
+ ret=1
+ ok=0
+ fi
+ ;;
+ "dscp_egress")
+ if [ $pc4 -eq 0 ] || [ $pc4z -gt 0 ]; then
+ echo "FAIL: dscp counters do not match, expected dscp3 > 0, dscp0 == 0 but got $pc4,$pc4z" 1>&2
+ ret=1
+ ok=0
+ fi
+ ;;
+ *)
+ echo "FAIL: Unknown DSCP check" 1>&2
+ ret=1
+ ok=0
+ esac
+
+ if [ $ok -eq 1 ] ;then
+ echo "PASS: $what: dscp packet counters match"
+ fi
+}
+
check_transfer()
{
in=$1
@@ -286,17 +360,26 @@ test_tcp_forwarding_ip()
ip netns exec $nsa nc -w 4 "$dstip" "$dstport" < "$nsin" > "$ns1out" &
cpid=$!
- sleep 3
+ sleep 1
- if ps -p $lpid > /dev/null;then
+ prev="$(ls -l $ns1out $ns2out)"
+ sleep 1
+
+ while [[ "$prev" != "$(ls -l $ns1out $ns2out)" ]]; do
+ sleep 1;
+ prev="$(ls -l $ns1out $ns2out)"
+ done
+
+ if test -d /proc/"$lpid"/; then
kill $lpid
fi
- if ps -p $cpid > /dev/null;then
+ if test -d /proc/"$cpid"/; then
kill $cpid
fi
- wait
+ wait $lpid
+ wait $cpid
if ! check_transfer "$nsin" "$ns2out" "ns1 -> ns2"; then
lret=1
@@ -316,6 +399,51 @@ test_tcp_forwarding()
return $?
}
+test_tcp_forwarding_set_dscp()
+{
+ check_dscp "dscp_none"
+
+ip netns exec $nsr1 nft -f - <<EOF
+table netdev dscpmangle {
+ chain setdscp0 {
+ type filter hook ingress device "veth0" priority 0; policy accept
+ ip dscp set cs3
+ }
+}
+EOF
+if [ $? -eq 0 ]; then
+ test_tcp_forwarding_ip "$1" "$2" 10.0.2.99 12345
+ check_dscp "dscp_ingress"
+
+ ip netns exec $nsr1 nft delete table netdev dscpmangle
+else
+ echo "SKIP: Could not load netdev:ingress for veth0"
+fi
+
+ip netns exec $nsr1 nft -f - <<EOF
+table netdev dscpmangle {
+ chain setdscp0 {
+ type filter hook egress device "veth1" priority 0; policy accept
+ ip dscp set cs3
+ }
+}
+EOF
+if [ $? -eq 0 ]; then
+ test_tcp_forwarding_ip "$1" "$2" 10.0.2.99 12345
+ check_dscp "dscp_egress"
+
+ ip netns exec $nsr1 nft flush table netdev dscpmangle
+else
+ echo "SKIP: Could not load netdev:egress for veth1"
+fi
+
+ # partial. If flowtable really works, then both dscp-is-0 and dscp-is-cs3
+ # counters should have seen packets (before and after ft offload kicks in).
+ ip netns exec $nsr1 nft -a insert rule inet filter forward ip dscp set cs3
+ test_tcp_forwarding_ip "$1" "$2" 10.0.2.99 12345
+ check_dscp "dscp_fwd"
+}
+
test_tcp_forwarding_nat()
{
local lret
@@ -385,6 +513,11 @@ table ip nat {
}
EOF
+if ! test_tcp_forwarding_set_dscp $ns1 $ns2 0 ""; then
+ echo "FAIL: flow offload for ns1/ns2 with dscp update" 1>&2
+ exit 0
+fi
+
if ! test_tcp_forwarding_nat $ns1 $ns2 0 ""; then
echo "FAIL: flow offload for ns1/ns2 with NAT" 1>&2
ip netns exec $nsr1 nft list ruleset
@@ -489,8 +622,8 @@ ip -net $nsr1 addr add 10.0.1.1/24 dev veth0
ip -net $nsr1 addr add dead:1::1/64 dev veth0
ip -net $nsr1 link set up dev veth0
-KEY_SHA="0x"$(ps -xaf | sha1sum | cut -d " " -f 1)
-KEY_AES="0x"$(ps -xaf | md5sum | cut -d " " -f 1)
+KEY_SHA="0x"$(ps -af | sha1sum | cut -d " " -f 1)
+KEY_AES="0x"$(ps -af | md5sum | cut -d " " -f 1)
SPI1=$RANDOM
SPI2=$RANDOM