summaryrefslogtreecommitdiff
path: root/net/ipv4/tcp_timer.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2025-03-27 07:48:21 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2025-03-27 07:48:21 +0300
commit1a9239bb4253f9076b5b4b2a1a4e8d7defd77a95 (patch)
tree286dda5e84757594218e684b94b01b3a3cac15a2 /net/ipv4/tcp_timer.c
parente61f33273ca755b3e2ebee4520a76097199dc7a8 (diff)
parent023b1e9d265ca0662111a9df23d22b4632717a8a (diff)
downloadlinux-1a9239bb4253f9076b5b4b2a1a4e8d7defd77a95.tar.xz
Merge tag 'net-next-6.15' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from Jakub Kicinski: "Core & protocols: - Continue Netlink conversions to per-namespace RTNL lock (IPv4 routing, routing rules, routing next hops, ARP ioctls) - Continue extending the use of netdev instance locks. As a driver opt-in protect queue operations and (in due course) ethtool operations with the instance lock and not RTNL lock. - Support collecting TCP timestamps (data submitted, sent, acked) in BPF, allowing for transparent (to the application) and lower overhead tracking of TCP RPC performance. - Tweak existing networking Rx zero-copy infra to support zero-copy Rx via io_uring. - Optimize MPTCP performance in single subflow mode by 29%. - Enable GRO on packets which went thru XDP CPU redirect (were queued for processing on a different CPU). Improving TCP stream performance up to 2x. - Improve performance of contended connect() by 200% by searching for an available 4-tuple under RCU rather than a spin lock. Bring an additional 229% improvement by tweaking hash distribution. - Avoid unconditionally touching sk_tsflags on RX, improving performance under UDP flood by as much as 10%. - Avoid skb_clone() dance in ping_rcv() to improve performance under ping flood. - Avoid FIB lookup in netfilter if socket is available, 20% perf win. - Rework network device creation (in-kernel) API to more clearly identify network namespaces and their roles. There are up to 4 namespace roles but we used to have just 2 netns pointer arguments, interpreted differently based on context. - Use sysfs_break_active_protection() instead of trylock to avoid deadlocks between unregistering objects and sysfs access. - Add a new sysctl and sockopt for capping max retransmit timeout in TCP. - Support masking port and DSCP in routing rule matches. - Support dumping IPv4 multicast addresses with RTM_GETMULTICAST. - Support specifying at what time packet should be sent on AF_XDP sockets. - Expose TCP ULP diagnostic info (for TLS and MPTCP) to non-admin users. - Add Netlink YAML spec for WiFi (nl80211) and conntrack. - Introduce EXPORT_IPV6_MOD() and EXPORT_IPV6_MOD_GPL() for symbols which only need to be exported when IPv6 support is built as a module. - Age FDB entries based on Rx not Tx traffic in VxLAN, similar to normal bridging. - Allow users to specify source port range for GENEVE tunnels. - netconsole: allow attaching kernel release, CPU ID and task name to messages as metadata Driver API: - Continue rework / fixing of Energy Efficient Ethernet (EEE) across the SW layers. Delegate the responsibilities to phylink where possible. Improve its handling in phylib. - Support symmetric OR-XOR RSS hashing algorithm. - Support tracking and preserving IRQ affinity by NAPI itself. - Support loopback mode speed selection for interface selftests. Device drivers: - Remove the IBM LCS driver for s390 - Remove the sb1000 cable modem driver - Add support for SFP module access over SMBus - Add MCTP transport driver for MCTP-over-USB - Enable XDP metadata support in multiple drivers - Ethernet high-speed NICs: - Broadcom (bnxt): - add PCIe TLP Processing Hints (TPH) support for new AMD platforms - support dumping RoCE queue state for debug - opt into instance locking - Intel (100G, ice, idpf): - ice: rework MSI-X IRQ management and distribution - ice: support for E830 devices - iavf: add support for Rx timestamping - iavf: opt into instance locking - nVidia/Mellanox: - mlx4: use page pool memory allocator for Rx - mlx5: support for one PTP device per hardware clock - mlx5: support for 200Gbps per-lane link modes - mlx5: move IPSec policy check after decryption - AMD/Solarflare: - support FW flashing via devlink - Cisco (enic): - use page pool memory allocator for Rx - enable 32, 64 byte CQEs - get max rx/tx ring size from the device - Meta (fbnic): - support flow steering and RSS configuration - report queue stats - support TCP segmentation - support IRQ coalescing - support ring size configuration - Marvell/Cavium: - support AF_XDP - Wangxun: - support for PTP clock and timestamping - Huawei (hibmcge): - checksum offload - add more statistics - Ethernet virtual: - VirtIO net: - aggressively suppress Tx completions, improve perf by 96% with 1 CPU and 55% with 2 CPUs - expose NAPI to IRQ mapping and persist NAPI settings - Google (gve): - support XDP in DQO RDA Queue Format - opt into instance locking - Microsoft vNIC: - support BIG TCP - Ethernet NICs consumer, and embedded: - Synopsys (stmmac): - cleanup Tx and Tx clock setting and other link-focused cleanups - enable SGMII and 2500BASEX mode switching for Intel platforms - support Sophgo SG2044 - Broadcom switches (b53): - support for BCM53101 - TI: - iep: add perout configuration support - icssg: support XDP - Cadence (macb): - implement BQL - Xilinx (axinet): - support dynamic IRQ moderation and changing coalescing at runtime - implement BQL - report standard stats - MediaTek: - support phylink managed EEE - Intel: - igc: don't restart the interface on every XDP program change - RealTek (r8169): - support reading registers of internal PHYs directly - increase max jumbo packet size on RTL8125/RTL8126 - Airoha: - support for RISC-V NPU packet processing unit - enable scatter-gather and support MTU up to 9kB - Tehuti (tn40xx): - support cards with TN4010 MAC and an Aquantia AQR105 PHY - Ethernet PHYs: - support for TJA1102S, TJA1121 - dp83tg720: add randomized polling intervals for link detection - dp83822: support changing the transmit amplitude voltage - support for LEDs on 88q2xxx - CAN: - canxl: support Remote Request Substitution bit access - flexcan: add S32G2/S32G3 SoC - WiFi: - remove cooked monitor support - strict mode for better AP testing - basic EPCS support - OMI RX bandwidth reduction support - batman-adv: add support for jumbo frames - WiFi drivers: - RealTek (rtw88): - support RTL8814AE and RTL8814AU - RealTek (rtw89): - switch using wiphy_lock and wiphy_work - add BB context to manipulate two PHY as preparation of MLO - improve BT-coexistence mechanism to play A2DP smoothly - Intel (iwlwifi): - add new iwlmld sub-driver for latest HW/FW combinations - MediaTek (mt76): - preparation for mt7996 Multi-Link Operation (MLO) support - Qualcomm/Atheros (ath12k): - continued work on MLO - Silabs (wfx): - Wake-on-WLAN support - Bluetooth: - add support for skb TX SND/COMPLETION timestamping - hci_core: enable buffer flow control for SCO/eSCO - coredump: log devcd dumps into the monitor - Bluetooth drivers: - intel: add support to configure TX power - nxp: handle bootloader error during cmd5 and cmd7" * tag 'net-next-6.15' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1681 commits) unix: fix up for "apparmor: add fine grained af_unix mediation" mctp: Fix incorrect tx flow invalidation condition in mctp-i2c net: usb: asix: ax88772: Increase phy_name size net: phy: Introduce PHY_ID_SIZE — minimum size for PHY ID string net: libwx: fix Tx L4 checksum net: libwx: fix Tx descriptor content for some tunnel packets atm: Fix NULL pointer dereference net: tn40xx: add pci-id of the aqr105-based Tehuti TN4010 cards net: tn40xx: prepare tn40xx driver to find phy of the TN9510 card net: tn40xx: create swnode for mdio and aqr105 phy and add to mdiobus net: phy: aquantia: add essential functions to aqr105 driver net: phy: aquantia: search for firmware-name in fwnode net: phy: aquantia: add probe function to aqr105 for firmware loading net: phy: Add swnode support to mdiobus_scan gve: add XDP DROP and PASS support for DQ gve: update XDP allocation path support RX buffer posting gve: merge packet buffer size fields gve: update GQ RX to use buf_size gve: introduce config-based allocation for XDP gve: remove xdp_xsk_done and xdp_xsk_wakeup statistics ...
Diffstat (limited to 'net/ipv4/tcp_timer.c')
-rw-r--r--net/ipv4/tcp_timer.c72
1 files changed, 42 insertions, 30 deletions
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index e7a75afa995d..e4c616bbd727 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -109,7 +109,7 @@ static int tcp_out_of_resources(struct sock *sk, bool do_reset)
/* If peer does not open window for long time, or did not transmit
* anything for long time, penalize it. */
- if ((s32)(tcp_jiffies32 - tp->lsndtime) > 2*TCP_RTO_MAX || !do_reset)
+ if ((s32)(tcp_jiffies32 - tp->lsndtime) > 2*tcp_rto_max(sk) || !do_reset)
shift++;
/* If some dubious ICMP arrived, penalize even more. */
@@ -189,12 +189,12 @@ static unsigned int tcp_model_timeout(struct sock *sk,
{
unsigned int linear_backoff_thresh, timeout;
- linear_backoff_thresh = ilog2(TCP_RTO_MAX / rto_base);
+ linear_backoff_thresh = ilog2(tcp_rto_max(sk) / rto_base);
if (boundary <= linear_backoff_thresh)
timeout = ((2 << boundary) - 1) * rto_base;
else
timeout = ((2 << linear_backoff_thresh) - 1) * rto_base +
- (boundary - linear_backoff_thresh) * TCP_RTO_MAX;
+ (boundary - linear_backoff_thresh) * tcp_rto_max(sk);
return jiffies_to_msecs(timeout);
}
/**
@@ -268,7 +268,7 @@ static int tcp_write_timeout(struct sock *sk)
retry_until = READ_ONCE(net->ipv4.sysctl_tcp_retries2);
if (sock_flag(sk, SOCK_DEAD)) {
- const bool alive = icsk->icsk_rto < TCP_RTO_MAX;
+ const bool alive = icsk->icsk_rto < tcp_rto_max(sk);
retry_until = tcp_orphan_retries(sk, alive);
do_reset = alive ||
@@ -322,8 +322,9 @@ void tcp_delack_timer_handler(struct sock *sk)
if (!(icsk->icsk_ack.pending & ICSK_ACK_TIMER))
return;
- if (time_after(icsk->icsk_ack.timeout, jiffies)) {
- sk_reset_timer(sk, &icsk->icsk_delack_timer, icsk->icsk_ack.timeout);
+ if (time_after(icsk_delack_timeout(icsk), jiffies)) {
+ sk_reset_timer(sk, &icsk->icsk_delack_timer,
+ icsk_delack_timeout(icsk));
return;
}
icsk->icsk_ack.pending &= ~ICSK_ACK_TIMER;
@@ -416,7 +417,8 @@ static void tcp_probe_timer(struct sock *sk)
}
max_probes = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_retries2);
if (sock_flag(sk, SOCK_DEAD)) {
- const bool alive = inet_csk_rto_backoff(icsk, TCP_RTO_MAX) < TCP_RTO_MAX;
+ unsigned int rto_max = tcp_rto_max(sk);
+ const bool alive = inet_csk_rto_backoff(icsk, rto_max) < rto_max;
max_probes = tcp_orphan_retries(sk, alive);
if (!alive && icsk->icsk_backoff >= max_probes)
@@ -481,8 +483,8 @@ static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req)
tcp_update_rto_stats(sk);
if (!tp->retrans_stamp)
tp->retrans_stamp = tcp_time_stamp_ts(tp);
- inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
- req->timeout << req->num_timeout, TCP_RTO_MAX);
+ tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
+ req->timeout << req->num_timeout, false);
}
static bool tcp_rtx_probe0_timed_out(const struct sock *sk,
@@ -492,7 +494,7 @@ static bool tcp_rtx_probe0_timed_out(const struct sock *sk,
const struct inet_connection_sock *icsk = inet_csk(sk);
u32 user_timeout = READ_ONCE(icsk->icsk_user_timeout);
const struct tcp_sock *tp = tcp_sk(sk);
- int timeout = TCP_RTO_MAX * 2;
+ int timeout = tcp_rto_max(sk) * 2;
s32 rcv_delta;
if (user_timeout) {
@@ -508,7 +510,7 @@ static bool tcp_rtx_probe0_timed_out(const struct sock *sk,
* and tp->rcv_tstamp might very well have been written recently.
* rcv_delta can thus be negative.
*/
- rcv_delta = icsk->icsk_timeout - tp->rcv_tstamp;
+ rcv_delta = icsk_timeout(icsk) - tp->rcv_tstamp;
if (rcv_delta <= timeout)
return false;
@@ -626,9 +628,9 @@ void tcp_retransmit_timer(struct sock *sk)
/* Retransmission failed because of local congestion,
* Let senders fight for local resources conservatively.
*/
- inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
- TCP_RESOURCE_PROBE_INTERVAL,
- TCP_RTO_MAX);
+ tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
+ TCP_RESOURCE_PROBE_INTERVAL,
+ false);
goto out;
}
@@ -665,7 +667,7 @@ out_reset_timer:
icsk->icsk_backoff = 0;
icsk->icsk_rto = clamp(__tcp_set_rto(tp),
tcp_rto_min(sk),
- TCP_RTO_MAX);
+ tcp_rto_max(sk));
} else if (sk->sk_state != TCP_SYN_SENT ||
tp->total_rto >
READ_ONCE(net->ipv4.sysctl_tcp_syn_linear_timeouts)) {
@@ -673,10 +675,10 @@ out_reset_timer:
* activated.
*/
icsk->icsk_backoff++;
- icsk->icsk_rto = min(icsk->icsk_rto << 1, TCP_RTO_MAX);
+ icsk->icsk_rto = min(icsk->icsk_rto << 1, tcp_rto_max(sk));
}
- inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
- tcp_clamp_rto_to_user_timeout(sk), TCP_RTO_MAX);
+ tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
+ tcp_clamp_rto_to_user_timeout(sk), false);
if (retransmits_timed_out(sk, READ_ONCE(net->ipv4.sysctl_tcp_retries1) + 1, 0))
__sk_dst_reset(sk);
@@ -684,7 +686,8 @@ out:;
}
/* Called with bottom-half processing disabled.
- Called by tcp_write_timer() */
+ * Called by tcp_write_timer() and tcp_release_cb().
+ */
void tcp_write_timer_handler(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
@@ -694,11 +697,11 @@ void tcp_write_timer_handler(struct sock *sk)
!icsk->icsk_pending)
return;
- if (time_after(icsk->icsk_timeout, jiffies)) {
- sk_reset_timer(sk, &icsk->icsk_retransmit_timer, icsk->icsk_timeout);
+ if (time_after(icsk_timeout(icsk), jiffies)) {
+ sk_reset_timer(sk, &icsk->icsk_retransmit_timer,
+ icsk_timeout(icsk));
return;
}
-
tcp_mstamp_refresh(tcp_sk(sk));
event = icsk->icsk_pending;
@@ -749,7 +752,17 @@ void tcp_syn_ack_timeout(const struct request_sock *req)
__NET_INC_STATS(net, LINUX_MIB_TCPTIMEOUTS);
}
-EXPORT_SYMBOL(tcp_syn_ack_timeout);
+EXPORT_IPV6_MOD(tcp_syn_ack_timeout);
+
+void tcp_reset_keepalive_timer(struct sock *sk, unsigned long len)
+{
+ sk_reset_timer(sk, &sk->sk_timer, jiffies + len);
+}
+
+static void tcp_delete_keepalive_timer(struct sock *sk)
+{
+ sk_stop_timer(sk, &sk->sk_timer);
+}
void tcp_set_keepalive(struct sock *sk, int val)
{
@@ -757,14 +770,13 @@ void tcp_set_keepalive(struct sock *sk, int val)
return;
if (val && !sock_flag(sk, SOCK_KEEPOPEN))
- inet_csk_reset_keepalive_timer(sk, keepalive_time_when(tcp_sk(sk)));
+ tcp_reset_keepalive_timer(sk, keepalive_time_when(tcp_sk(sk)));
else if (!val)
- inet_csk_delete_keepalive_timer(sk);
+ tcp_delete_keepalive_timer(sk);
}
-EXPORT_SYMBOL_GPL(tcp_set_keepalive);
-
+EXPORT_IPV6_MOD_GPL(tcp_set_keepalive);
-static void tcp_keepalive_timer (struct timer_list *t)
+static void tcp_keepalive_timer(struct timer_list *t)
{
struct sock *sk = from_timer(sk, t, sk_timer);
struct inet_connection_sock *icsk = inet_csk(sk);
@@ -775,7 +787,7 @@ static void tcp_keepalive_timer (struct timer_list *t)
bh_lock_sock(sk);
if (sock_owned_by_user(sk)) {
/* Try again later. */
- inet_csk_reset_keepalive_timer (sk, HZ/20);
+ tcp_reset_keepalive_timer(sk, HZ/20);
goto out;
}
@@ -841,7 +853,7 @@ static void tcp_keepalive_timer (struct timer_list *t)
}
resched:
- inet_csk_reset_keepalive_timer (sk, elapsed);
+ tcp_reset_keepalive_timer(sk, elapsed);
goto out;
death: