summaryrefslogtreecommitdiff
path: root/net/unix/af_unix.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2022-10-04 13:38:03 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2022-10-04 13:38:03 -0700
commit0326074ff4652329f2a1a9c8685104576bd8d131 (patch)
tree9a7574c7ccb05bf4c7cb34fc5a65457bb8f495cb /net/unix/af_unix.c
parent522667b24f08009591c90e75bfe2ffb67f555498 (diff)
parent681bf011b9b5989c6e9db6beb64494918aab9a43 (diff)
downloadlwn-0326074ff4652329f2a1a9c8685104576bd8d131.tar.gz
lwn-0326074ff4652329f2a1a9c8685104576bd8d131.zip
Merge tag 'net-next-6.1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from Jakub Kicinski: "Core: - Introduce and use a single page frag cache for allocating small skb heads, clawing back the 10-20% performance regression in UDP flood test from previous fixes. - Run packets which already went thru HW coalescing thru SW GRO. This significantly improves TCP segment coalescing and simplifies deployments as different workloads benefit from HW or SW GRO. - Shrink the size of the base zero-copy send structure. - Move TCP init under a new slow / sleepable version of DO_ONCE(). BPF: - Add BPF-specific, any-context-safe memory allocator. - Add helpers/kfuncs for PKCS#7 signature verification from BPF programs. - Define a new map type and related helpers for user space -> kernel communication over a ring buffer (BPF_MAP_TYPE_USER_RINGBUF). - Allow targeting BPF iterators to loop through resources of one task/thread. - Add ability to call selected destructive functions. Expose crash_kexec() to allow BPF to trigger a kernel dump. Use CAP_SYS_BOOT check on the loading process to judge permissions. - Enable BPF to collect custom hierarchical cgroup stats efficiently by integrating with the rstat framework. - Support struct arguments for trampoline based programs. Only structs with size <= 16B and x86 are supported. - Invoke cgroup/connect{4,6} programs for unprivileged ICMP ping sockets (instead of just TCP and UDP sockets). - Add a helper for accessing CLOCK_TAI for time sensitive network related programs. - Support accessing network tunnel metadata's flags. - Make TCP SYN ACK RTO tunable by BPF programs with TCP Fast Open. - Add support for writing to Netfilter's nf_conn:mark. Protocols: - WiFi: more Extremely High Throughput (EHT) and Multi-Link Operation (MLO) work (802.11be, WiFi 7). - vsock: improve support for SO_RCVLOWAT. - SMC: support SO_REUSEPORT. - Netlink: define and document how to use netlink in a "modern" way. Support reporting missing attributes via extended ACK. - IPSec: support collect metadata mode for xfrm interfaces. - TCPv6: send consistent autoflowlabel in SYN_RECV state and RST packets. - TCP: introduce optional per-netns connection hash table to allow better isolation between namespaces (opt-in, at the cost of memory and cache pressure). - MPTCP: support TCP_FASTOPEN_CONNECT. - Add NEXT-C-SID support in Segment Routing (SRv6) End behavior. - Adjust IP_UNICAST_IF sockopt behavior for connected UDP sockets. - Open vSwitch: - Allow specifying ifindex of new interfaces. - Allow conntrack and metering in non-initial user namespace. - TLS: support the Korean ARIA-GCM crypto algorithm. - Remove DECnet support. Driver API: - Allow selecting the conduit interface used by each port in DSA switches, at runtime. - Ethernet Power Sourcing Equipment and Power Device support. - Add tc-taprio support for queueMaxSDU parameter, i.e. setting per traffic class max frame size for time-based packet schedules. - Support PHY rate matching - adapting between differing host-side and link-side speeds. - Introduce QUSGMII PHY mode and 1000BASE-KX interface mode. - Validate OF (device tree) nodes for DSA shared ports; make phylink-related properties mandatory on DSA and CPU ports. Enforcing more uniformity should allow transitioning to phylink. - Require that flash component name used during update matches one of the components for which version is reported by info_get(). - Remove "weight" argument from driver-facing NAPI API as much as possible. It's one of those magic knobs which seemed like a good idea at the time but is too indirect to use in practice. - Support offload of TLS connections with 256 bit keys. New hardware / drivers: - Ethernet: - Microchip KSZ9896 6-port Gigabit Ethernet Switch - Renesas Ethernet AVB (EtherAVB-IF) Gen4 SoCs - Analog Devices ADIN1110 and ADIN2111 industrial single pair Ethernet (10BASE-T1L) MAC+PHY. - Rockchip RV1126 Gigabit Ethernet (a version of stmmac IP). - Ethernet SFPs / modules: - RollBall / Hilink / Turris 10G copper SFPs - HALNy GPON module - WiFi: - CYW43439 SDIO chipset (brcmfmac) - CYW89459 PCIe chipset (brcmfmac) - BCM4378 on Apple platforms (brcmfmac) Drivers: - CAN: - gs_usb: HW timestamp support - Ethernet PHYs: - lan8814: cable diagnostics - Ethernet NICs: - Intel (100G): - implement control of FCS/CRC stripping - port splitting via devlink - L2TPv3 filtering offload - nVidia/Mellanox: - tunnel offload for sub-functions - MACSec offload, w/ Extended packet number and replay window offload - significantly restructure, and optimize the AF_XDP support, align the behavior with other vendors - Huawei: - configuring DSCP map for traffic class selection - querying standard FEC statistics - querying SerDes lane number via ethtool - Marvell/Cavium: - egress priority flow control - MACSec offload - AMD/SolarFlare: - PTP over IPv6 and raw Ethernet - small / embedded: - ax88772: convert to phylink (to support SFP cages) - altera: tse: convert to phylink - ftgmac100: support fixed link - enetc: standard Ethtool counters - macb: ZynqMP SGMII dynamic configuration support - tsnep: support multi-queue and use page pool - lan743x: Rx IP & TCP checksum offload - igc: add xdp frags support to ndo_xdp_xmit - Ethernet high-speed switches: - Marvell (prestera): - support SPAN port features (traffic mirroring) - nexthop object offloading - Microchip (sparx5): - multicast forwarding offload - QoS queuing offload (tc-mqprio, tc-tbf, tc-ets) - Ethernet embedded switches: - Marvell (mv88e6xxx): - support RGMII cmode - NXP (felix): - standardized ethtool counters - Microchip (lan966x): - QoS queuing offload (tc-mqprio, tc-tbf, tc-cbs, tc-ets) - traffic policing and mirroring - link aggregation / bonding offload - QUSGMII PHY mode support - Qualcomm 802.11ax WiFi (ath11k): - cold boot calibration support on WCN6750 - support to connect to a non-transmit MBSSID AP profile - enable remain-on-channel support on WCN6750 - Wake-on-WLAN support for WCN6750 - support to provide transmit power from firmware via nl80211 - support to get power save duration for each client - spectral scan support for 160 MHz - MediaTek WiFi (mt76): - WiFi-to-Ethernet bridging offload for MT7986 chips - RealTek WiFi (rtw89): - P2P support" * tag 'net-next-6.1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1864 commits) eth: pse: add missing static inlines once: rename _SLOW to _SLEEPABLE net: pse-pd: add regulator based PSE driver dt-bindings: net: pse-dt: add bindings for regulator based PoDL PSE controller ethtool: add interface to interact with Ethernet Power Equipment net: mdiobus: search for PSE nodes by parsing PHY nodes. net: mdiobus: fwnode_mdiobus_register_phy() rework error handling net: add framework to support Ethernet PSE and PDs devices dt-bindings: net: phy: add PoDL PSE property net: marvell: prestera: Propagate nh state from hw to kernel net: marvell: prestera: Add neighbour cache accounting net: marvell: prestera: add stub handler neighbour events net: marvell: prestera: Add heplers to interact with fib_notifier_info net: marvell: prestera: Add length macros for prestera_ip_addr net: marvell: prestera: add delayed wq and flush wq on deinit net: marvell: prestera: Add strict cleanup of fib arbiter net: marvell: prestera: Add cleanup of allocated fib_nodes net: marvell: prestera: Add router nexthops ABI eth: octeon: fix build after netif_napi_add() changes net/mlx5: E-Switch, Return EBUSY if can't get mode lock ...
Diffstat (limited to 'net/unix/af_unix.c')
-rw-r--r--net/unix/af_unix.c83
1 files changed, 50 insertions, 33 deletions
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index bf338b782fc4..0f08c3177872 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -569,12 +569,6 @@ static void unix_sock_destructor(struct sock *sk)
skb_queue_purge(&sk->sk_receive_queue);
-#if IS_ENABLED(CONFIG_AF_UNIX_OOB)
- if (u->oob_skb) {
- kfree_skb(u->oob_skb);
- u->oob_skb = NULL;
- }
-#endif
DEBUG_NET_WARN_ON_ONCE(refcount_read(&sk->sk_wmem_alloc));
DEBUG_NET_WARN_ON_ONCE(!sk_unhashed(sk));
DEBUG_NET_WARN_ON_ONCE(sk->sk_socket);
@@ -620,6 +614,13 @@ static void unix_release_sock(struct sock *sk, int embrion)
unix_state_unlock(sk);
+#if IS_ENABLED(CONFIG_AF_UNIX_OOB)
+ if (u->oob_skb) {
+ kfree_skb(u->oob_skb);
+ u->oob_skb = NULL;
+ }
+#endif
+
wake_up_interruptible_all(&u->peer_wait);
if (skpair != NULL) {
@@ -785,15 +786,45 @@ static int unix_set_peek_off(struct sock *sk, int val)
}
#ifdef CONFIG_PROC_FS
+static int unix_count_nr_fds(struct sock *sk)
+{
+ struct sk_buff *skb;
+ struct unix_sock *u;
+ int nr_fds = 0;
+
+ spin_lock(&sk->sk_receive_queue.lock);
+ skb = skb_peek(&sk->sk_receive_queue);
+ while (skb) {
+ u = unix_sk(skb->sk);
+ nr_fds += atomic_read(&u->scm_stat.nr_fds);
+ skb = skb_peek_next(skb, &sk->sk_receive_queue);
+ }
+ spin_unlock(&sk->sk_receive_queue.lock);
+
+ return nr_fds;
+}
+
static void unix_show_fdinfo(struct seq_file *m, struct socket *sock)
{
struct sock *sk = sock->sk;
struct unix_sock *u;
+ int nr_fds;
if (sk) {
- u = unix_sk(sock->sk);
- seq_printf(m, "scm_fds: %u\n",
- atomic_read(&u->scm_stat.nr_fds));
+ u = unix_sk(sk);
+ if (sock->type == SOCK_DGRAM) {
+ nr_fds = atomic_read(&u->scm_stat.nr_fds);
+ goto out_print;
+ }
+
+ unix_state_lock(sk);
+ if (sk->sk_state != TCP_LISTEN)
+ nr_fds = atomic_read(&u->scm_stat.nr_fds);
+ else
+ nr_fds = unix_count_nr_fds(sk);
+ unix_state_unlock(sk);
+out_print:
+ seq_printf(m, "scm_fds: %u\n", nr_fds);
}
}
#else
@@ -2506,32 +2537,18 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg, size_t si
static int unix_read_skb(struct sock *sk, skb_read_actor_t recv_actor)
{
- int copied = 0;
-
- while (1) {
- struct unix_sock *u = unix_sk(sk);
- struct sk_buff *skb;
- int used, err;
-
- mutex_lock(&u->iolock);
- skb = skb_recv_datagram(sk, MSG_DONTWAIT, &err);
- mutex_unlock(&u->iolock);
- if (!skb)
- return err;
+ struct unix_sock *u = unix_sk(sk);
+ struct sk_buff *skb;
+ int err, copied;
- used = recv_actor(sk, skb);
- if (used <= 0) {
- if (!copied)
- copied = used;
- kfree_skb(skb);
- break;
- } else if (used <= skb->len) {
- copied += used;
- }
+ mutex_lock(&u->iolock);
+ skb = skb_recv_datagram(sk, MSG_DONTWAIT, &err);
+ mutex_unlock(&u->iolock);
+ if (!skb)
+ return err;
- kfree_skb(skb);
- break;
- }
+ copied = recv_actor(sk, skb);
+ kfree_skb(skb);
return copied;
}