Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted

Pull networking updates from Jakub Kicinski:
 "Core:

   - Add dedicated kmem_cache for typical/small skb->head, avoid having
     to access struct page at kfree time, and improve memory use.

   - Introduce sysctl to set default RPS configuration for new netdevs.

   - Define Netlink protocol specification format which can be used to
     describe messages used by each family and auto-generate parsers.
     Add tools for generating kernel data structures and uAPI headers.

   - Expose all net/core sysctls inside netns.

   - Remove 4s sleep in netpoll if carrier is instantly detected on
     boot.

   - Add configurable limit of MDB entries per port, and port-vlan.

   - Continue populating drop reasons throughout the stack.

   - Retire a handful of legacy Qdiscs and classifiers.

  Protocols:

   - Support IPv4 big TCP (TSO frames larger than 64kB).

   - Add IP_LOCAL_PORT_RANGE socket option, to control local port range
     on socket by socket basis.

   - Track and report in procfs number of MPTCP sockets used.

   - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path
     manager.

   - IPv6: don't check net.ipv6.route.max_size and rely on garbage
     collection to free memory (similarly to IPv4).

   - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986).

   - ICMP: add per-rate limit counters.

   - Add support for user scanning requests in ieee802154.

   - Remove static WEP support.

   - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate
     reporting.

   - WiFi 7 EHT channel puncturing support (client & AP).

  BPF:

   - Add a rbtree data structure following the "next-gen data structure"
     precedent set by recently added linked list, that is, by using
     kfunc + kptr instead of adding a new BPF map type.

   - Expose XDP hints via kfuncs with initial support for RX hash and
     timestamp metadata.

   - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to
     better support decap on GRE tunnel devices not operating in collect
     metadata.

   - Improve x86 JIT's codegen for PROBE_MEM runtime error checks.

   - Remove the need for trace_printk_lock for bpf_trace_printk and
     bpf_trace_vprintk helpers.

   - Extend libbpf's bpf_tracing.h support for tracing arguments of
     kprobes/uprobes and syscall as a special case.

   - Significantly reduce the search time for module symbols by
     livepatch and BPF.

   - Enable cpumasks to be used as kptrs, which is useful for tracing
     programs tracking which tasks end up running on which CPUs in
     different time intervals.

   - Add support for BPF trampoline on s390x and riscv64.

   - Add capability to export the XDP features supported by the NIC.

   - Add __bpf_kfunc tag for marking kernel functions as kfuncs.

   - Add cgroup.memory=nobpf kernel parameter option to disable BPF
     memory accounting for container environments.

  Netfilter:

   - Remove the CLUSTERIP target. It has been marked as obsolete for
     years, and we still have WARN splats wrt races of the out-of-band
     /proc interface installed by this target.

   - Add 'destroy' commands to nf_tables. They are identical to the
     existing 'delete' commands, but do not return an error if the
     referenced object (set, chain, rule...) did not exist.

  Driver API:

   - Improve cpumask_local_spread() locality to help NICs set the right
     IRQ affinity on AMD platforms.

   - Separate C22 and C45 MDIO bus transactions more clearly.

   - Introduce new DCB table to control DSCP rewrite on egress.

   - Support configuration of Physical Layer Collision Avoidance (PLCA)
     Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of
     shared medium Ethernet.

   - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing
     preemption of low priority frames by high priority frames.

   - Add support for controlling MACSec offload using netlink SET.

   - Rework devlink instance refcounts to allow registration and
     de-registration under the instance lock. Split the code into
     multiple files, drop some of the unnecessarily granular locks and
     factor out common parts of netlink operation handling.

   - Add TX frame aggregation parameters (for USB drivers).

   - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning
     messages with notifications for debug.

   - Allow offloading of UDP NEW connections via act_ct.

   - Add support for per action HW stats in TC.

   - Support hardware miss to TC action (continue processing in SW from
     a specific point in the action chain).

   - Warn if old Wireless Extension user space interface is used with
     modern cfg80211/mac80211 drivers. Do not support Wireless
     Extensions for Wi-Fi 7 devices at all. Everyone should switch to
     using nl80211 interface instead.

   - Improve the CAN bit timing configuration. Use extack to return
     error messages directly to user space, update the SJW handling,
     including the definition of a new default value that will benefit
     CAN-FD controllers, by increasing their oscillator tolerance.

  New hardware / drivers:

   - Ethernet:
      - nVidia BlueField-3 support (control traffic driver)
      - Ethernet support for imx93 SoCs
      - Motorcomm yt8531 gigabit Ethernet PHY
      - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA)
      - Microchip LAN8841 PHY (incl. cable diagnostics and PTP)
      - Amlogic gxl MDIO mux

   - WiFi:
      - RealTek RTL8188EU (rtl8xxxu)
      - Qualcomm Wi-Fi 7 devices (ath12k)

   - CAN:
      - Renesas R-Car V4H

  Drivers:

   - Bluetooth:
      - Set Per Platform Antenna Gain (PPAG) for Intel controllers.

   - Ethernet NICs:
      - Intel (1G, igc):
         - support TSN / Qbv / packet scheduling features of i226 model
      - Intel (100G, ice):
         - use GNSS subsystem instead of TTY
         - multi-buffer XDP support
         - extend support for GPIO pins to E823 devices
      - nVidia/Mellanox:
         - update the shared buffer configuration on PFC commands
         - implement PTP adjphase function for HW offset control
         - TC support for Geneve and GRE with VF tunnel offload
         - more efficient crypto key management method
         - multi-port eswitch support
      - Netronome/Corigine:
         - add DCB IEEE support
         - support IPsec offloading for NFP3800
      - Freescale/NXP (enetc):
         - support XDP_REDIRECT for XDP non-linear buffers
         - improve reconfig, avoid link flap and waiting for idle
         - support MAC Merge layer
      - Other NICs:
         - sfc/ef100: add basic devlink support for ef100
         - ionic: rx_push mode operation (writing descriptors via MMIO)
         - bnxt: use the auxiliary bus abstraction for RDMA
         - r8169: disable ASPM and reset bus in case of tx timeout
         - cpsw: support QSGMII mode for J721e CPSW9G
         - cpts: support pulse-per-second output
         - ngbe: add an mdio bus driver
         - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing
         - r8152: handle devices with FW with NCM support
         - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation
         - virtio-net: support multi buffer XDP
         - virtio/vsock: replace virtio_vsock_pkt with sk_buff
         - tsnep: XDP support

   - Ethernet high-speed switches:
      - nVidia/Mellanox (mlxsw):
         - add support for latency TLV (in FW control messages)
      - Microchip (sparx5):
         - separate explicit and implicit traffic forwarding rules, make
           the implicit rules always active
         - add support for egress DSCP rewrite
         - IS0 VCAP support (Ingress Classification)
         - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS
           etc.)
         - ES2 VCAP support (Egress Access Control)
         - support for Per-Stream Filtering and Policing (802.1Q,
           8.6.5.1)

   - Ethernet embedded switches:
      - Marvell (mv88e6xxx):
         - add MAB (port auth) offload support
         - enable PTP receive for mv88e6390
      - NXP (ocelot):
         - support MAC Merge layer
         - support for the the vsc7512 internal copper phys
      - Microchip:
         - lan9303: convert to PHYLINK
         - lan966x: support TC flower filter statistics
         - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x
         - lan937x: support Credit Based Shaper configuration
         - ksz9477: support Energy Efficient Ethernet
      - other:
         - qca8k: convert to regmap read/write API, use bulk operations
         - rswitch: Improve TX timestamp accuracy

   - Intel WiFi (iwlwifi):
      - EHT (Wi-Fi 7) rate reporting
      - STEP equalizer support: transfer some STEP (connection to radio
        on platforms with integrated wifi) related parameters from the
        BIOS to the firmware.

   - Qualcomm 802.11ax WiFi (ath11k):
      - IPQ5018 support
      - Fine Timing Measurement (FTM) responder role support
      - channel 177 support

   - MediaTek WiFi (mt76):
      - per-PHY LED support
      - mt7996: EHT (Wi-Fi 7) support
      - Wireless Ethernet Dispatch (WED) reset support
      - switch to using page pool allocator

   - RealTek WiFi (rtw89):
      - support new version of Bluetooth co-existance

   - Mobile:
      - rmnet: support TX aggregation"

* tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits)
  page_pool: add a comment explaining the fragment counter usage
  net: ethtool: fix __ethtool_dev_mm_supported() implementation
  ethtool: pse-pd: Fix double word in comments
  xsk: add linux/vmalloc.h to xsk.c
  sefltests: netdevsim: wait for devlink instance after netns removal
  selftest: fib_tests: Always cleanup before exit
  net/mlx5e: Align IPsec ASO result memory to be as required by hardware
  net/mlx5e: TC, Set CT miss to the specific ct action instance
  net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG
  net/mlx5: Refactor tc miss handling to a single function
  net/mlx5: Kconfig: Make tc offload depend on tc skb extension
  net/sched: flower: Support hardware miss to tc action
  net/sched: flower: Move filter handle initialization earlier
  net/sched: cls_api: Support hardware miss to tc action
  net/sched: Rename user cookie and act cookie
  sfc: fix builds without CONFIG_RTC_LIB
  sfc: clean up some inconsistent indentings
  net/mlx4_en: Introduce flexible array to silence overflow warning
  net: lan966x: Fix possible deadlock inside PTP
  net/ulp: Remove redundant ->clone() test in inet_clone_ulp().
  ...

1 files changed, 518 insertions, 0 deletions

diff --git a/net/compat.c b/net/compat.c
new file mode 100644
index 000000000..161b7bea1
--- /dev/null
+++ b/net/compat.c
@@ -0,0 +1,518 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * 32bit Socket syscall emulation. Based on arch/sparc64/kernel/sys_sparc32.c.
+ *
+ * Copyright (C) 2000		VA Linux Co
+ * Copyright (C) 2000		Don Dugger <n0ano@valinux.com>
+ * Copyright (C) 1999 		Arun Sharma <arun.sharma@intel.com>
+ * Copyright (C) 1997,1998 	Jakub Jelinek (jj@sunsite.mff.cuni.cz)
+ * Copyright (C) 1997 		David S. Miller (davem@caip.rutgers.edu)
+ * Copyright (C) 2000		Hewlett-Packard Co.
+ * Copyright (C) 2000		David Mosberger-Tang <davidm@hpl.hp.com>
+ * Copyright (C) 2000,2001	Andi Kleen, SuSE Labs
+ */
+
+#include <linux/kernel.h>
+#include <linux/gfp.h>
+#include <linux/fs.h>
+#include <linux/types.h>
+#include <linux/file.h>
+#include <linux/icmpv6.h>
+#include <linux/socket.h>
+#include <linux/syscalls.h>
+#include <linux/filter.h>
+#include <linux/compat.h>
+#include <linux/security.h>
+#include <linux/audit.h>
+#include <linux/export.h>
+
+#include <net/scm.h>
+#include <net/sock.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
+#include <linux/uaccess.h>
+#include <net/compat.h>
+
+int __get_compat_msghdr(struct msghdr *kmsg,
+			struct compat_msghdr *msg,
+			struct sockaddr __user **save_addr)
+{
+	ssize_t err;
+
+	kmsg->msg_flags = msg->msg_flags;
+	kmsg->msg_namelen = msg->msg_namelen;
+
+	if (!msg->msg_name)
+		kmsg->msg_namelen = 0;
+
+	if (kmsg->msg_namelen < 0)
+		return -EINVAL;
+
+	if (kmsg->msg_namelen > sizeof(struct sockaddr_storage))
+		kmsg->msg_namelen = sizeof(struct sockaddr_storage);
+
+	kmsg->msg_control_is_user = true;
+	kmsg->msg_get_inq = 0;
+	kmsg->msg_control_user = compat_ptr(msg->msg_control);
+	kmsg->msg_controllen = msg->msg_controllen;
+
+	if (save_addr)
+		*save_addr = compat_ptr(msg->msg_name);
+
+	if (msg->msg_name && kmsg->msg_namelen) {
+		if (!save_addr) {
+			err = move_addr_to_kernel(compat_ptr(msg->msg_name),
+						  kmsg->msg_namelen,
+						  kmsg->msg_name);
+			if (err < 0)
+				return err;
+		}
+	} else {
+		kmsg->msg_name = NULL;
+		kmsg->msg_namelen = 0;
+	}
+
+	if (msg->msg_iovlen > UIO_MAXIOV)
+		return -EMSGSIZE;
+
+	kmsg->msg_iocb = NULL;
+	kmsg->msg_ubuf = NULL;
+	return 0;
+}
+
+int get_compat_msghdr(struct msghdr *kmsg,
+		      struct compat_msghdr __user *umsg,
+		      struct sockaddr __user **save_addr,
+		      struct iovec **iov)
+{
+	struct compat_msghdr msg;
+	ssize_t err;
+
+	if (copy_from_user(&msg, umsg, sizeof(*umsg)))
+		return -EFAULT;
+
+	err = __get_compat_msghdr(kmsg, &msg, save_addr);
+	if (err)
+		return err;
+
+	err = import_iovec(save_addr ? ITER_DEST : ITER_SOURCE,
+			   compat_ptr(msg.msg_iov), msg.msg_iovlen,
+			   UIO_FASTIOV, iov, &kmsg->msg_iter);
+	return err < 0 ? err : 0;
+}
+
+/* Bleech... */
+#define CMSG_COMPAT_ALIGN(len)	ALIGN((len), sizeof(s32))
+
+#define CMSG_COMPAT_DATA(cmsg)				\
+	((void __user *)((char __user *)(cmsg) + sizeof(struct compat_cmsghdr)))
+#define CMSG_COMPAT_SPACE(len)				\
+	(sizeof(struct compat_cmsghdr) + CMSG_COMPAT_ALIGN(len))
+#define CMSG_COMPAT_LEN(len)				\
+	(sizeof(struct compat_cmsghdr) + (len))
+
+#define CMSG_COMPAT_FIRSTHDR(msg)			\
+	(((msg)->msg_controllen) >= sizeof(struct compat_cmsghdr) ?	\
+	 (struct compat_cmsghdr __user *)((msg)->msg_control) :		\
+	 (struct compat_cmsghdr __user *)NULL)
+
+#define CMSG_COMPAT_OK(ucmlen, ucmsg, mhdr) \
+	((ucmlen) >= sizeof(struct compat_cmsghdr) && \
+	 (ucmlen) <= (unsigned long) \
+	 ((mhdr)->msg_controllen - \
+	  ((char __user *)(ucmsg) - (char __user *)(mhdr)->msg_control_user)))
+
+static inline struct compat_cmsghdr __user *cmsg_compat_nxthdr(struct msghdr *msg,
+		struct compat_cmsghdr __user *cmsg, int cmsg_len)
+{
+	char __user *ptr = (char __user *)cmsg + CMSG_COMPAT_ALIGN(cmsg_len);
+	if ((unsigned long)(ptr + 1 - (char __user *)msg->msg_control) >
+			msg->msg_controllen)
+		return NULL;
+	return (struct compat_cmsghdr __user *)ptr;
+}
+
+/* There is a lot of hair here because the alignment rules (and
+ * thus placement) of cmsg headers and length are different for
+ * 32-bit apps.  -DaveM
+ */
+int cmsghdr_from_user_compat_to_kern(struct msghdr *kmsg, struct sock *sk,
+			       unsigned char *stackbuf, int stackbuf_size)
+{
+	struct compat_cmsghdr __user *ucmsg;
+	struct cmsghdr *kcmsg, *kcmsg_base;
+	compat_size_t ucmlen;
+	__kernel_size_t kcmlen, tmp;
+	int err = -EFAULT;
+
+	BUILD_BUG_ON(sizeof(struct compat_cmsghdr) !=
+		     CMSG_COMPAT_ALIGN(sizeof(struct compat_cmsghdr)));
+
+	kcmlen = 0;
+	kcmsg_base = kcmsg = (struct cmsghdr *)stackbuf;
+	ucmsg = CMSG_COMPAT_FIRSTHDR(kmsg);
+	while (ucmsg != NULL) {
+		if (get_user(ucmlen, &ucmsg->cmsg_len))
+			return -EFAULT;
+
+		/* Catch bogons. */
+		if (!CMSG_COMPAT_OK(ucmlen, ucmsg, kmsg))
+			return -EINVAL;
+
+		tmp = ((ucmlen - sizeof(*ucmsg)) + sizeof(struct cmsghdr));
+		tmp = CMSG_ALIGN(tmp);
+		kcmlen += tmp;
+		ucmsg = cmsg_compat_nxthdr(kmsg, ucmsg, ucmlen);
+	}
+	if (kcmlen == 0)
+		return -EINVAL;
+
+	/* The kcmlen holds the 64-bit version of the control length.
+	 * It may not be modified as we do not stick it into the kmsg
+	 * until we have successfully copied over all of the data
+	 * from the user.
+	 */
+	if (kcmlen > stackbuf_size)
+		kcmsg_base = kcmsg = sock_kmalloc(sk, kcmlen, GFP_KERNEL);
+	if (kcmsg == NULL)
+		return -ENOMEM;
+
+	/* Now copy them over neatly. */
+	memset(kcmsg, 0, kcmlen);
+	ucmsg = CMSG_COMPAT_FIRSTHDR(kmsg);
+	while (ucmsg != NULL) {
+		struct compat_cmsghdr cmsg;
+		if (copy_from_user(&cmsg, ucmsg, sizeof(cmsg)))
+			goto Efault;
+		if (!CMSG_COMPAT_OK(cmsg.cmsg_len, ucmsg, kmsg))
+			goto Einval;
+		tmp = ((cmsg.cmsg_len - sizeof(*ucmsg)) + sizeof(struct cmsghdr));
+		if ((char *)kcmsg_base + kcmlen - (char *)kcmsg < CMSG_ALIGN(tmp))
+			goto Einval;
+		kcmsg->cmsg_len = tmp;
+		kcmsg->cmsg_level = cmsg.cmsg_level;
+		kcmsg->cmsg_type = cmsg.cmsg_type;
+		tmp = CMSG_ALIGN(tmp);
+		if (copy_from_user(CMSG_DATA(kcmsg),
+				   CMSG_COMPAT_DATA(ucmsg),
+				   (cmsg.cmsg_len - sizeof(*ucmsg))))
+			goto Efault;
+
+		/* Advance. */
+		kcmsg = (struct cmsghdr *)((char *)kcmsg + tmp);
+		ucmsg = cmsg_compat_nxthdr(kmsg, ucmsg, cmsg.cmsg_len);
+	}
+
+	/*
+	 * check the length of messages copied in is the same as the
+	 * what we get from the first loop
+	 */
+	if ((char *)kcmsg - (char *)kcmsg_base != kcmlen)
+		goto Einval;
+
+	/* Ok, looks like we made it.  Hook it up and return success. */
+	kmsg->msg_control = kcmsg_base;
+	kmsg->msg_controllen = kcmlen;
+	return 0;
+
+Einval:
+	err = -EINVAL;
+Efault:
+	if (kcmsg_base != (struct cmsghdr *)stackbuf)
+		sock_kfree_s(sk, kcmsg_base, kcmlen);
+	return err;
+}
+
+int put_cmsg_compat(struct msghdr *kmsg, int level, int type, int len, void *data)
+{
+	struct compat_cmsghdr __user *cm = (struct compat_cmsghdr __user *) kmsg->msg_control;
+	struct compat_cmsghdr cmhdr;
+	struct old_timeval32 ctv;
+	struct old_timespec32 cts[3];
+	int cmlen;
+
+	if (cm == NULL || kmsg->msg_controllen < sizeof(*cm)) {
+		kmsg->msg_flags |= MSG_CTRUNC;
+		return 0; /* XXX: return error? check spec. */
+	}
+
+	if (!COMPAT_USE_64BIT_TIME) {
+		if (level == SOL_SOCKET && type == SO_TIMESTAMP_OLD) {
+			struct __kernel_old_timeval *tv = (struct __kernel_old_timeval *)data;
+			ctv.tv_sec = tv->tv_sec;
+			ctv.tv_usec = tv->tv_usec;
+			data = &ctv;
+			len = sizeof(ctv);
+		}
+		if (level == SOL_SOCKET &&
+		    (type == SO_TIMESTAMPNS_OLD || type == SO_TIMESTAMPING_OLD)) {
+			int count = type == SO_TIMESTAMPNS_OLD ? 1 : 3;
+			int i;
+			struct __kernel_old_timespec *ts = data;
+			for (i = 0; i < count; i++) {
+				cts[i].tv_sec = ts[i].tv_sec;
+				cts[i].tv_nsec = ts[i].tv_nsec;
+			}
+			data = &cts;
+			len = sizeof(cts[0]) * count;
+		}
+	}
+
+	cmlen = CMSG_COMPAT_LEN(len);
+	if (kmsg->msg_controllen < cmlen) {
+		kmsg->msg_flags |= MSG_CTRUNC;
+		cmlen = kmsg->msg_controllen;
+	}
+	cmhdr.cmsg_level = level;
+	cmhdr.cmsg_type = type;
+	cmhdr.cmsg_len = cmlen;
+
+	if (copy_to_user(cm, &cmhdr, sizeof cmhdr))
+		return -EFAULT;
+	if (copy_to_user(CMSG_COMPAT_DATA(cm), data, cmlen - sizeof(struct compat_cmsghdr)))
+		return -EFAULT;
+	cmlen = CMSG_COMPAT_SPACE(len);
+	if (kmsg->msg_controllen < cmlen)
+		cmlen = kmsg->msg_controllen;
+	kmsg->msg_control += cmlen;
+	kmsg->msg_controllen -= cmlen;
+	return 0;
+}
+
+static int scm_max_fds_compat(struct msghdr *msg)
+{
+	if (msg->msg_controllen <= sizeof(struct compat_cmsghdr))
+		return 0;
+	return (msg->msg_controllen - sizeof(struct compat_cmsghdr)) / sizeof(int);
+}
+
+void scm_detach_fds_compat(struct msghdr *msg, struct scm_cookie *scm)
+{
+	struct compat_cmsghdr __user *cm =
+		(struct compat_cmsghdr __user *)msg->msg_control;
+	unsigned int o_flags = (msg->msg_flags & MSG_CMSG_CLOEXEC) ? O_CLOEXEC : 0;
+	int fdmax = min_t(int, scm_max_fds_compat(msg), scm->fp->count);
+	int __user *cmsg_data = CMSG_COMPAT_DATA(cm);
+	int err = 0, i;
+
+	for (i = 0; i < fdmax; i++) {
+		err = receive_fd_user(scm->fp->fp[i], cmsg_data + i, o_flags);
+		if (err < 0)
+			break;
+	}
+
+	if (i > 0) {
+		int cmlen = CMSG_COMPAT_LEN(i * sizeof(int));
+
+		err = put_user(SOL_SOCKET, &cm->cmsg_level);
+		if (!err)
+			err = put_user(SCM_RIGHTS, &cm->cmsg_type);
+		if (!err)
+			err = put_user(cmlen, &cm->cmsg_len);
+		if (!err) {
+			cmlen = CMSG_COMPAT_SPACE(i * sizeof(int));
+			if (msg->msg_controllen < cmlen)
+				cmlen = msg->msg_controllen;
+			msg->msg_control += cmlen;
+			msg->msg_controllen -= cmlen;
+		}
+	}
+
+	if (i < scm->fp->count || (scm->fp->count && fdmax <= 0))
+		msg->msg_flags |= MSG_CTRUNC;
+
+	/*
+	 * All of the files that fit in the message have had their usage counts
+	 * incremented, so we just free the list.
+	 */
+	__scm_destroy(scm);
+}
+
+/* Argument list sizes for compat_sys_socketcall */
+#define AL(x) ((x) * sizeof(u32))
+static unsigned char nas[21] = {
+	AL(0), AL(3), AL(3), AL(3), AL(2), AL(3),
+	AL(3), AL(3), AL(4), AL(4), AL(4), AL(6),
+	AL(6), AL(2), AL(5), AL(5), AL(3), AL(3),
+	AL(4), AL(5), AL(4)
+};
+#undef AL
+
+static inline long __compat_sys_sendmsg(int fd,
+					struct compat_msghdr __user *msg,
+					unsigned int flags)
+{
+	return __sys_sendmsg(fd, (struct user_msghdr __user *)msg,
+			     flags | MSG_CMSG_COMPAT, false);
+}
+
+COMPAT_SYSCALL_DEFINE3(sendmsg, int, fd, struct compat_msghdr __user *, msg,
+		       unsigned int, flags)
+{
+	return __compat_sys_sendmsg(fd, msg, flags);
+}
+
+static inline long __compat_sys_sendmmsg(int fd,
+					 struct compat_mmsghdr __user *mmsg,
+					 unsigned int vlen, unsigned int flags)
+{
+	return __sys_sendmmsg(fd, (struct mmsghdr __user *)mmsg, vlen,
+			      flags | MSG_CMSG_COMPAT, false);
+}
+
+COMPAT_SYSCALL_DEFINE4(sendmmsg, int, fd, struct compat_mmsghdr __user *, mmsg,
+		       unsigned int, vlen, unsigned int, flags)
+{
+	return __compat_sys_sendmmsg(fd, mmsg, vlen, flags);
+}
+
+static inline long __compat_sys_recvmsg(int fd,
+					struct compat_msghdr __user *msg,
+					unsigned int flags)
+{
+	return __sys_recvmsg(fd, (struct user_msghdr __user *)msg,
+			     flags | MSG_CMSG_COMPAT, false);
+}
+
+COMPAT_SYSCALL_DEFINE3(recvmsg, int, fd, struct compat_msghdr __user *, msg,
+		       unsigned int, flags)
+{
+	return __compat_sys_recvmsg(fd, msg, flags);
+}
+
+static inline long __compat_sys_recvfrom(int fd, void __user *buf,
+					 compat_size_t len, unsigned int flags,
+					 struct sockaddr __user *addr,
+					 int __user *addrlen)
+{
+	return __sys_recvfrom(fd, buf, len, flags | MSG_CMSG_COMPAT, addr,
+			      addrlen);
+}
+
+COMPAT_SYSCALL_DEFINE4(recv, int, fd, void __user *, buf, compat_size_t, len, unsigned int, flags)
+{
+	return __compat_sys_recvfrom(fd, buf, len, flags, NULL, NULL);
+}
+
+COMPAT_SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, buf, compat_size_t, len,
+		       unsigned int, flags, struct sockaddr __user *, addr,
+		       int __user *, addrlen)
+{
+	return __compat_sys_recvfrom(fd, buf, len, flags, addr, addrlen);
+}
+
+COMPAT_SYSCALL_DEFINE5(recvmmsg_time64, int, fd, struct compat_mmsghdr __user *, mmsg,
+		       unsigned int, vlen, unsigned int, flags,
+		       struct __kernel_timespec __user *, timeout)
+{
+	return __sys_recvmmsg(fd, (struct mmsghdr __user *)mmsg, vlen,
+			      flags | MSG_CMSG_COMPAT, timeout, NULL);
+}
+
+#ifdef CONFIG_COMPAT_32BIT_TIME
+COMPAT_SYSCALL_DEFINE5(recvmmsg_time32, int, fd, struct compat_mmsghdr __user *, mmsg,
+		       unsigned int, vlen, unsigned int, flags,
+		       struct old_timespec32 __user *, timeout)
+{
+	return __sys_recvmmsg(fd, (struct mmsghdr __user *)mmsg, vlen,
+			      flags | MSG_CMSG_COMPAT, NULL, timeout);
+}
+#endif
+
+COMPAT_SYSCALL_DEFINE2(socketcall, int, call, u32 __user *, args)
+{
+	u32 a[AUDITSC_ARGS];
+	unsigned int len;
+	u32 a0, a1;
+	int ret;
+
+	if (call < SYS_SOCKET || call > SYS_SENDMMSG)
+		return -EINVAL;
+	len = nas[call];
+	if (len > sizeof(a))
+		return -EINVAL;
+
+	if (copy_from_user(a, args, len))
+		return -EFAULT;
+
+	ret = audit_socketcall_compat(len / sizeof(a[0]), a);
+	if (ret)
+		return ret;
+
+	a0 = a[0];
+	a1 = a[1];
+
+	switch (call) {
+	case SYS_SOCKET:
+		ret = __sys_socket(a0, a1, a[2]);
+		break;
+	case SYS_BIND:
+		ret = __sys_bind(a0, compat_ptr(a1), a[2]);
+		break;
+	case SYS_CONNECT:
+		ret = __sys_connect(a0, compat_ptr(a1), a[2]);
+		break;
+	case SYS_LISTEN:
+		ret = __sys_listen(a0, a1);
+		break;
+	case SYS_ACCEPT:
+		ret = __sys_accept4(a0, compat_ptr(a1), compat_ptr(a[2]), 0);
+		break;
+	case SYS_GETSOCKNAME:
+		ret = __sys_getsockname(a0, compat_ptr(a1), compat_ptr(a[2]));
+		break;
+	case SYS_GETPEERNAME:
+		ret = __sys_getpeername(a0, compat_ptr(a1), compat_ptr(a[2]));
+		break;
+	case SYS_SOCKETPAIR:
+		ret = __sys_socketpair(a0, a1, a[2], compat_ptr(a[3]));
+		break;
+	case SYS_SEND:
+		ret = __sys_sendto(a0, compat_ptr(a1), a[2], a[3], NULL, 0);
+		break;
+	case SYS_SENDTO:
+		ret = __sys_sendto(a0, compat_ptr(a1), a[2], a[3],
+				   compat_ptr(a[4]), a[5]);
+		break;
+	case SYS_RECV:
+		ret = __compat_sys_recvfrom(a0, compat_ptr(a1), a[2], a[3],
+					    NULL, NULL);
+		break;
+	case SYS_RECVFROM:
+		ret = __compat_sys_recvfrom(a0, compat_ptr(a1), a[2], a[3],
+					    compat_ptr(a[4]),
+					    compat_ptr(a[5]));
+		break;
+	case SYS_SHUTDOWN:
+		ret = __sys_shutdown(a0, a1);
+		break;
+	case SYS_SETSOCKOPT:
+		ret = __sys_setsockopt(a0, a1, a[2], compat_ptr(a[3]), a[4]);
+		break;
+	case SYS_GETSOCKOPT:
+		ret = __sys_getsockopt(a0, a1, a[2], compat_ptr(a[3]),
+				       compat_ptr(a[4]));
+		break;
+	case SYS_SENDMSG:
+		ret = __compat_sys_sendmsg(a0, compat_ptr(a1), a[2]);
+		break;
+	case SYS_SENDMMSG:
+		ret = __compat_sys_sendmmsg(a0, compat_ptr(a1), a[2], a[3]);
+		break;
+	case SYS_RECVMSG:
+		ret = __compat_sys_recvmsg(a0, compat_ptr(a1), a[2]);
+		break;
+	case SYS_RECVMMSG:
+		ret = __sys_recvmmsg(a0, compat_ptr(a1), a[2],
+				     a[3] | MSG_CMSG_COMPAT, NULL,
+				     compat_ptr(a[4]));
+		break;
+	case SYS_ACCEPT4:
+		ret = __sys_accept4(a0, compat_ptr(a1), compat_ptr(a[2]), a[3]);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+	return ret;
+}