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, 568 insertions, 0 deletions

diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c
new file mode 100644
index 000000000..8a2929014
--- /dev/null
+++ b/net/netfilter/nf_log.c
@@ -0,0 +1,568 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/proc_fs.h>
+#include <linux/skbuff.h>
+#include <linux/netfilter.h>
+#include <linux/seq_file.h>
+#include <net/protocol.h>
+#include <net/netfilter/nf_log.h>
+
+#include "nf_internals.h"
+
+/* Internal logging interface, which relies on the real
+   LOG target modules */
+
+#define NFLOGGER_NAME_LEN		64
+
+int sysctl_nf_log_all_netns __read_mostly;
+EXPORT_SYMBOL(sysctl_nf_log_all_netns);
+
+static struct nf_logger __rcu *loggers[NFPROTO_NUMPROTO][NF_LOG_TYPE_MAX] __read_mostly;
+static DEFINE_MUTEX(nf_log_mutex);
+
+#define nft_log_dereference(logger) \
+	rcu_dereference_protected(logger, lockdep_is_held(&nf_log_mutex))
+
+static struct nf_logger *__find_logger(int pf, const char *str_logger)
+{
+	struct nf_logger *log;
+	int i;
+
+	for (i = 0; i < NF_LOG_TYPE_MAX; i++) {
+		if (loggers[pf][i] == NULL)
+			continue;
+
+		log = nft_log_dereference(loggers[pf][i]);
+		if (!strncasecmp(str_logger, log->name, strlen(log->name)))
+			return log;
+	}
+
+	return NULL;
+}
+
+int nf_log_set(struct net *net, u_int8_t pf, const struct nf_logger *logger)
+{
+	const struct nf_logger *log;
+
+	if (pf == NFPROTO_UNSPEC || pf >= ARRAY_SIZE(net->nf.nf_loggers))
+		return -EOPNOTSUPP;
+
+	mutex_lock(&nf_log_mutex);
+	log = nft_log_dereference(net->nf.nf_loggers[pf]);
+	if (log == NULL)
+		rcu_assign_pointer(net->nf.nf_loggers[pf], logger);
+
+	mutex_unlock(&nf_log_mutex);
+
+	return 0;
+}
+EXPORT_SYMBOL(nf_log_set);
+
+void nf_log_unset(struct net *net, const struct nf_logger *logger)
+{
+	int i;
+	const struct nf_logger *log;
+
+	mutex_lock(&nf_log_mutex);
+	for (i = 0; i < NFPROTO_NUMPROTO; i++) {
+		log = nft_log_dereference(net->nf.nf_loggers[i]);
+		if (log == logger)
+			RCU_INIT_POINTER(net->nf.nf_loggers[i], NULL);
+	}
+	mutex_unlock(&nf_log_mutex);
+}
+EXPORT_SYMBOL(nf_log_unset);
+
+/* return EEXIST if the same logger is registered, 0 on success. */
+int nf_log_register(u_int8_t pf, struct nf_logger *logger)
+{
+	int i;
+	int ret = 0;
+
+	if (pf >= ARRAY_SIZE(init_net.nf.nf_loggers))
+		return -EINVAL;
+
+	mutex_lock(&nf_log_mutex);
+
+	if (pf == NFPROTO_UNSPEC) {
+		for (i = NFPROTO_UNSPEC; i < NFPROTO_NUMPROTO; i++) {
+			if (rcu_access_pointer(loggers[i][logger->type])) {
+				ret = -EEXIST;
+				goto unlock;
+			}
+		}
+		for (i = NFPROTO_UNSPEC; i < NFPROTO_NUMPROTO; i++)
+			rcu_assign_pointer(loggers[i][logger->type], logger);
+	} else {
+		if (rcu_access_pointer(loggers[pf][logger->type])) {
+			ret = -EEXIST;
+			goto unlock;
+		}
+		rcu_assign_pointer(loggers[pf][logger->type], logger);
+	}
+
+unlock:
+	mutex_unlock(&nf_log_mutex);
+	return ret;
+}
+EXPORT_SYMBOL(nf_log_register);
+
+void nf_log_unregister(struct nf_logger *logger)
+{
+	const struct nf_logger *log;
+	int i;
+
+	mutex_lock(&nf_log_mutex);
+	for (i = 0; i < NFPROTO_NUMPROTO; i++) {
+		log = nft_log_dereference(loggers[i][logger->type]);
+		if (log == logger)
+			RCU_INIT_POINTER(loggers[i][logger->type], NULL);
+	}
+	mutex_unlock(&nf_log_mutex);
+	synchronize_rcu();
+}
+EXPORT_SYMBOL(nf_log_unregister);
+
+int nf_log_bind_pf(struct net *net, u_int8_t pf,
+		   const struct nf_logger *logger)
+{
+	if (pf >= ARRAY_SIZE(net->nf.nf_loggers))
+		return -EINVAL;
+	mutex_lock(&nf_log_mutex);
+	if (__find_logger(pf, logger->name) == NULL) {
+		mutex_unlock(&nf_log_mutex);
+		return -ENOENT;
+	}
+	rcu_assign_pointer(net->nf.nf_loggers[pf], logger);
+	mutex_unlock(&nf_log_mutex);
+	return 0;
+}
+EXPORT_SYMBOL(nf_log_bind_pf);
+
+void nf_log_unbind_pf(struct net *net, u_int8_t pf)
+{
+	if (pf >= ARRAY_SIZE(net->nf.nf_loggers))
+		return;
+	mutex_lock(&nf_log_mutex);
+	RCU_INIT_POINTER(net->nf.nf_loggers[pf], NULL);
+	mutex_unlock(&nf_log_mutex);
+}
+EXPORT_SYMBOL(nf_log_unbind_pf);
+
+int nf_logger_find_get(int pf, enum nf_log_type type)
+{
+	struct nf_logger *logger;
+	int ret = -ENOENT;
+
+	if (pf == NFPROTO_INET) {
+		ret = nf_logger_find_get(NFPROTO_IPV4, type);
+		if (ret < 0)
+			return ret;
+
+		ret = nf_logger_find_get(NFPROTO_IPV6, type);
+		if (ret < 0) {
+			nf_logger_put(NFPROTO_IPV4, type);
+			return ret;
+		}
+
+		return 0;
+	}
+
+	rcu_read_lock();
+	logger = rcu_dereference(loggers[pf][type]);
+	if (logger == NULL)
+		goto out;
+
+	if (try_module_get(logger->me))
+		ret = 0;
+out:
+	rcu_read_unlock();
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nf_logger_find_get);
+
+void nf_logger_put(int pf, enum nf_log_type type)
+{
+	struct nf_logger *logger;
+
+	if (pf == NFPROTO_INET) {
+		nf_logger_put(NFPROTO_IPV4, type);
+		nf_logger_put(NFPROTO_IPV6, type);
+		return;
+	}
+
+	BUG_ON(loggers[pf][type] == NULL);
+
+	rcu_read_lock();
+	logger = rcu_dereference(loggers[pf][type]);
+	module_put(logger->me);
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(nf_logger_put);
+
+void nf_log_packet(struct net *net,
+		   u_int8_t pf,
+		   unsigned int hooknum,
+		   const struct sk_buff *skb,
+		   const struct net_device *in,
+		   const struct net_device *out,
+		   const struct nf_loginfo *loginfo,
+		   const char *fmt, ...)
+{
+	va_list args;
+	char prefix[NF_LOG_PREFIXLEN];
+	const struct nf_logger *logger;
+
+	rcu_read_lock();
+	if (loginfo != NULL)
+		logger = rcu_dereference(loggers[pf][loginfo->type]);
+	else
+		logger = rcu_dereference(net->nf.nf_loggers[pf]);
+
+	if (logger) {
+		va_start(args, fmt);
+		vsnprintf(prefix, sizeof(prefix), fmt, args);
+		va_end(args);
+		logger->logfn(net, pf, hooknum, skb, in, out, loginfo, prefix);
+	}
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL(nf_log_packet);
+
+void nf_log_trace(struct net *net,
+		  u_int8_t pf,
+		  unsigned int hooknum,
+		  const struct sk_buff *skb,
+		  const struct net_device *in,
+		  const struct net_device *out,
+		  const struct nf_loginfo *loginfo, const char *fmt, ...)
+{
+	va_list args;
+	char prefix[NF_LOG_PREFIXLEN];
+	const struct nf_logger *logger;
+
+	rcu_read_lock();
+	logger = rcu_dereference(net->nf.nf_loggers[pf]);
+	if (logger) {
+		va_start(args, fmt);
+		vsnprintf(prefix, sizeof(prefix), fmt, args);
+		va_end(args);
+		logger->logfn(net, pf, hooknum, skb, in, out, loginfo, prefix);
+	}
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL(nf_log_trace);
+
+#define S_SIZE (1024 - (sizeof(unsigned int) + 1))
+
+struct nf_log_buf {
+	unsigned int	count;
+	char		buf[S_SIZE + 1];
+};
+static struct nf_log_buf emergency, *emergency_ptr = &emergency;
+
+__printf(2, 3) int nf_log_buf_add(struct nf_log_buf *m, const char *f, ...)
+{
+	va_list args;
+	int len;
+
+	if (likely(m->count < S_SIZE)) {
+		va_start(args, f);
+		len = vsnprintf(m->buf + m->count, S_SIZE - m->count, f, args);
+		va_end(args);
+		if (likely(m->count + len < S_SIZE)) {
+			m->count += len;
+			return 0;
+		}
+	}
+	m->count = S_SIZE;
+	printk_once(KERN_ERR KBUILD_MODNAME " please increase S_SIZE\n");
+	return -1;
+}
+EXPORT_SYMBOL_GPL(nf_log_buf_add);
+
+struct nf_log_buf *nf_log_buf_open(void)
+{
+	struct nf_log_buf *m = kmalloc(sizeof(*m), GFP_ATOMIC);
+
+	if (unlikely(!m)) {
+		local_bh_disable();
+		do {
+			m = xchg(&emergency_ptr, NULL);
+		} while (!m);
+	}
+	m->count = 0;
+	return m;
+}
+EXPORT_SYMBOL_GPL(nf_log_buf_open);
+
+void nf_log_buf_close(struct nf_log_buf *m)
+{
+	m->buf[m->count] = 0;
+	printk("%s\n", m->buf);
+
+	if (likely(m != &emergency))
+		kfree(m);
+	else {
+		emergency_ptr = m;
+		local_bh_enable();
+	}
+}
+EXPORT_SYMBOL_GPL(nf_log_buf_close);
+
+#ifdef CONFIG_PROC_FS
+static void *seq_start(struct seq_file *seq, loff_t *pos)
+{
+	struct net *net = seq_file_net(seq);
+
+	mutex_lock(&nf_log_mutex);
+
+	if (*pos >= ARRAY_SIZE(net->nf.nf_loggers))
+		return NULL;
+
+	return pos;
+}
+
+static void *seq_next(struct seq_file *s, void *v, loff_t *pos)
+{
+	struct net *net = seq_file_net(s);
+
+	(*pos)++;
+
+	if (*pos >= ARRAY_SIZE(net->nf.nf_loggers))
+		return NULL;
+
+	return pos;
+}
+
+static void seq_stop(struct seq_file *s, void *v)
+{
+	mutex_unlock(&nf_log_mutex);
+}
+
+static int seq_show(struct seq_file *s, void *v)
+{
+	loff_t *pos = v;
+	const struct nf_logger *logger;
+	int i;
+	struct net *net = seq_file_net(s);
+
+	logger = nft_log_dereference(net->nf.nf_loggers[*pos]);
+
+	if (!logger)
+		seq_printf(s, "%2lld NONE (", *pos);
+	else
+		seq_printf(s, "%2lld %s (", *pos, logger->name);
+
+	if (seq_has_overflowed(s))
+		return -ENOSPC;
+
+	for (i = 0; i < NF_LOG_TYPE_MAX; i++) {
+		if (loggers[*pos][i] == NULL)
+			continue;
+
+		logger = nft_log_dereference(loggers[*pos][i]);
+		seq_puts(s, logger->name);
+		if (i == 0 && loggers[*pos][i + 1] != NULL)
+			seq_puts(s, ",");
+
+		if (seq_has_overflowed(s))
+			return -ENOSPC;
+	}
+
+	seq_puts(s, ")\n");
+
+	if (seq_has_overflowed(s))
+		return -ENOSPC;
+	return 0;
+}
+
+static const struct seq_operations nflog_seq_ops = {
+	.start	= seq_start,
+	.next	= seq_next,
+	.stop	= seq_stop,
+	.show	= seq_show,
+};
+#endif /* PROC_FS */
+
+#ifdef CONFIG_SYSCTL
+static char nf_log_sysctl_fnames[NFPROTO_NUMPROTO-NFPROTO_UNSPEC][3];
+static struct ctl_table nf_log_sysctl_table[NFPROTO_NUMPROTO+1];
+static struct ctl_table_header *nf_log_sysctl_fhdr;
+
+static struct ctl_table nf_log_sysctl_ftable[] = {
+	{
+		.procname	= "nf_log_all_netns",
+		.data		= &sysctl_nf_log_all_netns,
+		.maxlen		= sizeof(sysctl_nf_log_all_netns),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{ }
+};
+
+static int nf_log_proc_dostring(struct ctl_table *table, int write,
+			 void *buffer, size_t *lenp, loff_t *ppos)
+{
+	const struct nf_logger *logger;
+	char buf[NFLOGGER_NAME_LEN];
+	int r = 0;
+	int tindex = (unsigned long)table->extra1;
+	struct net *net = table->extra2;
+
+	if (write) {
+		struct ctl_table tmp = *table;
+
+		/* proc_dostring() can append to existing strings, so we need to
+		 * initialize it as an empty string.
+		 */
+		buf[0] = '\0';
+		tmp.data = buf;
+		r = proc_dostring(&tmp, write, buffer, lenp, ppos);
+		if (r)
+			return r;
+
+		if (!strcmp(buf, "NONE")) {
+			nf_log_unbind_pf(net, tindex);
+			return 0;
+		}
+		mutex_lock(&nf_log_mutex);
+		logger = __find_logger(tindex, buf);
+		if (logger == NULL) {
+			mutex_unlock(&nf_log_mutex);
+			return -ENOENT;
+		}
+		rcu_assign_pointer(net->nf.nf_loggers[tindex], logger);
+		mutex_unlock(&nf_log_mutex);
+	} else {
+		struct ctl_table tmp = *table;
+
+		tmp.data = buf;
+		mutex_lock(&nf_log_mutex);
+		logger = nft_log_dereference(net->nf.nf_loggers[tindex]);
+		if (!logger)
+			strscpy(buf, "NONE", sizeof(buf));
+		else
+			strscpy(buf, logger->name, sizeof(buf));
+		mutex_unlock(&nf_log_mutex);
+		r = proc_dostring(&tmp, write, buffer, lenp, ppos);
+	}
+
+	return r;
+}
+
+static int netfilter_log_sysctl_init(struct net *net)
+{
+	int i;
+	struct ctl_table *table;
+
+	table = nf_log_sysctl_table;
+	if (!net_eq(net, &init_net)) {
+		table = kmemdup(nf_log_sysctl_table,
+				 sizeof(nf_log_sysctl_table),
+				 GFP_KERNEL);
+		if (!table)
+			goto err_alloc;
+	} else {
+		for (i = NFPROTO_UNSPEC; i < NFPROTO_NUMPROTO; i++) {
+			snprintf(nf_log_sysctl_fnames[i],
+				 3, "%d", i);
+			nf_log_sysctl_table[i].procname	=
+				nf_log_sysctl_fnames[i];
+			nf_log_sysctl_table[i].maxlen = NFLOGGER_NAME_LEN;
+			nf_log_sysctl_table[i].mode = 0644;
+			nf_log_sysctl_table[i].proc_handler =
+				nf_log_proc_dostring;
+			nf_log_sysctl_table[i].extra1 =
+				(void *)(unsigned long) i;
+		}
+		nf_log_sysctl_fhdr = register_net_sysctl(net, "net/netfilter",
+							 nf_log_sysctl_ftable);
+		if (!nf_log_sysctl_fhdr)
+			goto err_freg;
+	}
+
+	for (i = NFPROTO_UNSPEC; i < NFPROTO_NUMPROTO; i++)
+		table[i].extra2 = net;
+
+	net->nf.nf_log_dir_header = register_net_sysctl(net,
+						"net/netfilter/nf_log",
+						table);
+	if (!net->nf.nf_log_dir_header)
+		goto err_reg;
+
+	return 0;
+
+err_reg:
+	if (!net_eq(net, &init_net))
+		kfree(table);
+	else
+		unregister_net_sysctl_table(nf_log_sysctl_fhdr);
+err_freg:
+err_alloc:
+	return -ENOMEM;
+}
+
+static void netfilter_log_sysctl_exit(struct net *net)
+{
+	struct ctl_table *table;
+
+	table = net->nf.nf_log_dir_header->ctl_table_arg;
+	unregister_net_sysctl_table(net->nf.nf_log_dir_header);
+	if (!net_eq(net, &init_net))
+		kfree(table);
+	else
+		unregister_net_sysctl_table(nf_log_sysctl_fhdr);
+}
+#else
+static int netfilter_log_sysctl_init(struct net *net)
+{
+	return 0;
+}
+
+static void netfilter_log_sysctl_exit(struct net *net)
+{
+}
+#endif /* CONFIG_SYSCTL */
+
+static int __net_init nf_log_net_init(struct net *net)
+{
+	int ret = -ENOMEM;
+
+#ifdef CONFIG_PROC_FS
+	if (!proc_create_net("nf_log", 0444, net->nf.proc_netfilter,
+			&nflog_seq_ops, sizeof(struct seq_net_private)))
+		return ret;
+#endif
+	ret = netfilter_log_sysctl_init(net);
+	if (ret < 0)
+		goto out_sysctl;
+
+	return 0;
+
+out_sysctl:
+#ifdef CONFIG_PROC_FS
+	remove_proc_entry("nf_log", net->nf.proc_netfilter);
+#endif
+	return ret;
+}
+
+static void __net_exit nf_log_net_exit(struct net *net)
+{
+	netfilter_log_sysctl_exit(net);
+#ifdef CONFIG_PROC_FS
+	remove_proc_entry("nf_log", net->nf.proc_netfilter);
+#endif
+}
+
+static struct pernet_operations nf_log_net_ops = {
+	.init = nf_log_net_init,
+	.exit = nf_log_net_exit,
+};
+
+int __init netfilter_log_init(void)
+{
+	return register_pernet_subsys(&nf_log_net_ops);
+}