Merge tag 'trace-v7.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Don't destroy user event fields when removal fails

   User event fields are destroyed before the event is removed from
   visibility. But that can fail leaving the still visible event with no
   fields. Move the destroying of the fields to after the event is
   successfully removed from visibility.

 - Initialize function graph state is fork before calling
   copy_exec_state()

   For non-CLONE_VM forks, copy_exec_state() allocates a new
   task_exec_state. If that allocation fails, ftrace_graph_exit_task()
   will free the tasks ret_stack pointer. Since that pointer is still
   using the parent's ret_stack, it mistakenly frees the parent's
   pointer too.

   Call ftrace_graph_init() on the task first which will NULL out the
   new tasks's ret_stack and if the copy fails, it will not free
   anything.

 - Remove FGRAPH_MAX_INDEX

   The macro FGRAPH_MAX_INDEX was added but never used. Remove it.

 - Save ent_size in function graph printing of nested functions

   The function graph tracer needs to look at the next event to see if
   the next event is the return of the current function entry. If it is,
   it prints a single line:

	ktime_get();

   Otherwise it prints it like a nested function:

	tick_nohz_irq_exit() {
	    ktime_get();
	    kcpustat_irq_exit();
	}

   In order to look at the next event, it must save the current event so
   that it has the information to print from it. It saves the event in
   the iterator descriptor called "ent". What it doesn't save is the
   ent_size of the event which is now used to know if the function graph
   arguments are to be printed. The peek doesn't save the size so the
   size used happens to be that of the size of the last event that was
   seen.

   Save the entry event size in the iterator descriptor so that the
   correct size is used.

 - Fix several errors with freeing data in the histogram code

   The histogram code had a lot of leaked or or incorrect accounting
   when failures happen. Correct them.

 - Fix histogram regression of .percent and .graph modifiers

   Up until 6.3 histogram values could have "percent" or "graph"
   modifiers that changed how they were printed. But a change that added
   restricting histograms values from being strings, stack traces and
   other modifiers inadvertently prevented them from using the percent
   and graph modifiers, which were legal use cases for values.

   Put back the percent and graph modifiers.

 - Fix various typos in the comments

 - Set the trace_clock before initializing a histogram with clock
   argument

   The histogram API allows the user to specific which trace clock to
   use via a "clock=" string. The histogram is set up first before the
   clock is checked. If the passed in clock is not valid, it exits
   without fully fixing up the histogram leaving it on the list and a
   use-after-free can trigger.

   Update the clock argument first and if it fails then exit gracefully
   before the histogram trigger is placed on any lists.

 - Restore :mod: trailer after parsing in ftrace_set_clr_event

   The function ftrace_set_clr_event() modifies the parse string and
   needs to put it back to what was passed in. It searches for ":mod:"
   via a strsep() but fails to put back the first ':' in the string.

   Add back the ':' in the passed in string.

 - Take trace_array reference when opening a tracer options file

   The options files are dynamically created and some tracers add their
   own options. When a tracer adds their own list of options, the
   trace_array holding them has an array to hold the list of options for
   each tracer. This array increases in size via a krealloc(), and the
   new entry gets a newly allocated array to hold the options of the new
   tracer being added.

   The element in each entry of the tracer's option array holds a
   pointer back to the trace_array, a pointer to the tracer it is
   associated to, a pointer to the flags of the option.

   The issue is that these arrays are freed when the trace_array is
   freed when its instance it represents is removed from the instances
   directory. There's a race that an open of one of these options files
   can happen when the instance is being removed.

   Add a new helper function to be called by the open function of the
   options file to iterate all existing trace_arrays under a lock and
   find the one that has the given option element in one of it's tracer
   arrays. If found, then update the associated trace_array's reference
   counter to keep it from being freed. If not found, have the open call
   return -ENODEV.

 - Disable interrupts when acquiring the lock in rb_wake_up_waiters()

   The function rb_wake_up_waiters() assumes it will be called in
   interrupt context and does not disable irqs when taking
   cpu_buffer->reader_lock, which can be called in hard interrupt
   context. The issue is in PREEMPT_RT, this function is called in
   thread context leaving this lock open to a deadlock.

   Take the lock with interrupts disabled.

 - Use rcu_assign_pointer() for tmp_ops filter hash

   The tmp_ops used in update_ftrace_direct_mod() assigns its
   filter_hash field directly, but that field is annotated as __rcu and
   sparse complains. Assign it with rcu_assign_pointer()

 - Fix use-after-free in enable_trigger_private_data_free()

   The trace_event_call is accessed through the event_trigger_data's
   trace_event_file pointer to put the trace_event_call on freeing. The
   issue is that the trace_event_file data may have been freed already
   causing a use-after-free. Add a field to the event_trigger_data that
   points directly to the trace_event_call so that it can decrement its
   reference directly without needing to go through the
   trace_event_file.

 - Fix accounting of buffer data remote headers

   trace_buffer_desc_size() and trace_remote_alloc_buffer() undercount
   the number of pages is needed for the asked for size as it doesn't
   take into account the meta data on each page. Add a helper function
   to do the calculation properly and use that in these functions.

 - Catch nr_page_va overflow in ring_buffer_desc sizing

   The number of pages per remote ring buffer is capped by
   ring_buffer_desc::nr_page_va (32 bits). A buffer_size large enough to
   overflow that field would silently allocate a descriptor smaller than
   what was asked for.

 - Do not resize the subbuf order if any per_cpu buffer is disabled

   The mmapping of ring buffers disables resizing the subbuffers, but it
   is done per-cpu whereas the subbuf size change is done for all the
   per_cpu buffers under the buffer->mutex. It could change the size of
   some while the mapping is happening on others. Have the resize of the
   subbuf order check all the per_cpu buffers under the lock to see if
   any of them is disabled before starting and causing an inconsistency
   between buffers that are being mapped.

* tag 'trace-v7.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: (25 commits)
  ring-buffer: Check resize_disabled before publishing the new subbuf order
  tracing/remotes: Catch nr_page_va overflow in ring_buffer_desc sizing
  tracing/remotes: Account for ring buffer page header in size calculation
  tracing: Don't dereference trace_event_file in deferred trigger free
  ftrace: Use rcu_assign_pointer() for tmp_ops filter hash
  ring-buffer: Acquire the lock with irqsave in rb_wake_up_waiters()
  tracing: Take trace_array reference when opening a tracer options file
  tracing: Fix ring_buffer_read_page_size() kernel-doc
  tracing: Restore :mod: trailer after parsing in ftrace_set_clr_event()
  tracing: Fix memory corruption from a "STACKTRACE" histogram key
  tracing: Fix memory corruption from the histogram stacktrace modifier
  tracing: Undo the registration when enabling the histogram trigger fails
  tracing: Take the reference before publishing the named histogram trigger
  tracing: Set the trace clock before registering the histogram trigger
  tracing: Fix typo "preceeded" in comment
  tracing: Fix typo "availabe" in comment
  tracing: Let histogram values keep the percent and graph modifiers
  tracing: Keep the entry count when the histogram stats allocation fails
  tracing: Free histogram the field rejected for a bad modifier
  tracing: Free histogram the var ref when its initialization fails
  ...

1 files changed, 530 insertions, 0 deletions

diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
new file mode 100644
index 000000000..060501b37
--- /dev/null
+++ b/net/ipv4/fib_rules.c
@@ -0,0 +1,530 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * INET		An implementation of the TCP/IP protocol suite for the LINUX
+ *		operating system.  INET is implemented using the  BSD Socket
+ *		interface as the means of communication with the user level.
+ *
+ *		IPv4 Forwarding Information Base: policy rules.
+ *
+ * Authors:	Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ *		Thomas Graf <tgraf@suug.ch>
+ *
+ * Fixes:
+ *		Rani Assaf	:	local_rule cannot be deleted
+ *		Marc Boucher	:	routing by fwmark
+ */
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/netlink.h>
+#include <linux/inetdevice.h>
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/rcupdate.h>
+#include <linux/export.h>
+#include <net/flow.h>
+#include <net/inet_dscp.h>
+#include <net/ip.h>
+#include <net/route.h>
+#include <net/tcp.h>
+#include <net/ip_fib.h>
+#include <net/nexthop.h>
+#include <net/fib_rules.h>
+#include <linux/indirect_call_wrapper.h>
+
+struct fib4_rule {
+	struct fib_rule		common;
+	u8			dst_len;
+	u8			src_len;
+	dscp_t			dscp;
+	dscp_t			dscp_mask;
+	u8			dscp_full:1;	/* DSCP or TOS selector */
+	__be32			src;
+	__be32			srcmask;
+	__be32			dst;
+	__be32			dstmask;
+#ifdef CONFIG_IP_ROUTE_CLASSID
+	u32			tclassid;
+#endif
+};
+
+static bool fib4_rule_matchall(const struct fib_rule *rule)
+{
+	struct fib4_rule *r = container_of(rule, struct fib4_rule, common);
+
+	if (r->dst_len || r->src_len || r->dscp)
+		return false;
+	return fib_rule_matchall(rule);
+}
+
+bool fib4_rule_default(const struct fib_rule *rule)
+{
+	if (!fib4_rule_matchall(rule) || rule->action != FR_ACT_TO_TBL ||
+	    rule->l3mdev)
+		return false;
+	if (rule->table != RT_TABLE_LOCAL && rule->table != RT_TABLE_MAIN &&
+	    rule->table != RT_TABLE_DEFAULT)
+		return false;
+	return true;
+}
+EXPORT_SYMBOL_GPL(fib4_rule_default);
+
+int fib4_rules_dump(struct net *net, struct notifier_block *nb,
+		    struct netlink_ext_ack *extack)
+{
+	return fib_rules_dump(net, nb, AF_INET, extack);
+}
+
+unsigned int fib4_rules_seq_read(const struct net *net)
+{
+	return fib_rules_seq_read(net, AF_INET);
+}
+
+int __fib_lookup(struct net *net, struct flowi4 *flp,
+		 struct fib_result *res, unsigned int flags)
+{
+	struct fib_lookup_arg arg = {
+		.result = res,
+		.flags = flags,
+	};
+	int err;
+
+	/* update flow if oif or iif point to device enslaved to l3mdev */
+	l3mdev_update_flow(net, flowi4_to_flowi(flp));
+
+	err = fib_rules_lookup(net->ipv4.rules_ops, flowi4_to_flowi(flp), 0, &arg);
+#ifdef CONFIG_IP_ROUTE_CLASSID
+	if (arg.rule)
+		res->tclassid = ((struct fib4_rule *)arg.rule)->tclassid;
+	else
+		res->tclassid = 0;
+#endif
+
+	if (err == -ESRCH)
+		err = -ENETUNREACH;
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(__fib_lookup);
+
+INDIRECT_CALLABLE_SCOPE int fib4_rule_action(struct fib_rule *rule,
+					     struct flowi *flp, int flags,
+					     struct fib_lookup_arg *arg)
+{
+	int err = -EAGAIN;
+	struct fib_table *tbl;
+	u32 tb_id;
+
+	switch (rule->action) {
+	case FR_ACT_TO_TBL:
+		break;
+
+	case FR_ACT_UNREACHABLE:
+		return -ENETUNREACH;
+
+	case FR_ACT_PROHIBIT:
+		return -EACCES;
+
+	case FR_ACT_BLACKHOLE:
+	default:
+		return -EINVAL;
+	}
+
+	rcu_read_lock();
+
+	tb_id = fib_rule_get_table(rule, arg);
+	tbl = fib_get_table(rule->fr_net, tb_id);
+	if (tbl)
+		err = fib_table_lookup(tbl, &flp->u.ip4,
+				       (struct fib_result *)arg->result,
+				       arg->flags);
+
+	rcu_read_unlock();
+	return err;
+}
+
+INDIRECT_CALLABLE_SCOPE bool fib4_rule_suppress(struct fib_rule *rule,
+						int flags,
+						struct fib_lookup_arg *arg)
+{
+	struct fib_result *result = arg->result;
+	struct net_device *dev = NULL;
+
+	if (result->fi) {
+		struct fib_nh_common *nhc = fib_info_nhc(result->fi, 0);
+
+		dev = nhc->nhc_dev;
+	}
+
+	/* do not accept result if the route does
+	 * not meet the required prefix length
+	 */
+	if (result->prefixlen <= rule->suppress_prefixlen)
+		goto suppress_route;
+
+	/* do not accept result if the route uses a device
+	 * belonging to a forbidden interface group
+	 */
+	if (rule->suppress_ifgroup != -1 && dev && dev->group == rule->suppress_ifgroup)
+		goto suppress_route;
+
+	return false;
+
+suppress_route:
+	if (!(arg->flags & FIB_LOOKUP_NOREF))
+		fib_info_put(result->fi);
+	return true;
+}
+
+INDIRECT_CALLABLE_SCOPE int fib4_rule_match(struct fib_rule *rule,
+					    struct flowi *fl, int flags)
+{
+	struct fib4_rule *r = (struct fib4_rule *) rule;
+	struct flowi4 *fl4 = &fl->u.ip4;
+	__be32 daddr = fl4->daddr;
+	__be32 saddr = fl4->saddr;
+
+	if (((saddr ^ r->src) & r->srcmask) ||
+	    ((daddr ^ r->dst) & r->dstmask))
+		return 0;
+
+	/* When DSCP selector is used we need to match on the entire DSCP field
+	 * in the flow information structure. When TOS selector is used we need
+	 * to mask the upper three DSCP bits prior to matching to maintain
+	 * legacy behavior.
+	 */
+	if (r->dscp_full && (r->dscp ^ fl4->flowi4_dscp) & r->dscp_mask)
+		return 0;
+	else if (!r->dscp_full && r->dscp &&
+		 !fib_dscp_masked_match(r->dscp, fl4))
+		return 0;
+
+	if (rule->ip_proto && (rule->ip_proto != fl4->flowi4_proto))
+		return 0;
+
+	if (!fib_rule_port_match(&rule->sport_range, rule->sport_mask,
+				 fl4->fl4_sport))
+		return 0;
+
+	if (!fib_rule_port_match(&rule->dport_range, rule->dport_mask,
+				 fl4->fl4_dport))
+		return 0;
+
+	return 1;
+}
+
+#define FIB_MAX_AUTO_TABLE_ID  4096
+
+static struct fib_table *fib_empty_table(struct net *net)
+{
+	u32 id = 1;
+
+	while (1) {
+		if (!fib_get_table(net, id))
+			return fib_new_table(net, id);
+
+		if (id++ == FIB_MAX_AUTO_TABLE_ID)
+			break;
+	}
+	return NULL;
+}
+
+static int fib4_nl2rule_dscp(const struct nlattr *nla, struct fib4_rule *rule4,
+			     struct netlink_ext_ack *extack)
+{
+	if (rule4->dscp) {
+		NL_SET_ERR_MSG(extack, "Cannot specify both TOS and DSCP");
+		return -EINVAL;
+	}
+
+	rule4->dscp = inet_dsfield_to_dscp(nla_get_u8(nla) << 2);
+	rule4->dscp_mask = inet_dsfield_to_dscp(INET_DSCP_MASK);
+	rule4->dscp_full = true;
+
+	return 0;
+}
+
+static int fib4_nl2rule_dscp_mask(const struct nlattr *nla,
+				  struct fib4_rule *rule4,
+				  struct netlink_ext_ack *extack)
+{
+	dscp_t dscp_mask;
+
+	if (!rule4->dscp_full) {
+		NL_SET_ERR_MSG_ATTR(extack, nla,
+				    "Cannot specify DSCP mask without DSCP value");
+		return -EINVAL;
+	}
+
+	dscp_mask = inet_dsfield_to_dscp(nla_get_u8(nla) << 2);
+	if (rule4->dscp & ~dscp_mask) {
+		NL_SET_ERR_MSG_ATTR(extack, nla, "Invalid DSCP mask");
+		return -EINVAL;
+	}
+
+	rule4->dscp_mask = dscp_mask;
+
+	return 0;
+}
+
+static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
+			       struct fib_rule_hdr *frh,
+			       struct nlattr **tb,
+			       struct netlink_ext_ack *extack)
+{
+	struct fib4_rule *rule4 = (struct fib4_rule *)rule;
+	struct net *net = rule->fr_net;
+	int err = -EINVAL;
+
+	if (tb[FRA_FLOWLABEL] || tb[FRA_FLOWLABEL_MASK]) {
+		NL_SET_ERR_MSG(extack,
+			       "Flow label cannot be specified for IPv4 FIB rules");
+		goto errout;
+	}
+
+	if (!inet_validate_dscp(frh->tos)) {
+		NL_SET_ERR_MSG(extack,
+			       "Invalid dsfield (tos): ECN bits must be 0");
+		goto errout;
+	}
+	/* IPv4 currently doesn't handle high order DSCP bits correctly */
+	if (frh->tos & ~IPTOS_TOS_MASK) {
+		NL_SET_ERR_MSG(extack, "Invalid tos");
+		goto errout;
+	}
+	rule4->dscp = inet_dsfield_to_dscp(frh->tos);
+
+	if (tb[FRA_DSCP] &&
+	    fib4_nl2rule_dscp(tb[FRA_DSCP], rule4, extack) < 0)
+		goto errout;
+
+	if (tb[FRA_DSCP_MASK] &&
+	    fib4_nl2rule_dscp_mask(tb[FRA_DSCP_MASK], rule4, extack) < 0)
+		goto errout;
+
+	if (!net->ipv4.fib_has_custom_rules) {
+		/* split local/main if they are not already split */
+		err = fib_unmerge(net);
+		if (err)
+			goto errout;
+	}
+
+	if (rule->table == RT_TABLE_UNSPEC && !rule->l3mdev) {
+		if (rule->action == FR_ACT_TO_TBL) {
+			struct fib_table *table;
+
+			table = fib_empty_table(net);
+			if (!table) {
+				err = -ENOBUFS;
+				goto errout;
+			}
+
+			rule->table = table->tb_id;
+		}
+	}
+
+	if (frh->src_len)
+		rule4->src = nla_get_in_addr(tb[FRA_SRC]);
+
+	if (frh->dst_len)
+		rule4->dst = nla_get_in_addr(tb[FRA_DST]);
+
+#ifdef CONFIG_IP_ROUTE_CLASSID
+	if (tb[FRA_FLOW]) {
+		rule4->tclassid = nla_get_u32(tb[FRA_FLOW]);
+		if (rule4->tclassid)
+			atomic_inc(&net->ipv4.fib_num_tclassid_users);
+	}
+#endif
+
+	if (fib_rule_requires_fldissect(rule))
+		net->ipv4.fib_rules_require_fldissect++;
+
+	rule4->src_len = frh->src_len;
+	rule4->srcmask = inet_make_mask(rule4->src_len);
+	rule4->dst_len = frh->dst_len;
+	rule4->dstmask = inet_make_mask(rule4->dst_len);
+
+	net->ipv4.fib_has_custom_rules = true;
+
+	err = 0;
+errout:
+	return err;
+}
+
+static void fib4_rule_delete(struct fib_rule *rule)
+{
+	struct net *net = rule->fr_net;
+
+#ifdef CONFIG_IP_ROUTE_CLASSID
+	if (((struct fib4_rule *)rule)->tclassid)
+		atomic_dec(&net->ipv4.fib_num_tclassid_users);
+#endif
+
+	if (net->ipv4.fib_rules_require_fldissect &&
+	    fib_rule_requires_fldissect(rule))
+		net->ipv4.fib_rules_require_fldissect--;
+}
+
+static int fib4_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh,
+			     struct nlattr **tb)
+{
+	struct fib4_rule *rule4 = (struct fib4_rule *) rule;
+
+	if (frh->src_len && (rule4->src_len != frh->src_len))
+		return 0;
+
+	if (frh->dst_len && (rule4->dst_len != frh->dst_len))
+		return 0;
+
+	if (frh->tos &&
+	    (rule4->dscp_full ||
+	     inet_dscp_to_dsfield(rule4->dscp) != frh->tos))
+		return 0;
+
+	if (tb[FRA_DSCP]) {
+		dscp_t dscp;
+
+		dscp = inet_dsfield_to_dscp(nla_get_u8(tb[FRA_DSCP]) << 2);
+		if (!rule4->dscp_full || rule4->dscp != dscp)
+			return 0;
+	}
+
+	if (tb[FRA_DSCP_MASK]) {
+		dscp_t dscp_mask;
+
+		dscp_mask = inet_dsfield_to_dscp(nla_get_u8(tb[FRA_DSCP_MASK]) << 2);
+		if (!rule4->dscp_full || rule4->dscp_mask != dscp_mask)
+			return 0;
+	}
+
+#ifdef CONFIG_IP_ROUTE_CLASSID
+	if (tb[FRA_FLOW] && (rule4->tclassid != nla_get_u32(tb[FRA_FLOW])))
+		return 0;
+#endif
+
+	if (frh->src_len && (rule4->src != nla_get_in_addr(tb[FRA_SRC])))
+		return 0;
+
+	if (frh->dst_len && (rule4->dst != nla_get_in_addr(tb[FRA_DST])))
+		return 0;
+
+	return 1;
+}
+
+static int fib4_rule_fill(struct fib_rule *rule, struct sk_buff *skb,
+			  struct fib_rule_hdr *frh)
+{
+	struct fib4_rule *rule4 = (struct fib4_rule *) rule;
+
+	frh->dst_len = rule4->dst_len;
+	frh->src_len = rule4->src_len;
+
+	if (rule4->dscp_full) {
+		frh->tos = 0;
+		if (nla_put_u8(skb, FRA_DSCP,
+			       inet_dscp_to_dsfield(rule4->dscp) >> 2) ||
+		    nla_put_u8(skb, FRA_DSCP_MASK,
+			       inet_dscp_to_dsfield(rule4->dscp_mask) >> 2))
+			goto nla_put_failure;
+	} else {
+		frh->tos = inet_dscp_to_dsfield(rule4->dscp);
+	}
+
+	if ((rule4->dst_len &&
+	     nla_put_in_addr(skb, FRA_DST, rule4->dst)) ||
+	    (rule4->src_len &&
+	     nla_put_in_addr(skb, FRA_SRC, rule4->src)))
+		goto nla_put_failure;
+#ifdef CONFIG_IP_ROUTE_CLASSID
+	if (rule4->tclassid &&
+	    nla_put_u32(skb, FRA_FLOW, rule4->tclassid))
+		goto nla_put_failure;
+#endif
+	return 0;
+
+nla_put_failure:
+	return -ENOBUFS;
+}
+
+static size_t fib4_rule_nlmsg_payload(struct fib_rule *rule)
+{
+	return nla_total_size(4) /* dst */
+	       + nla_total_size(4) /* src */
+	       + nla_total_size(4) /* flow */
+	       + nla_total_size(1) /* dscp */
+	       + nla_total_size(1); /* dscp mask */
+}
+
+static void fib4_rule_flush_cache(struct fib_rules_ops *ops)
+{
+	rt_cache_flush(ops->fro_net);
+}
+
+static bool fib4_rule_need_rtnl(struct net *net)
+{
+	return !net->ipv4.fib_has_custom_rules;
+}
+
+static const struct fib_rules_ops __net_initconst fib4_rules_ops_template = {
+	.family		= AF_INET,
+	.rule_size	= sizeof(struct fib4_rule),
+	.addr_size	= sizeof(u32),
+	.action		= fib4_rule_action,
+	.suppress	= fib4_rule_suppress,
+	.match		= fib4_rule_match,
+	.configure	= fib4_rule_configure,
+	.delete		= fib4_rule_delete,
+	.compare	= fib4_rule_compare,
+	.fill		= fib4_rule_fill,
+	.nlmsg_payload	= fib4_rule_nlmsg_payload,
+	.flush_cache	= fib4_rule_flush_cache,
+	.need_rtnl	= fib4_rule_need_rtnl,
+	.nlgroup	= RTNLGRP_IPV4_RULE,
+	.owner		= THIS_MODULE,
+};
+
+static int fib_default_rules_init(struct fib_rules_ops *ops)
+{
+	int err;
+
+	err = fib_default_rule_add(ops, 0, RT_TABLE_LOCAL);
+	if (err < 0)
+		return err;
+	err = fib_default_rule_add(ops, 0x7FFE, RT_TABLE_MAIN);
+	if (err < 0)
+		return err;
+	err = fib_default_rule_add(ops, 0x7FFF, RT_TABLE_DEFAULT);
+	if (err < 0)
+		return err;
+	return 0;
+}
+
+int __net_init fib4_rules_init(struct net *net)
+{
+	int err;
+	struct fib_rules_ops *ops;
+
+	ops = fib_rules_register(&fib4_rules_ops_template, net);
+	if (IS_ERR(ops))
+		return PTR_ERR(ops);
+
+	err = fib_default_rules_init(ops);
+	if (err < 0)
+		goto fail;
+	net->ipv4.rules_ops = ops;
+	net->ipv4.fib_has_custom_rules = false;
+	net->ipv4.fib_rules_require_fldissect = 0;
+	return 0;
+
+fail:
+	/* also cleans all rules already added */
+	fib_rules_unregister(ops);
+	return err;
+}
+
+void __net_exit fib4_rules_exit(struct net *net)
+{
+	fib_rules_unregister(net->ipv4.rules_ops);
+}