netfilter: x_tables: Switch synchronization to RCU

When running concurrent iptables rules replacement with data, the per CPU
sequence count is checked after the assignment of the new information.
The sequence count is used to synchronize with the packet path without the
use of any explicit locking. If there are any packets in the packet path using
the table information, the sequence count is incremented to an odd value and
is incremented to an even after the packet process completion.

The new table value assignment is followed by a write memory barrier so every
CPU should see the latest value. If the packet path has started with the old
table information, the sequence counter will be odd and the iptables
replacement will wait till the sequence count is even prior to freeing the
old table info.

However, this assumes that the new table information assignment and the memory
barrier is actually executed prior to the counter check in the replacement
thread. If CPU decides to execute the assignment later as there is no user of
the table information prior to the sequence check, the packet path in another
CPU may use the old table information. The replacement thread would then free
the table information under it leading to a use after free in the packet
processing context-

Unable to handle kernel NULL pointer dereference at virtual
address 000000000000008e
pc : ip6t_do_table+0x5d0/0x89c
lr : ip6t_do_table+0x5b8/0x89c
ip6t_do_table+0x5d0/0x89c
ip6table_filter_hook+0x24/0x30
nf_hook_slow+0x84/0x120
ip6_input+0x74/0xe0
ip6_rcv_finish+0x7c/0x128
ipv6_rcv+0xac/0xe4
__netif_receive_skb+0x84/0x17c
process_backlog+0x15c/0x1b8
napi_poll+0x88/0x284
net_rx_action+0xbc/0x23c
__do_softirq+0x20c/0x48c

This could be fixed by forcing instruction order after the new table
information assignment or by switching to RCU for the synchronization.

Fixes: 80055dab5de0 ("netfilter: x_tables: make xt_replace_table wait until old rules are not used anymore")
Reported-by: Sean Tranchetti <stranche@codeaurora.org>
Reported-by: kernel test robot <lkp@intel.com>
Suggested-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

1 files changed, 15 insertions, 34 deletions

diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index af22dbe85e2c..acce622582e3 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -1349,6 +1349,14 @@ struct xt_counters *xt_counters_alloc(unsigned int counters)
 }
 EXPORT_SYMBOL(xt_counters_alloc);
 
+struct xt_table_info
+*xt_table_get_private_protected(const struct xt_table *table)
+{
+	return rcu_dereference_protected(table->private,
+					 mutex_is_locked(&xt[table->af].mutex));
+}
+EXPORT_SYMBOL(xt_table_get_private_protected);
+
 struct xt_table_info *
 xt_replace_table(struct xt_table *table,
 	      unsigned int num_counters,
@@ -1356,7 +1364,6 @@ xt_replace_table(struct xt_table *table,
 	      int *error)
 {
 	struct xt_table_info *private;
-	unsigned int cpu;
 	int ret;
 
 	ret = xt_jumpstack_alloc(newinfo);
@@ -1366,47 +1373,20 @@ xt_replace_table(struct xt_table *table,
 	}
 
 	/* Do the substitution. */
-	local_bh_disable();
-	private = table->private;
+	private = xt_table_get_private_protected(table);
 
 	/* Check inside lock: is the old number correct? */
 	if (num_counters != private->number) {
 		pr_debug("num_counters != table->private->number (%u/%u)\n",
 			 num_counters, private->number);
-		local_bh_enable();
 		*error = -EAGAIN;
 		return NULL;
 	}
 
 	newinfo->initial_entries = private->initial_entries;
-	/*
-	 * Ensure contents of newinfo are visible before assigning to
-	 * private.
-	 */
-	smp_wmb();
-	table->private = newinfo;
-
-	/* make sure all cpus see new ->private value */
-	smp_wmb();
 
-	/*
-	 * Even though table entries have now been swapped, other CPU's
-	 * may still be using the old entries...
-	 */
-	local_bh_enable();
-
-	/* ... so wait for even xt_recseq on all cpus */
-	for_each_possible_cpu(cpu) {
-		seqcount_t *s = &per_cpu(xt_recseq, cpu);
-		u32 seq = raw_read_seqcount(s);
-
-		if (seq & 1) {
-			do {
-				cond_resched();
-				cpu_relax();
-			} while (seq == raw_read_seqcount(s));
-		}
-	}
+	rcu_assign_pointer(table->private, newinfo);
+	synchronize_rcu();
 
 	audit_log_nfcfg(table->name, table->af, private->number,
 			!private->number ? AUDIT_XT_OP_REGISTER :
@@ -1442,12 +1422,12 @@ struct xt_table *xt_register_table(struct net *net,
 	}
 
 	/* Simplifies replace_table code. */
-	table->private = bootstrap;
+	rcu_assign_pointer(table->private, bootstrap);
 
 	if (!xt_replace_table(table, 0, newinfo, &ret))
 		goto unlock;
 
-	private = table->private;
+	private = xt_table_get_private_protected(table);
 	pr_debug("table->private->number = %u\n", private->number);
 
 	/* save number of initial entries */
@@ -1470,7 +1450,8 @@ void *xt_unregister_table(struct xt_table *table)
 	struct xt_table_info *private;
 
 	mutex_lock(&xt[table->af].mutex);
-	private = table->private;
+	private = xt_table_get_private_protected(table);
+	RCU_INIT_POINTER(table->private, NULL);
 	list_del(&table->list);
 	mutex_unlock(&xt[table->af].mutex);
 	audit_log_nfcfg(table->name, table->af, private->number,