diff mbox series

[v2,net,1/3] ipmr: add debug check for mr table cleanup

Message ID 64f267b5c0dd74f5bc8795b4ff868b5b103741da.1732289799.git.pabeni@redhat.com (mailing list archive)
State Accepted
Commit 11b6e701bce96f98474084f26821157cb0dccf69
Delegated to: Netdev Maintainers
Headers show
Series net: fix mcast RCU splats | expand

Checks

Context Check Description
netdev/series_format success Posting correctly formatted
netdev/tree_selection success Clearly marked for net
netdev/ynl success Generated files up to date; no warnings/errors; no diff in generated;
netdev/fixes_present success Fixes tag present in non-next series
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 3 this patch: 3
netdev/build_tools success No tools touched, skip
netdev/cc_maintainers success CCed 6 of 6 maintainers
netdev/build_clang success Errors and warnings before: 3 this patch: 3
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/deprecated_api success None detected
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 8 this patch: 8
netdev/checkpatch success total: 0 errors, 0 warnings, 0 checks, 64 lines checked
netdev/build_clang_rust success No Rust files in patch. Skipping build
netdev/kdoc success Errors and warnings before: 1 this patch: 1
netdev/source_inline success Was 0 now: 0
netdev/contest success net-next-2024-11-25--00-00 (tests: 791)

Commit Message

Paolo Abeni Nov. 24, 2024, 3:40 p.m. UTC 
The multicast route tables lifecycle, for both ipv4 and ipv6, is
protected by RCU using the RTNL lock for write access. In many
places a table pointer escapes the RCU (or RTNL) protected critical
section, but such scenarios are actually safe because tables are
deleted only at namespace cleanup time or just after allocation, in
case of default rule creation failure.

Tables freed at namespace cleanup time are assured to be alive for the
whole netns lifetime; tables freed just after creation time are never
exposed to other possible users.

Ensure that the free conditions are respected in ip{,6}mr_free_table, to
document the locking schema and to prevent future possible introduction
of 'table del' operation from breaking it.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
v1 -> v2:
 - fix build errors with CONFIG_IP{,V6}_MROUTE_MULTIPLE_TABLES=n
---
 net/ipv4/ipmr.c  | 14 ++++++++++++++
 net/ipv6/ip6mr.c | 14 ++++++++++++++
 2 files changed, 28 insertions(+)

Comments

David Ahern Nov. 26, 2024, 3:34 p.m. UTC | #1 
On 11/24/24 8:40 AM, Paolo Abeni wrote:
> The multicast route tables lifecycle, for both ipv4 and ipv6, is
> protected by RCU using the RTNL lock for write access. In many
> places a table pointer escapes the RCU (or RTNL) protected critical
> section, but such scenarios are actually safe because tables are
> deleted only at namespace cleanup time or just after allocation, in
> case of default rule creation failure.
> 
> Tables freed at namespace cleanup time are assured to be alive for the
> whole netns lifetime; tables freed just after creation time are never
> exposed to other possible users.
> 
> Ensure that the free conditions are respected in ip{,6}mr_free_table, to
> document the locking schema and to prevent future possible introduction
> of 'table del' operation from breaking it.
> 
> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
> ---
> v1 -> v2:
>  - fix build errors with CONFIG_IP{,V6}_MROUTE_MULTIPLE_TABLES=n
> ---
>  net/ipv4/ipmr.c  | 14 ++++++++++++++
>  net/ipv6/ip6mr.c | 14 ++++++++++++++
>  2 files changed, 28 insertions(+)
> 

Reviewed-by: David Ahern <dsahern@kernel.org>
diff mbox series

Patch

diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index c58dd78509a2..bac0776648e0 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -120,6 +120,11 @@  static void ipmr_expire_process(struct timer_list *t);
 				lockdep_rtnl_is_held() ||		\
 				list_empty(&net->ipv4.mr_tables))
 
+static bool ipmr_can_free_table(struct net *net)
+{
+	return !check_net(net) || !net->ipv4.mr_rules_ops;
+}
+
 static struct mr_table *ipmr_mr_table_iter(struct net *net,
 					   struct mr_table *mrt)
 {
@@ -302,6 +307,11 @@  EXPORT_SYMBOL(ipmr_rule_default);
 #define ipmr_for_each_table(mrt, net) \
 	for (mrt = net->ipv4.mrt; mrt; mrt = NULL)
 
+static bool ipmr_can_free_table(struct net *net)
+{
+	return !check_net(net);
+}
+
 static struct mr_table *ipmr_mr_table_iter(struct net *net,
 					   struct mr_table *mrt)
 {
@@ -413,6 +423,10 @@  static struct mr_table *ipmr_new_table(struct net *net, u32 id)
 
 static void ipmr_free_table(struct mr_table *mrt)
 {
+	struct net *net = read_pnet(&mrt->net);
+
+	DEBUG_NET_WARN_ON_ONCE(!ipmr_can_free_table(net));
+
 	timer_shutdown_sync(&mrt->ipmr_expire_timer);
 	mroute_clean_tables(mrt, MRT_FLUSH_VIFS | MRT_FLUSH_VIFS_STATIC |
 				 MRT_FLUSH_MFC | MRT_FLUSH_MFC_STATIC);
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index d66f58932a79..b80fca894916 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -108,6 +108,11 @@  static void ipmr_expire_process(struct timer_list *t);
 				lockdep_rtnl_is_held() || \
 				list_empty(&net->ipv6.mr6_tables))
 
+static bool ip6mr_can_free_table(struct net *net)
+{
+	return !check_net(net) || !net->ipv6.mr6_rules_ops;
+}
+
 static struct mr_table *ip6mr_mr_table_iter(struct net *net,
 					    struct mr_table *mrt)
 {
@@ -291,6 +296,11 @@  EXPORT_SYMBOL(ip6mr_rule_default);
 #define ip6mr_for_each_table(mrt, net) \
 	for (mrt = net->ipv6.mrt6; mrt; mrt = NULL)
 
+static bool ip6mr_can_free_table(struct net *net)
+{
+	return !check_net(net);
+}
+
 static struct mr_table *ip6mr_mr_table_iter(struct net *net,
 					    struct mr_table *mrt)
 {
@@ -392,6 +402,10 @@  static struct mr_table *ip6mr_new_table(struct net *net, u32 id)
 
 static void ip6mr_free_table(struct mr_table *mrt)
 {
+	struct net *net = read_pnet(&mrt->net);
+
+	DEBUG_NET_WARN_ON_ONCE(!ip6mr_can_free_table(net));
+
 	timer_shutdown_sync(&mrt->ipmr_expire_timer);
 	mroute_clean_tables(mrt, MRT6_FLUSH_MIFS | MRT6_FLUSH_MIFS_STATIC |
 				 MRT6_FLUSH_MFC | MRT6_FLUSH_MFC_STATIC);