IPVS: fixes after the new hash tables
Subsystems (3)
Julian Anastasov
maintainerv4 cover IPVS: fixes after the new hash tables
Hello,
This patchset contains fixes after the recent net-next
work for resizable hash tables. We target multiple reports from Sashiko and one from syzkaller. The patches are based on the net tree where the fixed commits are present...
v4:
patch 3: add error message for too many hash table changes in ip_vs_conn_fill_cport()
v3:
patch 3: use cp->lock in ip_vs_conn_fill_cport() to protect the cp->flags modifications
v2:
* patch 3: remove cp->lock from ip_vs_conn_fill_cport() and avoid races with resizing and possible multiple attempts to fill cport.
Julian Anastasov (3):
ipvs: fixes for the new ip_vs_status info
ipvs: fix races around the conn_lfactor and svc_lfactor sysctl vars
ipvs: fix the spin_lock usage for RT build
net/netfilter/ipvs/ip_vs_conn.c | 71 +++++++++++++++++---------------- net/netfilter/ipvs/ip_vs_ctl.c | 63 ++++++++++++++++++++--------- 2 files changed, 82 insertions(+), 52 deletions(-)
Signature · 1 line
2.53.0
Julian Anastasov
maintainerPATCH v4 1/3 ipvs: fixes for the new ip_vs_status info
Sashiko reports some problems for the recently added /proc/net/ip_vs_status:
* ip_vs_status_show() as a table reader may run long after the conn_tab and svc_table table are released. While ip_vs_conn_flush() properly changes the conn_tab_changes counter when conn_tab is removed, ip_vs_del_service() and ip_vs_flush() were missing such change for the svc_table_changes counter. As result, readers like ip_vs_dst_event() and ip_vs_status_show() may continue to use a freed table after a cond_resched_rcu() call.
* While counting the buckets in ip_vs_status_show() make sure we traverse only the needed number of entries in the chain. This also prevents possible overflow of the 'count' variable.
* Add check for 'loops' to prevent infinite loops while restarting the traversal on table change.
* While IP_VS_CONN_TAB_MAX_BITS is 20 on 32-bit platforms and there is no risk to overflow when multiplying the number of conn_tab buckets to 100, prefer the div_u64() helper to make the following dividing safer.
* Use 0440 permissions for ip_vs_status to restrict the info only to root due to the exported information for hash distribution.
--- net/netfilter/ipvs/ip_vs_ctl.c | 51 ++++++++++++++++++++++++---------- 1 file changed, 36 insertions(+), 15 deletions(-)
net/netfilter/ipvs/ip_vs_ctl.c +36 -15
@@ -2032,6 +2032,9 @@ static int ip_vs_del_service(struct ip_vs_service *svc)cancel_delayed_work_sync (&ipvs->svc_resize_work);if (t) {rcu_assign_pointer (ipvs->svc_table,NULL ); +/* Inform readers that table is removed */ +smp_mb__before_atomic (); +atomic_inc (&ipvs->svc_table_changes);while (1 ) { p =rcu_dereference_protected (t->new_tbl,1 );call_rcu (&t->rcu_head, ip_vs_rht_rcu_free);
@@ -2078,6 +2081,9 @@ static int ip_vs_flush(struct netns_ipvs *ipvs, bool cleanup) t =rcu_dereference_protected (ipvs->svc_table,1 );if (t) {rcu_assign_pointer (ipvs->svc_table,NULL ); +/* Inform readers that table is removed */ +smp_mb__before_atomic (); +atomic_inc (&ipvs->svc_table_changes);while (1 ) { p =rcu_dereference_protected (t->new_tbl,1 );call_rcu (&t->rcu_head, ip_vs_rht_rcu_free);
@@ -3004,7 +3010,8 @@ static int ip_vs_status_show(struct seq_file *seq, void *v)int old_gen, new_gen;u32 counts[8 ];u32 bucket; -int count; +u32 count; +int loops;u32 sum1;u32 sum;int i;
@@ -3020,6 +3027,7 @@ static int ip_vs_status_show(struct seq_file *seq, void *v)if (!atomic_read (&ipvs->conn_count)) goto after_conns; old_gen =atomic_read (&ipvs->conn_tab_changes); + loops =0 ; repeat_conn:smp_rmb ();/* ipvs->conn_tab and conn_tab_changes */
@@ -3032,8 +3040,11 @@ static int ip_vs_status_show(struct seq_file *seq, void *v) resched_score++; ip_vs_rht_walk_bucket_rcu(t, bucket, head) { count =0 ; -hlist_bl_for_each_entry_rcu (hn, e, head, node) +hlist_bl_for_each_entry_rcu (hn, e, head, node) { count++; +if (count >=ARRAY_SIZE (counts) -1 ) +break ; + } } resched_score += count;if (resched_score >=100 ) {
@@ -3042,37 +3053,41 @@ static int ip_vs_status_show(struct seq_file *seq, void *v) new_gen =atomic_read (&ipvs->conn_tab_changes);/* New table installed ? */ if (old_gen != new_gen) { +/* Too many changes? */ +if (++loops >=5 ) + goto after_conns; old_gen = new_gen; goto repeat_conn; } } - counts[min (count, (int )ARRAY_SIZE (counts) -1 )]++; + counts[count]++; } }for (sum =0 , i =0 ; i <ARRAY_SIZE (counts); i++) sum += counts[i]; sum1 = sum - counts[0 ]; -seq_printf (seq,"Conn buckets empty:\t%u (%lu%%)\n" , - counts[0 ], (unsigned long )counts[0 ] *100 /max (sum,1U )); +seq_printf (seq,"Conn buckets empty:\t%u (%llu%%)\n" , + counts[0 ],div_u64 ((u64 )counts[0 ] *100U ,max (sum,1U )));for (i =1 ; i <ARRAY_SIZE (counts); i++) {if (!counts[i])continue ; -seq_printf (seq,"Conn buckets len-%d:\t%u (%lu%%)\n" , +seq_printf (seq,"Conn buckets len-%d:\t%u (%llu%%)\n" , i, counts[i], - (unsigned long )counts[i] *100 /max (sum1,1U )); +div_u64 ((u64 )counts[i] *100U ,max (sum1,1U ))); } after_conns: t =rcu_dereference (ipvs->svc_table); count =ip_vs_get_num_services (ipvs); -seq_printf (seq,"Services:\t%d\n" , count); +seq_printf (seq,"Services:\t%u\n" , count);seq_printf (seq,"Service buckets:\t%d (%d bits, lfactor %d)\n" , t ? t->size :0 , t ? t->bits :0 , t ? t->lfactor :0 );if (!count) goto after_svc; old_gen =atomic_read (&ipvs->svc_table_changes); + loops =0 ; repeat_svc:smp_rmb ();/* ipvs->svc_table and svc_table_changes */
@@ -3086,8 +3101,11 @@ static int ip_vs_status_show(struct seq_file *seq, void *v) ip_vs_rht_walk_bucket_rcu(t, bucket, head) { count =0 ;hlist_bl_for_each_entry_rcu (svc, e, head, - s_list) + s_list) { count++; +if (count >=ARRAY_SIZE (counts) -1 ) +break ; + } } resched_score += count;if (resched_score >=100 ) {
@@ -3096,24 +3114,27 @@ static int ip_vs_status_show(struct seq_file *seq, void *v) new_gen =atomic_read (&ipvs->svc_table_changes);/* New table installed ? */ if (old_gen != new_gen) { +/* Too many changes? */ +if (++loops >=5 ) + goto after_svc; old_gen = new_gen; goto repeat_svc; } } - counts[min (count, (int )ARRAY_SIZE (counts) -1 )]++; + counts[count]++; } }for (sum =0 , i =0 ; i <ARRAY_SIZE (counts); i++) sum += counts[i]; sum1 = sum - counts[0 ]; -seq_printf (seq,"Service buckets empty:\t%u (%lu%%)\n" , - counts[0 ], (unsigned long )counts[0 ] *100 /max (sum,1U )); +seq_printf (seq,"Service buckets empty:\t%u (%llu%%)\n" , + counts[0 ],div_u64 ((u64 )counts[0 ] *100U ,max (sum,1U )));for (i =1 ; i <ARRAY_SIZE (counts); i++) {if (!counts[i])continue ; -seq_printf (seq,"Service buckets len-%d:\t%u (%lu%%)\n" , +seq_printf (seq,"Service buckets len-%d:\t%u (%llu%%)\n" , i, counts[i], - (unsigned long )counts[i] *100 /max (sum1,1U )); +div_u64 ((u64 )counts[i] *100U ,max (sum1,1U ))); } after_svc:
@@ -5039,7 +5060,7 @@ int __net_init ip_vs_control_net_init(struct netns_ipvs *ipvs) ipvs->net->proc_net, ip_vs_stats_percpu_show, NULL)) goto err_percpu; -if (!proc_create_net_single ("ip_vs_status" ,0 , ipvs->net->proc_net, +if (!proc_create_net_single ("ip_vs_status" ,0440 , ipvs->net->proc_net, ip_vs_status_show,NULL )) goto err_status;#endif
Signature · 1 line
2.53.0
Julian Anastasov
maintainerPATCH v4 2/3 ipvs: fix races around the conn_lfactor and svc_lfactor sysctl vars
In reply to Julian AnastasovSashiko warns that the new sysctls vars can be changed after the hash tables are destroyed and their respective resizing works canceled, leading to mod_delayed_work() being called for canceled works.
Solve this in different ways. conn_tab can be present even without services and is destroyed only on netns exit, so use disable_delayed_work_sync() to disable the work instead of adding more synchronization mechanisms.
As for the svc_table, it is destroyed when the services are deleted, so we must be sure that netns exit is not called yet (the check for 'enable') and the work is not canceled by checking all under same mutex lock.
Also, use WRITE_ONCE when updating the sysctl vars as we already read them with READ_ONCE.
--- net/netfilter/ipvs/ip_vs_conn.c | 2 +- net/netfilter/ipvs/ip_vs_ctl.c | 12 +++++++++--- 2 files changed, 10 insertions(+), 4 deletions(-)
net/netfilter/ipvs/ip_vs_conn.c +1 -1
@@ -1835,7 +1835,7 @@ static void ip_vs_conn_flush(struct netns_ipvs *ipvs)if (!rcu_dereference_protected (ipvs->conn_tab,1 ))return ; -cancel_delayed_work_sync (&ipvs->conn_resize_work); +disable_delayed_work_sync (&ipvs->conn_resize_work);if (!atomic_read (&ipvs->conn_count)) goto unreg;
net/netfilter/ipvs/ip_vs_ctl.c +9 -3
@@ -2469,7 +2469,7 @@ static int ipvs_proc_conn_lfactor(const struct ctl_table *table, int write,if (val <-8 || val >8 ) { ret = -EINVAL ; }else { - *valp = val; +WRITE_ONCE (*valp, val);if (rcu_access_pointer (ipvs->conn_tab))mod_delayed_work (system_unbound_wq, &ipvs->conn_resize_work,0 );
@@ -2496,10 +2496,16 @@ static int ipvs_proc_svc_lfactor(const struct ctl_table *table, int write,if (val <-8 || val >8 ) { ret = -EINVAL ; }else { - *valp = val; -if (rcu_access_pointer (ipvs->svc_table)) +mutex_lock (&ipvs->service_mutex); +WRITE_ONCE (*valp, val); +/* Make sure the services are present */ +if (rcu_access_pointer (ipvs->svc_table) && +READ_ONCE (ipvs->enable) && + !test_bit (IP_VS_WORK_SVC_NORESIZE , + &ipvs->work_flags))mod_delayed_work (system_unbound_wq, &ipvs->svc_resize_work,0 ); +mutex_unlock (&ipvs->service_mutex); } }return ret;
Signature · 1 line
2.53.0
Julian Anastasov
maintainerPATCH v4 3/3 ipvs: fix the spin_lock usage for RT build
In reply to Julian Anastasovsyzbot reports for sleeping function called from invalid context [1]. The recently added code for resizable hash tables uses hlist_bl bit locks in combination with spin_lock for
the connection fields (cp->lock).
Fix the following problems:
* avoid using spin_lock(&cp->lock) under locked bit lock because it sleeps on PREEMPT_RT
* as the recent changes call ip_vs_conn_hash() only for newly allocated connection, the spin_lock can be removed there because the connection is still not linked to table and does not need cp->lock protection.
* the lock can be removed also from ip_vs_conn_unlink() where we are the last connection user.
* the last place that is fixed is ip_vs_conn_fill_cport() where now the cp->lock is locked before the other locks to ensure other packets do not modify the cp->flags in non-atomic way. Here we make sure cport and flags are changed only once if two or more packets race to fill the cport. Also, we fill cport early, so that if we race with resizing there will be valid cport key for the hashing. Add a warning if too many hash table changes occur for our RCU read-side critical section which is error condition but minor because the connection still can expire gracefully. Problems reported by Sashiko.
[1]:
BUG: sleeping function called from invalid context at kernel/locking/spinlock_rt.c:48
in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 16, name: ktimers/0preempt_count: 2, expected: 0
RCU nest depth: 3, expected: 3
8 locks held by ktimers/0/16:
#0: ffffffff8de5f260 (local_bh){.+.+}-{1:3}, at: __local_bh_disable_ip+0x3c/0x420 kernel/softirq.c:163 #1: ffffffff8dfc80c0 (rcu_read_lock){....}-{1:3}, at: __local_bh_disable_ip+0x3c/0x420 kernel/softirq.c:163 #2: ffff8880b8826360 (&base->expiry_lock){+...}-{3:3}, at: spin_lock include/linux/spinlock_rt.h:45 [inline] #2: ffff8880b8826360 (&base->expiry_lock){+...}-{3:3}, at: timer_base_lock_expiry kernel/time/timer.c:1502 [inline] #2: ffff8880b8826360 (&base->expiry_lock){+...}-{3:3}, at: __run_timer_base+0x120/0x9f0 kernel/time/timer.c:2384 #3: ffffffff8dfc80c0 (rcu_read_lock){....}-{1:3}, at: rcu_lock_acquire include/linux/rcupdate.h:300 [inline] #3: ffffffff8dfc80c0 (rcu_read_lock){....}-{1:3}, at: rcu_read_lock include/linux/rcupdate.h:838 [inline] #3: ffffffff8dfc80c0 (rcu_read_lock){....}-{1:3}, at: __rt_spin_lock kernel/locking/spinlock_rt.c:50 [inline] #3: ffffffff8dfc80c0 (rcu_read_lock){....}-{1:3}, at: rt_spin_lock+0x1e0/0x400 kernel/locking/spinlock_rt.c:57 #4: ffffc90000157a80 ((&cp->timer)){+...}-{0:0}, at: call_timer_fn+0xd4/0x5e0 kernel/time/timer.c:1745 #5: ffffffff8dfc80c0 (rcu_read_lock){....}-{1:3}, at: rcu_lock_acquire include/linux/rcupdate.h:300 [inline] #5: ffffffff8dfc80c0 (rcu_read_lock){....}-{1:3}, at: rcu_read_lock include/linux/rcupdate.h:838 [inline] #5: ffffffff8dfc80c0 (rcu_read_lock){....}-{1:3}, at: ip_vs_conn_unlink net/netfilter/ipvs/ip_vs_conn.c:315 [inline] #5: ffffffff8dfc80c0 (rcu_read_lock){....}-{1:3}, at: ip_vs_conn_expire+0x257/0x2390 net/netfilter/ipvs/ip_vs_conn.c:1260 #6: ffffffff8de5f260 (local_bh){.+.+}-{1:3}, at: __local_bh_disable_ip+0x3c/0x420 kernel/softirq.c:163 #7: ffff888068d4c3f0 (&cp->lock#2){+...}-{3:3}, at: spin_lock include/linux/spinlock_rt.h:45 [inline] #7: ffff888068d4c3f0 (&cp->lock#2){+...}-{3:3}, at: ip_vs_conn_unlink net/netfilter/ipvs/ip_vs_conn.c:324 [inline] #7: ffff888068d4c3f0 (&cp->lock#2){+...}-{3:3}, at: ip_vs_conn_expire+0xd4a/0x2390 net/netfilter/ipvs/ip_vs_conn.c:1260
Preemption disabled at:
[<ffffffff898a6358>] bit_spin_lock include/linux/bit_spinlock.h:38 [inline]
[<ffffffff898a6358>] hlist_bl_lock+0x18/0x110 include/linux/list_bl.h:149
CPU: 0 UID: 0 PID: 16 Comm: ktimers/0 Tainted: G W L syzkaller #0 PREEMPT_{RT,(full)}
Tainted: [W]=WARN, [L]=SOFTLOCKUP
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/18/2026
Call Trace:
<TASK>
dump_stack_lvl+0xe8/0x150 lib/dump_stack.c:120
__might_resched+0x329/0x480 kernel/sched/core.c:9162
__rt_spin_lock kernel/locking/spinlock_rt.c:48 [inline]
rt_spin_lock+0xc2/0x400 kernel/locking/spinlock_rt.c:57
spin_lock include/linux/spinlock_rt.h:45 [inline]
ip_vs_conn_unlink net/netfilter/ipvs/ip_vs_conn.c:324 [inline]
ip_vs_conn_expire+0xd4a/0x2390 net/netfilter/ipvs/ip_vs_conn.c:1260
call_timer_fn+0x192/0x5e0 kernel/time/timer.c:1748
expire_timers kernel/time/timer.c:1799 [inline]
__run_timers kernel/time/timer.c:2374 [inline]
__run_timer_base+0x6a3/0x9f0 kernel/time/timer.c:2386
run_timer_base kernel/time/timer.c:2395 [inline]
run_timer_softirq+0xb7/0x170 kernel/time/timer.c:2405
handle_softirqs+0x1de/0x6d0 kernel/softirq.c:622
__do_softirq kernel/softirq.c:656 [inline]
run_ktimerd+0x69/0x100 kernel/softirq.c:1151
smpboot_thread_fn+0x541/0xa50 kernel/smpboot.c:160
kthread+0x388/0x470 kernel/kthread.c:436
ret_from_fork+0x514/0xb70 arch/x86/kernel/process.c:158
ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:245
</TASK>--- net/netfilter/ipvs/ip_vs_conn.c | 69 +++++++++++++++++---------------- 1 file changed, 36 insertions(+), 33 deletions(-)
net/netfilter/ipvs/ip_vs_conn.c +36 -33
@@ -267,27 +267,20 @@ static inline int ip_vs_conn_hash(struct ip_vs_conn *cp) hash_key2 = hash_key; use2 = false; } +conn_tab_lock (t, cp, hash_key, hash_key2, use2, true/* new_hash */ , &head, &head2); -spin_lock (&cp->lock); - -if (!(cp->flags &IP_VS_CONN_F_HASHED )) { - cp->flags |=IP_VS_CONN_F_HASHED ; -WRITE_ONCE (cp->hn0.hash_key, hash_key); -WRITE_ONCE (cp->hn1.hash_key, hash_key2); -refcount_inc (&cp->refcnt); -hlist_bl_add_head_rcu (&cp->hn0.node, head); -if (use2) -hlist_bl_add_head_rcu (&cp->hn1.node, head2); - ret =1 ; - }else { -pr_err ("%s(): request for already hashed, called from %pS\n" , - __func__,__builtin_return_address (0 )); - ret =0 ; - } -spin_unlock (&cp->lock); + cp->flags |=IP_VS_CONN_F_HASHED ; +WRITE_ONCE (cp->hn0.hash_key, hash_key); +WRITE_ONCE (cp->hn1.hash_key, hash_key2); +refcount_inc (&cp->refcnt); +hlist_bl_add_head_rcu (&cp->hn0.node, head); +if (use2) +hlist_bl_add_head_rcu (&cp->hn1.node, head2); +conn_tab_unlock (head, head2); + ret =1 ;/* Schedule resizing if load increases */ if (atomic_read(&ipvs->conn_count) > t->u_thresh &&
@@ -321,7 +314,6 @@ static inline bool ip_vs_conn_unlink(struct ip_vs_conn *cp)conn_tab_lock (t, cp, hash_key, hash_key2, use2, false/* new_hash */ , &head, &head2); -spin_lock (&cp->lock);if (cp->flags &IP_VS_CONN_F_HASHED ) {/* Decrease refcnt and unlink conn only if we are last user */
@@ -334,7 +326,6 @@ static inline bool ip_vs_conn_unlink(struct ip_vs_conn *cp) } } -spin_unlock (&cp->lock);conn_tab_unlock (head, head2);rcu_read_unlock ();
@@ -637,6 +628,7 @@ void ip_vs_conn_fill_cport(struct ip_vs_conn *cp, __be16 cport)struct ip_vs_conn_hnode *hn;u32 hash_key, hash_key_new;struct ip_vs_conn_param p; +bool by_me = false;int ntbl;int dir;
@@ -664,8 +656,11 @@ void ip_vs_conn_fill_cport(struct ip_vs_conn *cp, __be16 cport) t =rcu_dereference (t->new_tbl); ntbl++;/* We are lost? */ -if (ntbl >=2 ) +if (ntbl >=2 ) { +IP_VS_ERR_RL ("%s(): Too many ht changes for dir %d\n" , + __func__, dir);return ; + } }/* Rehashing during resize? Use the recent table for adds */
@@ -683,10 +678,13 @@ void ip_vs_conn_fill_cport(struct ip_vs_conn *cp, __be16 cport)if (head > head2 && t == t2)swap (head, head2); +/* Protect the cp->flags modification */ +spin_lock_bh (&cp->lock); +/* Lock seqcount only for the old bucket, even if we are on new table * because it affects the del operation, not the adding. */ -spin_lock_bh (&t->lock[hash_key & t->lock_mask].l); +spin_lock (&t->lock[hash_key & t->lock_mask].l);preempt_disable_nested ();write_seqcount_begin (&t->seqc[hash_key & t->seqc_mask]);
@@ -704,14 +702,23 @@ void ip_vs_conn_fill_cport(struct ip_vs_conn *cp, __be16 cport)hlist_bl_unlock (head);write_seqcount_end (&t->seqc[hash_key & t->seqc_mask]);preempt_enable_nested (); -spin_unlock_bh (&t->lock[hash_key & t->lock_mask].l); +spin_unlock (&t->lock[hash_key & t->lock_mask].l); +spin_unlock_bh (&cp->lock); hash_key = hash_key_new; goto retry; } -spin_lock (&cp->lock); -if ((cp->flags &IP_VS_CONN_F_NO_CPORT ) && - (cp->flags &IP_VS_CONN_F_HASHED )) { +/* Fill cport once, even if multiple packets try to do it */ +if (cp->flags &IP_VS_CONN_F_NO_CPORT && (!cp->cport || by_me)) { +/* If we race with resizing make sure cport is set for dir 1 */ +if (!cp->cport) { + cp->cport = cport; + by_me = true; + } +if (!dir) { +atomic_dec (&ipvs->no_cport_conns[af_id]); + cp->flags &= ~IP_VS_CONN_F_NO_CPORT ; + }/* We do not recalc hash_key_r under lock, we assume the * parameters in cp do not change, i.e. cport is * the only possible change.
@@ -726,21 +733,17 @@ void ip_vs_conn_fill_cport(struct ip_vs_conn *cp, __be16 cport)hlist_bl_del_rcu (&hn->node);hlist_bl_add_head_rcu (&hn->node, head_new); } -if (!dir) { -atomic_dec (&ipvs->no_cport_conns[af_id]); - cp->flags &= ~IP_VS_CONN_F_NO_CPORT ; - cp->cport = cport; - } } -spin_unlock (&cp->lock);if (head != head2)hlist_bl_unlock (head2);hlist_bl_unlock (head);write_seqcount_end (&t->seqc[hash_key & t->seqc_mask]);preempt_enable_nested (); -spin_unlock_bh (&t->lock[hash_key & t->lock_mask].l); -if (dir--) +spin_unlock (&t->lock[hash_key & t->lock_mask].l); + +spin_unlock_bh (&cp->lock); +if (dir-- && by_me) goto next_dir; }
Signature · 1 line
2.53.0