bpf: using rcu_read_lock for bpf_sk_storage_map iterator
Subsystems (3)
PATCH v3 1/1 bpf: using rcu_read_lock for bpf_sk_storage_map iterator
If a bucket contains a lot of sockets, during bpf_iter traversing a bucket, concurrent userspace bpf_map_update_elem() and bpf program bpf_sk_storage_{get,delete}() may experience some undesirable delays as they will compete with bpf_iter for bucket lock.
Note that the number of buckets for bpf_sk_storage_map is roughly the same as the number of cpus. So if there are lots of sockets in the system, each bucket could contain lots of sockets.
Different actual use cases may experience different delays. Here, using selftest bpf_iter subtest bpf_sk_storage_map, I hacked the kernel with ktime_get_mono_fast_ns() to collect the time when a bucket was locked during bpf_iter prog traversing that bucket. This way, the maximum incurred delay was measured w.r.t. the number of elements in a bucket.
# elems in each bucket delay(ns)
64 17000
256 72512
2048 875246The potential delays will be further increased if
we have even more elemnts in a bucket. Using rcu_read_lock() is a reasonable compromise here. It may lose some precision, e.g., access stale sockets, but it will not hurt performance of bpf program or user space application which also tries to get/delete or update map elements.
--- net/core/bpf_sk_storage.c | 29 ++++++++++++----------------- 1 file changed, 12 insertions(+), 17 deletions(-)
Changelog:
v2 -> v3:
- fix a bug hlist_for_each_entry() => hlist_for_each_entry_rcu(). (Martin)
- use rcu_dereference() instead of rcu_dereference_raw() for lockdep checking. (Martin)
v1 -> v2:
- added some performance number. (Song)
- tried to silence some sparse complains. but still has some left like context imbalance in "..." - different lock contexts for basic block which the code is too hard for sparse to analyze. (Jakub)
net/core/bpf_sk_storage.c +12 -17
@@ -678,6 +678,7 @@ struct bpf_iter_seq_sk_storage_map_info {static struct bpf_local_storage_elem *bpf_sk_storage_map_seq_find_next (struct bpf_iter_seq_sk_storage_map_info *info,struct bpf_local_storage_elem *prev_selem) +__acquires (RCU )__releases (RCU ) {struct bpf_local_storage *sk_storage;struct bpf_local_storage_elem *selem;
@@ -701,11 +702,11 @@ bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info,if (!selem) {/* not found, unlock and go to the next bucket */ b = &smap->buckets[bucket_id++]; -raw_spin_unlock_bh (&b->lock); +rcu_read_unlock (); skip_elems =0 ;break ; } - sk_storage =rcu_dereference_raw (selem->local_storage); + sk_storage =rcu_dereference (selem->local_storage);if (sk_storage) { info->skip_elems = skip_elems + count;return selem;
@@ -715,10 +716,10 @@ bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info,for (i = bucket_id; i < (1U << smap->bucket_log); i++) { b = &smap->buckets[i]; -raw_spin_lock_bh (&b->lock); +rcu_read_lock (); count =0 ; -hlist_for_each_entry (selem, &b->list, map_node) { - sk_storage =rcu_dereference_raw (selem->local_storage); +hlist_for_each_entry_rcu (selem, &b->list, map_node) { + sk_storage =rcu_dereference (selem->local_storage);if (sk_storage && count >= skip_elems) { info->bucket_id = i; info->skip_elems = count;
@@ -726,7 +727,7 @@ bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info, } count++; } -raw_spin_unlock_bh (&b->lock); +rcu_read_unlock (); skip_elems =0 ; }
@@ -785,7 +786,7 @@ static int __bpf_sk_storage_map_seq_show(struct seq_file *seq, ctx.meta = &meta; ctx.map = info->map;if (selem) { - sk_storage =rcu_dereference_raw (selem->local_storage); + sk_storage =rcu_dereference (selem->local_storage); ctx.sk = sk_storage->owner; ctx.value =SDATA (selem)->data; }
@@ -801,18 +802,12 @@ static int bpf_sk_storage_map_seq_show(struct seq_file *seq, void *v) }static void bpf_sk_storage_map_seq_stop (struct seq_file *seq,void *v) +__releases (RCU ) { -struct bpf_iter_seq_sk_storage_map_info *info = seq->private; -struct bpf_local_storage_map *smap; -struct bpf_local_storage_map_bucket *b; - -if (!v) { +if (!v) (void )__bpf_sk_storage_map_seq_show (seq, v); - }else { - smap = (struct bpf_local_storage_map *)info->map; - b = &smap->buckets[info->bucket_id]; -raw_spin_unlock_bh (&b->lock); - } +else +rcu_read_unlock (); } static int bpf_iter_init_sk_storage_map(void *priv_data,
Signature · 1 line
2.24.1
On Tue, Sep 15, 2020 at 11:16:49PM -0700, Yonghong Song wrote:
[ ... ]
net/core/bpf_sk_storage.c struct bpf_iter_seq_sk_storage_map_info { · line 684
Quoted 12 lines
net/core/bpf_sk_storage.c +1
-0@@ -678,6 +678,7 @@ struct bpf_iter_seq_sk_storage_map_info {static struct bpf_local_storage_elem *bpf_sk_storage_map_seq_find_next (struct bpf_iter_seq_sk_storage_map_info *info,struct bpf_local_storage_elem *prev_selem) +__acquires (RCU )__releases (RCU ) {struct bpf_local_storage *sk_storage;struct bpf_local_storage_elem *selem;
In the while loop earlier in this function, if I read it correctly, it is sort of continuing the earlier hlist_for_each_entry_rcu() for the same bucket, so the hlist_entry_safe() needs to be changed also. Something like this (uncompiled code):
while (selem) {
- selem = hlist_entry_safe(selem->map_node.next,
+ selem = hlist_entry_safe(rcu_dereference(hlist_next_rcu(&selem->map_node)),
struct bpf_local_storage_elem, map_node);
if (!selem) {
/* not found, unlock and go to the next bucket */Quoted 14 lines
net/core/bpf_sk_storage.c +2
-2@@ -701,11 +702,11 @@ bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info,if (!selem) {/* not found, unlock and go to the next bucket */ b = &smap->buckets[bucket_id++]; -raw_spin_unlock_bh (&b->lock); +rcu_read_unlock (); skip_elems =0 ;break ; } - sk_storage =rcu_dereference_raw (selem->local_storage); + sk_storage =rcu_dereference (selem->local_storage);if (sk_storage) { info->skip_elems = skip_elems + count;return selem;
Quoted 21 lines · Martin KaFai Lau
On Tue, Sep 15, 2020 at 11:16:49PM -0700, Yonghong Song wrote:
[ ... ]net/core/bpf_sk_storage.c struct bpf_iter_seq_sk_storage_map_info { · line 684
Quoted 12 lines
net/core/bpf_sk_storage.c +1
-0@@ -678,6 +678,7 @@ struct bpf_iter_seq_sk_storage_map_info {static struct bpf_local_storage_elem *bpf_sk_storage_map_seq_find_next (struct bpf_iter_seq_sk_storage_map_info *info,struct bpf_local_storage_elem *prev_selem) +__acquires (RCU )__releases (RCU ) {struct bpf_local_storage *sk_storage;struct bpf_local_storage_elem *selem;In the while loop earlier in this function, if I read it correctly, it is sort of continuing the earlier
hlist_for_each_entry_rcu()for the same bucket, so thehlist_entry_safe()needs to be changed also. Something like this (uncompiled code):while (selem) {
Review
Quoted 5 lines
(quoted diff) +1
-1- selem = hlist_entry_safe(selem->map_node.next, + selem = hlist_entry_safe(rcu_dereference(hlist_next_rcu(&selem->map_node)), struct bpf_local_storage_elem, map_node); if (!selem) { /* not found, unlock and go to the next bucket */
Thanks and Ack. Will send v4 shortly.
Quoted 15 lines
Quoted 15 lines
net/core/bpf_sk_storage.c +2
-2@@ -701,11 +702,11 @@ bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info,if (!selem) {/* not found, unlock and go to the next bucket */ b = &smap->buckets[bucket_id++]; -raw_spin_unlock_bh (&b->lock); +rcu_read_unlock (); skip_elems =0 ;break ; } - sk_storage =rcu_dereference_raw (selem->local_storage); + sk_storage =rcu_dereference (selem->local_storage);if (sk_storage) { info->skip_elems = skip_elems + count;return selem;