leandrof/linux
1
0
Fork 0
forked from Minki/linux
Code Issues Pull Requests Packages Projects Releases Wiki Activity

bpf: Optimize call_rcu in non-preallocated hash map.

Browse Source 
Doing call_rcu() million times a second becomes a bottle neck.
Convert non-preallocated hash map from call_rcu to SLAB_TYPESAFE_BY_RCU.
The rcu critical section is no longer observed for one htab element
which makes non-preallocated hash map behave just like preallocated hash map.
The map elements are released back to kernel memory after observing
rcu critical section.
This improves 'map_perf_test 4' performance from 100k events per second
to 250k events per second.

bpf_mem_alloc + percpu_counter + typesafe_by_rcu provide 10x performance
boost to non-preallocated hash map and make it within few % of preallocated map
while consuming fraction of memory.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20220902211058.60789-8-alexei.starovoitov@gmail.com
This commit is contained in:
Alexei Starovoitov 2022-09-02 14:10:49 -07:00 committed by Daniel Borkmann
parent 86fe28f769
commit 0fd7c5d433
3 changed files with 7 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
kernel/bpf/hashtab.c
View File

@ -953,8 +953,12 @@ static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
__pcpu_freelist_push(&htab->freelist, &l->fnode); __pcpu_freelist_push(&htab->freelist, &l->fnode);
} else { } else {
dec_elem_count(htab); dec_elem_count(htab);
l->htab = htab; if (htab->map.map_type == BPF_MAP_TYPE_PERCPU_HASH) {
call_rcu(&l->rcu, htab_elem_free_rcu); l->htab = htab;
call_rcu(&l->rcu, htab_elem_free_rcu);
} else {
htab_elem_free(htab, l);
}
} }
} }

2
kernel/bpf/memalloc.c
View File

@ -281,7 +281,7 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size)
return -ENOMEM; return -ENOMEM;
size += LLIST_NODE_SZ; /* room for llist_node */ size += LLIST_NODE_SZ; /* room for llist_node */
snprintf(buf, sizeof(buf), "bpf-%u", size); snprintf(buf, sizeof(buf), "bpf-%u", size);
kmem_cache = kmem_cache_create(buf, size, 8, 0, NULL); kmem_cache = kmem_cache_create(buf, size, 8, SLAB_TYPESAFE_BY_RCU, NULL);
if (!kmem_cache) { if (!kmem_cache) {
free_percpu(pc); free_percpu(pc);
return -ENOMEM; return -ENOMEM;

11
tools/testing/selftests/bpf/progs/timer.c
View File

@ -208,17 +208,6 @@ static int timer_cb2(void *map, int *key, struct hmap_elem *val)
*/ */
bpf_map_delete_elem(map, key); bpf_map_delete_elem(map, key);
/* in non-preallocated hashmap both 'key' and 'val' are RCU
* protected and still valid though this element was deleted
* from the map. Arm this timer for ~35 seconds. When callback
* finishes the call_rcu will invoke:
* htab_elem_free_rcu
* check_and_free_timer
* bpf_timer_cancel_and_free
* to cancel this 35 second sleep and delete the timer for real.
*/
if (bpf_timer_start(&val->timer, 1ull << 35, 0) != 0)
err |= 256;
ok |= 4; ok |= 4;
} }
return 0; return 0;