From: Martin KaFai Lau <kafai@fb.com>
To: <bpf@vger.kernel.org>
Cc: Alexei Starovoitov <ast@kernel.org>,
Daniel Borkmann <daniel@iogearbox.net>, <kernel-team@fb.com>,
<netdev@vger.kernel.org>
Subject: [PATCH bpf-next] bpf: sk_storage: Prefer to get a free cache_idx
Date: Wed, 17 Jun 2020 10:42:26 -0700 [thread overview]
Message-ID: <20200617174226.2301909-1-kafai@fb.com> (raw)
The cache_idx is currently picked by RR. There is chance that
the same cache_idx will be picked by multiple sk_storage_maps while
other cache_idx is still unused. e.g. It could happen when the
sk_storage_map is recreated during the restart of the user
space process.
This patch tracks the usage count for each cache_idx. There is
16 of them now (defined in BPF_SK_STORAGE_CACHE_SIZE).
It will try to pick the free cache_idx. If none was found,
it would pick one with the minimal usage count.
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
---
net/core/bpf_sk_storage.c | 41 +++++++++++++++++++++++++++++++++++----
1 file changed, 37 insertions(+), 4 deletions(-)
diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index d2c4d16dadba..1dae4b543243 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -11,8 +11,6 @@
#include <uapi/linux/sock_diag.h>
#include <uapi/linux/btf.h>
-static atomic_t cache_idx;
-
#define SK_STORAGE_CREATE_FLAG_MASK \
(BPF_F_NO_PREALLOC | BPF_F_CLONE)
@@ -81,6 +79,9 @@ struct bpf_sk_storage_elem {
#define SDATA(_SELEM) (&(_SELEM)->sdata)
#define BPF_SK_STORAGE_CACHE_SIZE 16
+static DEFINE_SPINLOCK(cache_idx_lock);
+static u64 cache_idx_usage_counts[BPF_SK_STORAGE_CACHE_SIZE];
+
struct bpf_sk_storage {
struct bpf_sk_storage_data __rcu *cache[BPF_SK_STORAGE_CACHE_SIZE];
struct hlist_head list; /* List of bpf_sk_storage_elem */
@@ -512,6 +513,37 @@ static int sk_storage_delete(struct sock *sk, struct bpf_map *map)
return 0;
}
+static u16 cache_idx_get(void)
+{
+ u64 min_usage = U64_MAX;
+ u16 i, res = 0;
+
+ spin_lock(&cache_idx_lock);
+
+ for (i = 0; i < BPF_SK_STORAGE_CACHE_SIZE; i++) {
+ if (cache_idx_usage_counts[i] < min_usage) {
+ min_usage = cache_idx_usage_counts[i];
+ res = i;
+
+ /* Found a free cache_idx */
+ if (!min_usage)
+ break;
+ }
+ }
+ cache_idx_usage_counts[res]++;
+
+ spin_unlock(&cache_idx_lock);
+
+ return res;
+}
+
+static void cache_idx_free(u16 idx)
+{
+ spin_lock(&cache_idx_lock);
+ cache_idx_usage_counts[idx]--;
+ spin_unlock(&cache_idx_lock);
+}
+
/* Called by __sk_destruct() & bpf_sk_storage_clone() */
void bpf_sk_storage_free(struct sock *sk)
{
@@ -560,6 +592,8 @@ static void bpf_sk_storage_map_free(struct bpf_map *map)
smap = (struct bpf_sk_storage_map *)map;
+ cache_idx_free(smap->cache_idx);
+
/* Note that this map might be concurrently cloned from
* bpf_sk_storage_clone. Wait for any existing bpf_sk_storage_clone
* RCU read section to finish before proceeding. New RCU
@@ -673,8 +707,7 @@ static struct bpf_map *bpf_sk_storage_map_alloc(union bpf_attr *attr)
}
smap->elem_size = sizeof(struct bpf_sk_storage_elem) + attr->value_size;
- smap->cache_idx = (unsigned int)atomic_inc_return(&cache_idx) %
- BPF_SK_STORAGE_CACHE_SIZE;
+ smap->cache_idx = cache_idx_get();
return &smap->map;
}
--
2.24.1
next reply other threads:[~2020-06-17 17:42 UTC|newest]
Thread overview: 3+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-06-17 17:42 Martin KaFai Lau [this message]
2020-06-18 5:01 ` [PATCH bpf-next] bpf: sk_storage: Prefer to get a free cache_idx John Fastabend
2020-06-18 21:48 ` Alexei Starovoitov
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20200617174226.2301909-1-kafai@fb.com \
--to=kafai@fb.com \
--cc=ast@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=kernel-team@fb.com \
--cc=netdev@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).