bpf.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: John Fastabend <john.fastabend@gmail.com>
To: bpf@vger.kernel.org, netdev@vger.kernel.org
Cc: daniel@iogearbox.net, joamaki@gmail.com,
	xiyou.wangcong@gmail.com, jakub@cloudflare.com,
	john.fastabend@gmail.com
Subject: [PATCH bpf v2 4/5] bpf: sockmap, strparser, and tls are reusing qdisc_skb_cb and colliding
Date: Wed,  3 Nov 2021 13:47:35 -0700	[thread overview]
Message-ID: <20211103204736.248403-5-john.fastabend@gmail.com> (raw)
In-Reply-To: <20211103204736.248403-1-john.fastabend@gmail.com>

Strparser is reusing the qdisc_skb_cb struct to stash the skb message
handling progress, e.g. offset and length of the skb. First this is
poorly named and inherits a struct from qdisc that doesn't reflect the
actual usage of cb[] at this layer.

But, more importantly strparser is using the following to access its
metadata.

(struct _strp_msg *)((void *)skb->cb + offsetof(struct qdisc_skb_cb, data))

Where _strp_msg is defined as,

 struct _strp_msg {
        struct strp_msg            strp;                 /*     0     8 */
        int                        accum_len;            /*     8     4 */

        /* size: 12, cachelines: 1, members: 2 */
        /* last cacheline: 12 bytes */
 };

So we use 12 bytes of ->data[] in struct. However in BPF code running
parser and verdict the user has read capabilities into the data[]
array as well. Its not too problematic, but we should not be
exposing internal state to BPF program. If its really needed then we can
use the probe_read() APIs which allow reading kernel memory. And I don't
believe cb[] layer poses any API breakage by moving this around because
programs can't depend on cb[] across layers.

In order to fix another issue with a ctx rewrite we need to stash a temp
variable somewhere. To make this work cleanly this patch builds a cb
struct for sk_skb types called sk_skb_cb struct. Then we can use this
consistently in the strparser, sockmap space. Additionally we can
start allowing ->cb[] write access after this.

Fixes: 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface"
Tested-by: Jussi Maki <joamaki@gmail.com>
Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
---
 include/net/strparser.h   | 16 +++++++++++++++-
 net/core/filter.c         | 22 ++++++++++++++++++++++
 net/strparser/strparser.c | 10 +---------
 3 files changed, 38 insertions(+), 10 deletions(-)

diff --git a/include/net/strparser.h b/include/net/strparser.h
index 1d20b98493a1..bec1439bd3be 100644
--- a/include/net/strparser.h
+++ b/include/net/strparser.h
@@ -54,10 +54,24 @@ struct strp_msg {
 	int offset;
 };
 
+struct _strp_msg {
+	/* Internal cb structure. struct strp_msg must be first for passing
+	 * to upper layer.
+	 */
+	struct strp_msg strp;
+	int accum_len;
+};
+
+struct sk_skb_cb {
+#define SK_SKB_CB_PRIV_LEN 20
+	unsigned char data[SK_SKB_CB_PRIV_LEN];
+	struct _strp_msg strp;
+};
+
 static inline struct strp_msg *strp_msg(struct sk_buff *skb)
 {
 	return (struct strp_msg *)((void *)skb->cb +
-		offsetof(struct qdisc_skb_cb, data));
+		offsetof(struct sk_skb_cb, strp));
 }
 
 /* Structure for an attached lower socket */
diff --git a/net/core/filter.c b/net/core/filter.c
index a68418268e92..c3936d0724b8 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -9782,11 +9782,33 @@ static u32 sk_skb_convert_ctx_access(enum bpf_access_type type,
 				     struct bpf_prog *prog, u32 *target_size)
 {
 	struct bpf_insn *insn = insn_buf;
+	int off;
 
 	switch (si->off) {
 	case offsetof(struct __sk_buff, data_end):
 		insn = bpf_convert_data_end_access(si, insn);
 		break;
+	case offsetof(struct __sk_buff, cb[0]) ...
+	     offsetofend(struct __sk_buff, cb[4]) - 1:
+		BUILD_BUG_ON(sizeof_field(struct sk_skb_cb, data) < 20);
+		BUILD_BUG_ON((offsetof(struct sk_buff, cb) +
+			      offsetof(struct sk_skb_cb, data)) %
+			     sizeof(__u64));
+
+		prog->cb_access = 1;
+		off  = si->off;
+		off -= offsetof(struct __sk_buff, cb[0]);
+		off += offsetof(struct sk_buff, cb);
+		off += offsetof(struct sk_skb_cb, data);
+		if (type == BPF_WRITE)
+			*insn++ = BPF_STX_MEM(BPF_SIZE(si->code), si->dst_reg,
+					      si->src_reg, off);
+		else
+			*insn++ = BPF_LDX_MEM(BPF_SIZE(si->code), si->dst_reg,
+					      si->src_reg, off);
+		break;
+
+
 	default:
 		return bpf_convert_ctx_access(type, si, insn_buf, prog,
 					      target_size);
diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c
index 9c0343568d2a..1a72c67afed5 100644
--- a/net/strparser/strparser.c
+++ b/net/strparser/strparser.c
@@ -27,18 +27,10 @@
 
 static struct workqueue_struct *strp_wq;
 
-struct _strp_msg {
-	/* Internal cb structure. struct strp_msg must be first for passing
-	 * to upper layer.
-	 */
-	struct strp_msg strp;
-	int accum_len;
-};
-
 static inline struct _strp_msg *_strp_msg(struct sk_buff *skb)
 {
 	return (struct _strp_msg *)((void *)skb->cb +
-		offsetof(struct qdisc_skb_cb, data));
+		offsetof(struct sk_skb_cb, strp));
 }
 
 /* Lower lock held */
-- 
2.33.0


  parent reply	other threads:[~2021-11-03 20:48 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-11-03 20:47 [PATCH bpf v2 0/5] bpf, sockmap: fixes stress testing and regression John Fastabend
2021-11-03 20:47 ` [PATCH bpf v2 1/5] bpf, sockmap: Use stricter sk state checks in sk_lookup_assign John Fastabend
2021-11-08 10:10   ` Jakub Sitnicki
2021-11-03 20:47 ` [PATCH bpf v2 2/5] bpf, sockmap: Remove unhash handler for BPF sockmap usage John Fastabend
2021-11-03 20:47 ` [PATCH bpf v2 3/5] bpf, sockmap: Fix race in ingress receive verdict with redirect to self John Fastabend
2021-11-03 20:47 ` John Fastabend [this message]
2021-11-03 20:47 ` [PATCH bpf v2 5/5] bpf, sockmap: sk_skb data_end access incorrect when src_reg = dst_reg John Fastabend
2021-11-08 10:16 ` [PATCH bpf v2 0/5] bpf, sockmap: fixes stress testing and regression Jakub Sitnicki
2021-11-09  0:10 ` patchwork-bot+netdevbpf

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=20211103204736.248403-5-john.fastabend@gmail.com \
    --to=john.fastabend@gmail.com \
    --cc=bpf@vger.kernel.org \
    --cc=daniel@iogearbox.net \
    --cc=jakub@cloudflare.com \
    --cc=joamaki@gmail.com \
    --cc=netdev@vger.kernel.org \
    --cc=xiyou.wangcong@gmail.com \
    /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).