From: Kuniyuki Iwashima <kuniyu@xxxxxxxxxx>
Date: Thu, 21 Dec 2023 16:04:43 +0900
> From: Martin KaFai Lau <martin.lau@xxxxxxxxx>
> Date: Wed, 20 Dec 2023 22:35:26 -0800
> > On 12/20/23 5:28 PM, Kuniyuki Iwashima wrote:
> > > +static int tcp_validate_header(struct tcp_syncookie *ctx)
> > > +{
> > > + s64 csum;
> > > +
> > > + if (tcp_reload_headers(ctx))
> > > + goto err;
> > > +
> > > + csum = bpf_csum_diff(0, 0, (void *)ctx->tcp, ctx->tcp->doff * 4, 0);
> > > + if (csum < 0)
> > > + goto err;
> > > +
> > > + if (ctx->ipv4) {
> > > + /* check tcp_v4_csum(csum) is 0 if not on lo. */
> > > +
> > > + csum = bpf_csum_diff(0, 0, (void *)ctx->ipv4, ctx->ipv4->ihl * 4, 0);
> > > + if (csum < 0)
> > > + goto err;
> > > +
> > > + if (csum_fold(csum) != 0)
> > > + goto err;
> > > + } else if (ctx->ipv6) {
> > > + /* check tcp_v6_csum(csum) is 0 if not on lo. */
> > > + }
> > > +
> > > + return 0;
> > > +err:
> > > + return -1;
> > > +}
> > > +
> > > +static int tcp_parse_option(__u32 index, struct tcp_syncookie *ctx)
> > > +{
> > > + char opcode, opsize;
> > > +
> > > + if (ctx->ptr + 1 > ctx->data_end)
> > > + goto stop;
> > > +
> > > + opcode = *ctx->ptr++;
> > > +
> > > + if (opcode == TCPOPT_EOL)
> > > + goto stop;
> > > +
> > > + if (opcode == TCPOPT_NOP)
> > > + goto next;
> > > +
> > > + if (ctx->ptr + 1 > ctx->data_end)
> > > + goto stop;
> > > +
> > > + opsize = *ctx->ptr++;
> > > +
> > > + if (opsize < 2)
> > > + goto stop;
> > > +
> > > + switch (opcode) {
> > > + case TCPOPT_MSS:
> > > + if (opsize == TCPOLEN_MSS && ctx->tcp->syn &&
> > > + ctx->ptr + (TCPOLEN_MSS - 2) < ctx->data_end)
> > > + ctx->attrs.mss = get_unaligned_be16(ctx->ptr);
> > > + break;
> > > + case TCPOPT_WINDOW:
> > > + if (opsize == TCPOLEN_WINDOW && ctx->tcp->syn &&
> > > + ctx->ptr + (TCPOLEN_WINDOW - 2) < ctx->data_end) {
> > > + ctx->attrs.wscale_ok = 1;
> > > + ctx->attrs.snd_wscale = *ctx->ptr;
> > > + }
> > > + break;
> > > + case TCPOPT_TIMESTAMP:
> > > + if (opsize == TCPOLEN_TIMESTAMP &&
> > > + ctx->ptr + (TCPOLEN_TIMESTAMP - 2) < ctx->data_end) {
> > > + ctx->attrs.rcv_tsval = get_unaligned_be32(ctx->ptr);
> > > + ctx->attrs.rcv_tsecr = get_unaligned_be32(ctx->ptr + 4);
> > > +
> > > + if (ctx->tcp->syn && ctx->attrs.rcv_tsecr)
> > > + ctx->attrs.tstamp_ok = 0;
> > > + else
> > > + ctx->attrs.tstamp_ok = 1;
> > > + }
> > > + break;
> > > + case TCPOPT_SACK_PERM:
> > > + if (opsize == TCPOLEN_SACK_PERM && ctx->tcp->syn &&
> > > + ctx->ptr + (TCPOLEN_SACK_PERM - 2) < ctx->data_end)
> > > + ctx->attrs.sack_ok = 1;
> > > + break;
> > > + }
> > > +
> > > + ctx->ptr += opsize - 2;
> > > +next:
> > > + return 0;
> > > +stop:
> > > + return 1;
> > > +}
> > > +
> > > +static void tcp_parse_options(struct tcp_syncookie *ctx)
> > > +{
> > > + ctx->ptr = (char *)(ctx->tcp + 1);
> > > +
> > > + bpf_loop(40, tcp_parse_option, ctx, 0);
> > > +}
> > > +
> > > +static int tcp_validate_sysctl(struct tcp_syncookie *ctx)
> > > +{
> > > + if ((ctx->ipv4 && ctx->attrs.mss != MSS_LOCAL_IPV4) ||
> > > + (ctx->ipv6 && ctx->attrs.mss != MSS_LOCAL_IPV6))
> > > + goto err;
> > > +
> > > + if (!ctx->attrs.wscale_ok || ctx->attrs.snd_wscale != 7)
> > > + goto err;
> > > +
> > > + if (!ctx->attrs.tstamp_ok)
> >
> > The bpf-ci reported error in cpuv4. The email from bot+bpf-ci@xxxxxxxxxx has the
> > link.
>
> I like the mail from the bot, it's useful, but it seems that
> it's sent to the patch author only when the CI passes ?
>
> But yeah, I found the failed test.
> https://github.com/kernel-patches/bpf/actions/runs/7284164398/job/19849657597
>
>
> >
> > I tried the following:
> >
> > if (!ctx->attrs.tstamp_ok) {
> > bpf_printk("ctx->attrs.tstamp_ok %u",
> > ctx->attrs.tstamp_ok);
> > goto err;
> > }
> >
> >
> > The above prints tstamp_ok as 1 while there is a "if (!ctx->attrs.tstamp_ok)"
> > test before it.
> >
> > Yonghong and I debugged it quite a bit. verifier concluded the
> > ctx->attrs.tstamp_ok is 0. We knew some red herring like cpuv4 has fewer
> > register spilling but not able to root cause it yet.
> >
> > In the mean time, there are existing selftests parsing the tcp header. For
> > example, the test_parse_tcp_hdr_opt[_dynptr].c. Not as complete as your
> > tcp_parse_option() but should be pretty close. It does not use bpf_loop. It uses
> > a bounded loop + a subprog (the parse_hdr_opt in the selftests) instead. You can
> > consider a similar construct to see if it works around the cpuv4 CI issue for
> > the time being.
>
> Sure, I'll install the latest clang/llvm and check if the test
> passes without bpf_loop().
I've tested a simple diff below and some more different patterns, but
the prog cannot be loaded. Without bpf_loop(), the parser can loop
only 4 times (s/40/4/), but then, it does not fully parse the necessary
options, so the packet is dropped due to tcp_validate_sysctl(), and the
test fails.
So it seems that tcp_parse_option() cannot work around the issue even
without bpf_loop() and this series needs to wait the cpuv4 fix..
---8<---
@@ -259,9 +260,13 @@ static int tcp_parse_option(__u32 index, struct tcp_syncookie *ctx)
static void tcp_parse_options(struct tcp_syncookie *ctx)
{
+ int i;
+
ctx->ptr = (char *)(ctx->tcp + 1);
- bpf_loop(40, tcp_parse_option, ctx, 0);
+ for (i = 0; i < 40; i++)
+ if (tcp_parse_option(i, ctx))
+ break;
}
static int tcp_validate_sysctl(struct tcp_syncookie *ctx)
---8<---
---8<---
BPF program is too large. Processed 1000001 insn
processed 1000001 insns (limit 1000000) max_states_per_insn 30 total_states 41159 peak_states 344 mark_read 55
-- END PROG LOAD LOG --
libbpf: prog 'tcp_custom_syncookie': failed to load: -7
---8<---
