This change prepares syncookie_{tc,xdp} for update in callbakcs
verification logic. To allow bpf_loop() verification converge when
multiple callback itreations are considered:
- track offset inside TCP payload explicitly, not as a part of the
pointer;
- make sure that offset does not exceed MAX_PACKET_OFF enforced by
verifier;
- make sure that offset is tracked as unbound scalar between
iterations, otherwise verifier won't be able infer that bpf_loop
callback reaches identical states.
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20231121020701.26440-2-eddyz87@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
#define DEFAULT_TTL 64
#define MAX_ALLOWED_PORTS 8
#define DEFAULT_TTL 64
#define MAX_ALLOWED_PORTS 8
+#define MAX_PACKET_OFF 0xffff
+
#define swap(a, b) \
do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0)
#define swap(a, b) \
do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0)
}
struct tcpopt_context {
}
struct tcpopt_context {
- __u8 *ptr;
- __u8 *end;
void *data_end;
__be32 *tsecr;
__u8 wscale;
bool option_timestamp;
bool option_sack;
void *data_end;
__be32 *tsecr;
__u8 wscale;
bool option_timestamp;
bool option_sack;
-static int tscookie_tcpopt_parse(struct tcpopt_context *ctx)
+static __always_inline u8 *next(struct tcpopt_context *ctx, __u32 sz)
+ __u64 off = ctx->off;
+ __u8 *data;
- if (ctx->ptr >= ctx->end)
- return 1;
- if (ctx->ptr >= ctx->data_end)
- return 1;
+ /* Verifier forbids access to packet when offset exceeds MAX_PACKET_OFF */
+ if (off > MAX_PACKET_OFF - sz)
+ return NULL;
+ data = ctx->data + off;
+ barrier_var(data);
+ if (data + sz >= ctx->data_end)
+ return NULL;
- if (opcode == TCPOPT_EOL)
- return 1;
- if (opcode == TCPOPT_NOP) {
- ++ctx->ptr;
- return 0;
- }
+ ctx->off += sz;
+ return data;
+}
- if (ctx->ptr + 1 >= ctx->end)
- return 1;
- if (ctx->ptr + 1 >= ctx->data_end)
+static int tscookie_tcpopt_parse(struct tcpopt_context *ctx)
+{
+ __u8 *opcode, *opsize, *wscale, *tsecr;
+ __u32 off = ctx->off;
+
+ opcode = next(ctx, 1);
+ if (!opcode)
- opsize = ctx->ptr[1];
- if (opsize < 2)
+
+ if (*opcode == TCPOPT_EOL)
+ if (*opcode == TCPOPT_NOP)
+ return 0;
- if (ctx->ptr + opsize > ctx->end)
+ opsize = next(ctx, 1);
+ if (!opsize || *opsize < 2)
- if (opsize == TCPOLEN_WINDOW && ctx->ptr + TCPOLEN_WINDOW <= ctx->data_end)
- ctx->wscale = ctx->ptr[2] < TCP_MAX_WSCALE ? ctx->ptr[2] : TCP_MAX_WSCALE;
+ wscale = next(ctx, 1);
+ if (!wscale)
+ return 1;
+ if (*opsize == TCPOLEN_WINDOW)
+ ctx->wscale = *wscale < TCP_MAX_WSCALE ? *wscale : TCP_MAX_WSCALE;
break;
case TCPOPT_TIMESTAMP:
break;
case TCPOPT_TIMESTAMP:
- if (opsize == TCPOLEN_TIMESTAMP && ctx->ptr + TCPOLEN_TIMESTAMP <= ctx->data_end) {
+ tsecr = next(ctx, 4);
+ if (!tsecr)
+ return 1;
+ if (*opsize == TCPOLEN_TIMESTAMP) {
ctx->option_timestamp = true;
/* Client's tsval becomes our tsecr. */
ctx->option_timestamp = true;
/* Client's tsval becomes our tsecr. */
- *ctx->tsecr = get_unaligned((__be32 *)(ctx->ptr + 2));
+ *ctx->tsecr = get_unaligned((__be32 *)tsecr);
}
break;
case TCPOPT_SACK_PERM:
}
break;
case TCPOPT_SACK_PERM:
- if (opsize == TCPOLEN_SACK_PERM)
+ if (*opsize == TCPOLEN_SACK_PERM)
ctx->option_sack = true;
break;
}
ctx->option_sack = true;
break;
}
+ ctx->off = off + *opsize;
static __always_inline bool tscookie_init(struct tcphdr *tcp_header,
__u16 tcp_len, __be32 *tsval,
static __always_inline bool tscookie_init(struct tcphdr *tcp_header,
__u16 tcp_len, __be32 *tsval,
- __be32 *tsecr, void *data_end)
+ __be32 *tsecr, void *data, void *data_end)
{
struct tcpopt_context loop_ctx = {
{
struct tcpopt_context loop_ctx = {
- .ptr = (__u8 *)(tcp_header + 1),
- .end = (__u8 *)tcp_header + tcp_len,
.data_end = data_end,
.tsecr = tsecr,
.wscale = TS_OPT_WSCALE_MASK,
.option_timestamp = false,
.option_sack = false,
.data_end = data_end,
.tsecr = tsecr,
.wscale = TS_OPT_WSCALE_MASK,
.option_timestamp = false,
.option_sack = false,
+ /* Note: currently verifier would track .off as unbound scalar.
+ * In case if verifier would at some point get smarter and
+ * compute bounded value for this var, beware that it might
+ * hinder bpf_loop() convergence validation.
+ */
+ .off = (__u8 *)(tcp_header + 1) - (__u8 *)data,
cookie = (__u32)value;
if (tscookie_init((void *)hdr->tcp, hdr->tcp_len,
cookie = (__u32)value;
if (tscookie_init((void *)hdr->tcp, hdr->tcp_len,
- &tsopt_buf[0], &tsopt_buf[1], data_end))
+ &tsopt_buf[0], &tsopt_buf[1], data, data_end))
tsopt = tsopt_buf;
/* Check that there is enough space for a SYNACK. It also covers
tsopt = tsopt_buf;
/* Check that there is enough space for a SYNACK. It also covers