[PATCH bpf v4 1/2] bpf: don't return EINVAL from {get,set}sockopt when optlen > PAGE_SIZE

[Stanislav Fomichev <sdf@xxxxxxxxxx>]

Attaching to these hooks can break iptables because its optval is
usually quite big, or at least bigger than the current PAGE_SIZE limit.
David also mentioned some SCTP options can be big (around 256k).

There are two possible ways to fix it:
1. Increase the limit to match iptables max optval. There is, however,
   no clear upper limit. Technically, iptables can accept up to
   512M of data (not sure how practical it is though).

2. Bypass the value (don't expose to BPF) if it's too big and trigger
   BPF only with level/optname so BPF can still decide whether
   to allow/deny big sockopts.

The initial attempt was implemented using strategy #1. Due to
listed shortcomings, let's switch to strategy #2. When there is
legitimate a real use-case for iptables/SCTP, we can consider increasing
 the PAGE_SIZE limit.

To support the cases where len(optval) > PAGE_SIZE we can
leverage upcoming sleepable BPF work by providing a helper
which can do copy_from_user (sleepable) at the given offset
from the original large buffer.

v4:
* use temporary buffer to avoid optval == optval_end == NULL;
  this removes the corner case in the verifier that might assume
  non-zero PTR_TO_PACKET/PTR_TO_PACKET_END.

v3:
* don't increase the limit, bypass the argument

v2:
* proper comments formatting (Jakub Kicinski)

Fixes: 0d01da6afc54 ("bpf: implement getsockopt and setsockopt hooks")
Cc: David Laight <David.Laight@xxxxxxxxxx>
Signed-off-by: Stanislav Fomichev <sdf@xxxxxxxxxx>
---
 include/linux/filter.h |  1 +
 kernel/bpf/cgroup.c    | 31 +++++++++++++++++++++++++------
 2 files changed, 26 insertions(+), 6 deletions(-)

diff --git a/include/linux/filter.h b/include/linux/filter.h
index 259377723603..f4565a70f8ba 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1276,6 +1276,7 @@ struct bpf_sockopt_kern {
 	s32		optname;
 	s32		optlen;
 	s32		retval;
+	u8		optval_too_large;
 };
 
 #endif /* __LINUX_FILTER_H__ */
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 4d76f16524cc..be78c01bf459 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -1276,9 +1276,18 @@ static bool __cgroup_bpf_prog_array_is_empty(struct cgroup *cgrp,
 
 static int sockopt_alloc_buf(struct bpf_sockopt_kern *ctx, int max_optlen)
 {
-	if (unlikely(max_optlen > PAGE_SIZE) || max_optlen < 0)
+	if (unlikely(max_optlen < 0))
 		return -EINVAL;
 
+	if (unlikely(max_optlen > PAGE_SIZE)) {
+		/* We don't expose optvals that are greater than PAGE_SIZE
+		 * to the BPF program.
+		 */
+		ctx->optval = &ctx->optval_too_large;
+		ctx->optval_end = &ctx->optval_too_large;
+		return 0;
+	}
+
 	ctx->optval = kzalloc(max_optlen, GFP_USER);
 	if (!ctx->optval)
 		return -ENOMEM;
@@ -1288,9 +1297,15 @@ static int sockopt_alloc_buf(struct bpf_sockopt_kern *ctx, int max_optlen)
 	return 0;
 }
 
+static int sockopt_has_optval(struct bpf_sockopt_kern *ctx)
+{
+	return ctx->optval != &ctx->optval_too_large;
+}
+
 static void sockopt_free_buf(struct bpf_sockopt_kern *ctx)
 {
-	kfree(ctx->optval);
+	if (sockopt_has_optval(ctx))
+		kfree(ctx->optval);
 }
 
 int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level,
@@ -1325,7 +1340,8 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level,
 
 	ctx.optlen = *optlen;
 
-	if (copy_from_user(ctx.optval, optval, *optlen) != 0) {
+	if (sockopt_has_optval(&ctx) &&
+	    copy_from_user(ctx.optval, optval, *optlen) != 0) {
 		ret = -EFAULT;
 		goto out;
 	}
@@ -1354,7 +1370,8 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level,
 		*level = ctx.level;
 		*optname = ctx.optname;
 		*optlen = ctx.optlen;
-		*kernel_optval = ctx.optval;
+		if (sockopt_has_optval(&ctx))
+			*kernel_optval = ctx.optval;
 	}
 
 out:
@@ -1407,7 +1424,8 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
 		if (ctx.optlen > max_optlen)
 			ctx.optlen = max_optlen;
 
-		if (copy_from_user(ctx.optval, optval, ctx.optlen) != 0) {
+		if (sockopt_has_optval(&ctx) &&
+		    copy_from_user(ctx.optval, optval, ctx.optlen) != 0) {
 			ret = -EFAULT;
 			goto out;
 		}
@@ -1436,7 +1454,8 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
 		goto out;
 	}
 
-	if (copy_to_user(optval, ctx.optval, ctx.optlen) ||
+	if ((sockopt_has_optval(&ctx) &&
+	     copy_to_user(optval, ctx.optval, ctx.optlen)) ||
 	    put_user(ctx.optlen, optlen)) {
 		ret = -EFAULT;
 		goto out;
-- 
2.27.0.290.gba653c62da-goog