bpf: don't return EINVAL from {get,set}sockopt when optlen > PAGE_SIZE
Subsystems (6)
PATCH v4 1/2 bpf: don't return EINVAL from {get,set}sockopt when optlen > PAGE_SIZE
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)
--- include/linux/filter.h | 1 + kernel/bpf/cgroup.c | 31 +++++++++++++++++++++++++------ 2 files changed, 26 insertions(+), 6 deletions(-)
include/linux/filter.h +1 -0
@@ -1276,6 +1276,7 @@ struct bpf_sockopt_kern {s32 optname;s32 optlen;s32 retval; + u8 optval_too_large; };#endif /* __LINUX_FILTER_H__ */
kernel/bpf/cgroup.c +25 -6
@@ -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;
Signature · 1 line
2.27.0.290.gba653c62da-goog
PATCH v4 2/2 selftests/bpf: make sure optvals > PAGE_SIZE are bypassed
We are relying on the fact, that we can pass > sizeof(int) optvals to the SOL_IP+IP_FREEBIND option (the kernel will take first 4 bytes). In the BPF program, we return EPERM if optval is greater than optval_end (implemented via PTR_TO_PACKET/PTR_TO_PACKET_END) and rely on the verifier to enforce the fact that this data can not be touched.
--- .../selftests/bpf/prog_tests/sockopt_sk.c | 26 +++++++++++++++++++ .../testing/selftests/bpf/progs/sockopt_sk.c | 20 ++++++++++++++ 2 files changed, 46 insertions(+)
tools/testing/selftests/bpf/prog_tests/sockopt_sk.c +26 -0
@@ -13,6 +13,7 @@ static int getsetsockopt(void)char cc[16 ];/* TCP_CA_NAME_MAX */ } buf = {};socklen_t optlen; +char *big_buf; fd =socket (AF_INET ,SOCK_STREAM ,0 );if (fd <0 ) {
@@ -78,6 +79,31 @@ static int getsetsockopt(void) goto err; } +/* IP_FREEBIND - BPF can't access optval when optlen > PAGE_SIZE */ + + optlen =getpagesize () *2 ; + big_buf =calloc (1 , optlen); +if (!big_buf) { +log_err ("Couldn't allocate two pages" ); + goto err; + } + + err =setsockopt (fd,SOL_IP ,IP_FREEBIND , big_buf, optlen); +if (err !=0 ) { +log_err ("Failed to call setsockopt, ret=%d" , err); +free (big_buf); + goto err; + } + + err =getsockopt (fd,SOL_IP ,IP_FREEBIND , big_buf, &optlen); +if (err !=0 ) { +log_err ("Failed to call getsockopt, ret=%d" , err); +free (big_buf); + goto err; + } + +free (big_buf); +/* SO_SNDBUF is overwritten */ buf.u32 =0x01010101 ;
tools/testing/selftests/bpf/progs/sockopt_sk.c +20 -0
@@ -51,6 +51,16 @@ int _getsockopt(struct bpf_sockopt *ctx)return 1 ; } +if (ctx->level ==SOL_IP && ctx->optname ==IP_FREEBIND ) { +if (optval > optval_end) { +/* For optval > PAGE_SIZE, the actual data +* is not provided. +*/ +return 0 ;/* EPERM, unexpected data size */ + } +return 1 ; + } +if (ctx->level !=SOL_CUSTOM )return 0 ;/* EPERM, deny everything except custom level */
@@ -112,6 +122,16 @@ int _setsockopt(struct bpf_sockopt *ctx)return 1 ; } +if (ctx->level ==SOL_IP && ctx->optname ==IP_FREEBIND ) { +if (optval > optval_end) { +/* For optval > PAGE_SIZE, the actual data +* is not provided. +*/ +return 0 ;/* EPERM, unexpected data size */ + } +return 1 ; + } +if (ctx->level !=SOL_CUSTOM )return 0 ;/* EPERM, deny everything except custom level */
Signature · 1 line
2.27.0.290.gba653c62da-goog
Quoted 24 lines · Stanislav Fomichev
Attaching to these hooks can break iptables because its optval is usually quite big, or at least bigger than the current
PAGE_SIZElimit. 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
thePAGE_SIZElimit.To support the cases where len(optval) >
PAGE_SIZEwe can leverage upcoming sleepable BPF work by providing a helper which can docopy_from_user(sleepable) at the given offset from the original large buffer.
Quoted 4 lines
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.
just replied with another idea in v3 thread...
Re: [PATCH bpf v4 2/2] selftests/bpf: make sure optvals > PAGE_SIZE are bypassed
In reply to Stanislav FomichevReview
Quoted 2 lines · Stanislav Fomichev
(quoted diff) +2
-0+ if (ctx->level == SOL_IP && ctx->optname == IP_FREEBIND) { + if (optval > optval_end) {
same issue as before ?
see reply in v3.
Quoted 8 lines
tools/testing/selftests/bpf/progs/sockopt_sk.c +8
-0+/* For optval > PAGE_SIZE, the actual data +* is not provided. +*/ +return 0 ;/* EPERM, unexpected data size */ + } +return 1 ; + } +
Quoted 26 lines · Alexei Starovoitov
Quoted 24 lines · Stanislav Fomichev
Attaching to these hooks can break iptables because its optval is usually quite big, or at least bigger than the current
PAGE_SIZElimit. 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
thePAGE_SIZElimit.To support the cases where len(optval) >
PAGE_SIZEwe can leverage upcoming sleepable BPF work by providing a helper which can docopy_from_user(sleepable) at the given offset from the original large buffer.
Quoted 6 lines
Quoted 4 lines
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.just replied with another idea in v3 thread...
Yeah, sorry about that, posted 5 mins before your reply :-( Sorry for the noise.