@@ -390,20 +390,20 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk,
__ret; \
})
-#define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen) \
+#define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen, enabled) \
({ \
int __ret = 0; \
- if (cgroup_bpf_enabled(CGROUP_GETSOCKOPT)) \
+ enabled = cgroup_bpf_enabled(CGROUP_GETSOCKOPT); \
+ if (enabled) \
copy_from_sockptr(&__ret, optlen, sizeof(int)); \
__ret; \
})
#define BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock, level, optname, optval, optlen, \
- max_optlen, retval) \
+ max_optlen, retval, enabled) \
({ \
int __ret = retval; \
- if (cgroup_bpf_enabled(CGROUP_GETSOCKOPT) && \
- cgroup_bpf_sock_enabled(sock, CGROUP_GETSOCKOPT)) \
+ if (enabled && cgroup_bpf_sock_enabled(sock, CGROUP_GETSOCKOPT)) \
if (!(sock)->sk_prot->bpf_bypass_getsockopt || \
!INDIRECT_CALL_INET_1((sock)->sk_prot->bpf_bypass_getsockopt, \
tcp_bpf_bypass_getsockopt, \
@@ -518,9 +518,10 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map,
#define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; })
#define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(atype, major, minor, access) ({ 0; })
#define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,pos) ({ 0; })
-#define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen) ({ 0; })
+#define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen, enabled) ({ 0; })
#define BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock, level, optname, optval, \
- optlen, max_optlen, retval) ({ retval; })
+ optlen, max_optlen, retval, \
+ enabled) ({ retval; })
#define BPF_CGROUP_RUN_PROG_GETSOCKOPT_KERN(sock, level, optname, optval, \
optlen, retval) ({ retval; })
#define BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock, level, optname, optval, optlen, \
@@ -2363,6 +2363,7 @@ int do_sock_getsockopt(struct socket *sock, bool compat, int level,
int optname, sockptr_t optval, sockptr_t optlen)
{
int max_optlen __maybe_unused;
+ bool enabled __maybe_unused;
const struct proto_ops *ops;
int err;
@@ -2371,7 +2372,7 @@ int do_sock_getsockopt(struct socket *sock, bool compat, int level,
return err;
if (!compat)
- max_optlen = BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen);
+ max_optlen = BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen, enabled);
ops = READ_ONCE(sock->ops);
if (level == SOL_SOCKET) {
@@ -2390,7 +2391,7 @@ int do_sock_getsockopt(struct socket *sock, bool compat, int level,
if (!compat)
err = BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock->sk, level, optname,
optval, optlen, max_optlen,
- err);
+ err, enabled);
return err;
}
The return value from `cgroup_bpf_enabled(CGROUP_GETSOCKOPT)` can change between the invocations of `BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN` and `BPF_CGROUP_RUN_PROG_GETSOCKOPT`. If `cgroup_bpf_enabled(CGROUP_GETSOCKOPT)` changes from "false" to "true" between the invocations of `BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN` and `BPF_CGROUP_RUN_PROG_GETSOCKOPT`, `BPF_CGROUP_RUN_PROG_GETSOCKOPT` will receive an -EFAULT from `__cgroup_bpf_run_filter_getsockopt(max_optlen=0)` due to `get_user()` was not reached in `BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN`. Scenario shown as below: `process A` `process B` ----------- ------------ BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN enable CGROUP_GETSOCKOPT BPF_CGROUP_RUN_PROG_GETSOCKOPT (-EFAULT) To prevent this, invoke `cgroup_bpf_enabled()` only once and cache the result in a newly added local variable `enabled`. Both `BPF_CGROUP_*` macros in `do_sock_getsockopt` will then check their condition using the same `enabled` variable as the condition variable, instead of using the return values from `cgroup_bpf_enabled` called by themselves as the condition variable(which could yield different results). This ensures that either both `BPF_CGROUP_*` macros pass the condition or neither does. Co-developed-by: Yanghui Li <yanghui.li@mediatek.com> Signed-off-by: Yanghui Li <yanghui.li@mediatek.com> Co-developed-by: Cheng-Jui Wang <cheng-jui.wang@mediatek.com> Signed-off-by: Cheng-Jui Wang <cheng-jui.wang@mediatek.com> Signed-off-by: Tze-nan Wu <Tze-nan.Wu@mediatek.com> --- Chagnes from v1 to v2: https://lore.kernel.org/all/20240819082513.27176-1-Tze-nan.Wu@mediatek.com/ Instead of using cgroup_lock in the fastpath, invoke cgroup_bpf_enabled only once and cache the value in the newly added variable `enabled`. `BPF_CGROUP_*` macros in do_sock_getsockopt can then both check their condition with the new variable `enable`, ensuring that either they both passing the condition or both do not. Chagnes from v2 to v3: https://lore.kernel.org/all/20240819155627.1367-1-Tze-nan.Wu@mediatek.com/ Hide cgroup_bpf_enabled in the macro, and some modifications to adapt the coding style. --- include/linux/bpf-cgroup.h | 15 ++++++++------- net/socket.c | 5 +++-- 2 files changed, 11 insertions(+), 9 deletions(-)