From 9cacf81f8161111db25f98e78a7a0e32ae142b3f Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Fri, 15 Jan 2021 08:34:59 -0800 Subject: bpf: Remove extra lock_sock for TCP_ZEROCOPY_RECEIVE Add custom implementation of getsockopt hook for TCP_ZEROCOPY_RECEIVE. We skip generic hooks for TCP_ZEROCOPY_RECEIVE and have a custom call in do_tcp_getsockopt using the on-stack data. This removes 3% overhead for locking/unlocking the socket. Without this patch: 3.38% 0.07% tcp_mmap [kernel.kallsyms] [k] __cgroup_bpf_run_filter_getsockopt | --3.30%--__cgroup_bpf_run_filter_getsockopt | --0.81%--__kmalloc With the patch applied: 0.52% 0.12% tcp_mmap [kernel.kallsyms] [k] __cgroup_bpf_run_filter_getsockopt_kern Note, exporting uapi/tcp.h requires removing netinet/tcp.h from test_progs.h because those headers have confliciting definitions. Signed-off-by: Stanislav Fomichev Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20210115163501.805133-2-sdf@google.com --- include/linux/bpf-cgroup.h | 27 +++++++++++++++++++++++---- include/linux/indirect_call_wrapper.h | 6 ++++++ 2 files changed, 29 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 72e69a0e1e8c..bcb2915e6124 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -147,6 +147,10 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, int __user *optlen, int max_optlen, int retval); +int __cgroup_bpf_run_filter_getsockopt_kern(struct sock *sk, int level, + int optname, void *optval, + int *optlen, int retval); + static inline enum bpf_cgroup_storage_type cgroup_storage_type( struct bpf_map *map) { @@ -364,10 +368,23 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, ({ \ int __ret = retval; \ if (cgroup_bpf_enabled) \ - __ret = __cgroup_bpf_run_filter_getsockopt(sock, level, \ - optname, optval, \ - optlen, max_optlen, \ - retval); \ + if (!(sock)->sk_prot->bpf_bypass_getsockopt || \ + !INDIRECT_CALL_INET_1((sock)->sk_prot->bpf_bypass_getsockopt, \ + tcp_bpf_bypass_getsockopt, \ + level, optname)) \ + __ret = __cgroup_bpf_run_filter_getsockopt( \ + sock, level, optname, optval, optlen, \ + max_optlen, retval); \ + __ret; \ +}) + +#define BPF_CGROUP_RUN_PROG_GETSOCKOPT_KERN(sock, level, optname, optval, \ + optlen, retval) \ +({ \ + int __ret = retval; \ + if (cgroup_bpf_enabled) \ + __ret = __cgroup_bpf_run_filter_getsockopt_kern( \ + sock, level, optname, optval, optlen, retval); \ __ret; \ }) @@ -452,6 +469,8 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, #define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock, level, optname, optval, \ optlen, max_optlen, retval) ({ 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, \ kernel_optval) ({ 0; }) diff --git a/include/linux/indirect_call_wrapper.h b/include/linux/indirect_call_wrapper.h index 54c02c84906a..cfcfef37b2f1 100644 --- a/include/linux/indirect_call_wrapper.h +++ b/include/linux/indirect_call_wrapper.h @@ -60,4 +60,10 @@ #define INDIRECT_CALL_INET(f, f2, f1, ...) f(__VA_ARGS__) #endif +#if IS_ENABLED(CONFIG_INET) +#define INDIRECT_CALL_INET_1(f, f1, ...) INDIRECT_CALL_1(f, f1, __VA_ARGS__) +#else +#define INDIRECT_CALL_INET_1(f, f1, ...) f(__VA_ARGS__) +#endif + #endif -- cgit v1.2.3 From 20f2505fb436cfa674cf1f46aaa624f44d3d1d03 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Fri, 15 Jan 2021 08:35:00 -0800 Subject: bpf: Try to avoid kzalloc in cgroup/{s,g}etsockopt When we attach a bpf program to cgroup/getsockopt any other getsockopt() syscall starts incurring kzalloc/kfree cost. Let add a small buffer on the stack and use it for small (majority) {s,g}etsockopt values. The buffer is small enough to fit into the cache line and cover the majority of simple options (most of them are 4 byte ints). It seems natural to do the same for setsockopt, but it's a bit more involved when the BPF program modifies the data (where we have to kmalloc). The assumption is that for the majority of setsockopt calls (which are doing pure BPF options or apply policy) this will bring some benefit as well. Without this patch (we remove about 1% __kmalloc): 3.38% 0.07% tcp_mmap [kernel.kallsyms] [k] __cgroup_bpf_run_filter_getsockopt | --3.30%--__cgroup_bpf_run_filter_getsockopt | --0.81%--__kmalloc Signed-off-by: Stanislav Fomichev Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20210115163501.805133-3-sdf@google.com --- include/linux/filter.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 7fdce5407214..5b3137d7b690 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1298,6 +1298,11 @@ struct bpf_sysctl_kern { u64 tmp_reg; }; +#define BPF_SOCKOPT_KERN_BUF_SIZE 32 +struct bpf_sockopt_buf { + u8 data[BPF_SOCKOPT_KERN_BUF_SIZE]; +}; + struct bpf_sockopt_kern { struct sock *sk; u8 *optval; -- cgit v1.2.3 From a9ed15dae0755a0368735e0556a462d8519bdb05 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Fri, 15 Jan 2021 08:35:01 -0800 Subject: bpf: Split cgroup_bpf_enabled per attach type When we attach any cgroup hook, the rest (even if unused/unattached) start to contribute small overhead. In particular, the one we want to avoid is __cgroup_bpf_run_filter_skb which does two redirections to get to the cgroup and pushes/pulls skb. Let's split cgroup_bpf_enabled to be per-attach to make sure only used attach types trigger. I've dropped some existing high-level cgroup_bpf_enabled in some places because BPF_PROG_CGROUP_XXX_RUN macros usually have another cgroup_bpf_enabled check. I also had to copy-paste BPF_CGROUP_RUN_SA_PROG_LOCK for GETPEERNAME/GETSOCKNAME because type for cgroup_bpf_enabled[type] has to be constant and known at compile time. Signed-off-by: Stanislav Fomichev Signed-off-by: Alexei Starovoitov Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20210115163501.805133-4-sdf@google.com --- include/linux/bpf-cgroup.h | 38 ++++++++++++++++++++------------------ 1 file changed, 20 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index bcb2915e6124..0748fd87969e 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -23,8 +23,8 @@ struct ctl_table_header; #ifdef CONFIG_CGROUP_BPF -extern struct static_key_false cgroup_bpf_enabled_key; -#define cgroup_bpf_enabled static_branch_unlikely(&cgroup_bpf_enabled_key) +extern struct static_key_false cgroup_bpf_enabled_key[MAX_BPF_ATTACH_TYPE]; +#define cgroup_bpf_enabled(type) static_branch_unlikely(&cgroup_bpf_enabled_key[type]) DECLARE_PER_CPU(struct bpf_cgroup_storage*, bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]); @@ -189,7 +189,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled) \ + if (cgroup_bpf_enabled(BPF_CGROUP_INET_INGRESS)) \ __ret = __cgroup_bpf_run_filter_skb(sk, skb, \ BPF_CGROUP_INET_INGRESS); \ \ @@ -199,7 +199,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled && sk && sk == skb->sk) { \ + if (cgroup_bpf_enabled(BPF_CGROUP_INET_EGRESS) && sk && sk == skb->sk) { \ typeof(sk) __sk = sk_to_full_sk(sk); \ if (sk_fullsock(__sk)) \ __ret = __cgroup_bpf_run_filter_skb(__sk, skb, \ @@ -211,7 +211,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_SK_PROG(sk, type) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled) { \ + if (cgroup_bpf_enabled(type)) { \ __ret = __cgroup_bpf_run_filter_sk(sk, type); \ } \ __ret; \ @@ -232,7 +232,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, type) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled) \ + if (cgroup_bpf_enabled(type)) \ __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type, \ NULL); \ __ret; \ @@ -241,7 +241,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, type, t_ctx) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled) { \ + if (cgroup_bpf_enabled(type)) { \ lock_sock(sk); \ __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type, \ t_ctx); \ @@ -256,8 +256,10 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_PROG_INET6_BIND_LOCK(sk, uaddr) \ BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET6_BIND, NULL) -#define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (cgroup_bpf_enabled && \ - sk->sk_prot->pre_connect) +#define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) \ + ((cgroup_bpf_enabled(BPF_CGROUP_INET4_CONNECT) || \ + cgroup_bpf_enabled(BPF_CGROUP_INET6_CONNECT)) && \ + (sk)->sk_prot->pre_connect) #define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr) \ BPF_CGROUP_RUN_SA_PROG(sk, uaddr, BPF_CGROUP_INET4_CONNECT) @@ -301,7 +303,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_PROG_SOCK_OPS_SK(sock_ops, sk) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled) \ + if (cgroup_bpf_enabled(BPF_CGROUP_SOCK_OPS)) \ __ret = __cgroup_bpf_run_filter_sock_ops(sk, \ sock_ops, \ BPF_CGROUP_SOCK_OPS); \ @@ -311,7 +313,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled && (sock_ops)->sk) { \ + if (cgroup_bpf_enabled(BPF_CGROUP_SOCK_OPS) && (sock_ops)->sk) { \ typeof(sk) __sk = sk_to_full_sk((sock_ops)->sk); \ if (__sk && sk_fullsock(__sk)) \ __ret = __cgroup_bpf_run_filter_sock_ops(__sk, \ @@ -324,7 +326,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type, major, minor, access) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled) \ + if (cgroup_bpf_enabled(BPF_CGROUP_DEVICE)) \ __ret = __cgroup_bpf_check_dev_permission(type, major, minor, \ access, \ BPF_CGROUP_DEVICE); \ @@ -336,7 +338,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write, buf, count, pos) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled) \ + if (cgroup_bpf_enabled(BPF_CGROUP_SYSCTL)) \ __ret = __cgroup_bpf_run_filter_sysctl(head, table, write, \ buf, count, pos, \ BPF_CGROUP_SYSCTL); \ @@ -347,7 +349,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, kernel_optval) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled) \ + if (cgroup_bpf_enabled(BPF_CGROUP_SETSOCKOPT)) \ __ret = __cgroup_bpf_run_filter_setsockopt(sock, level, \ optname, optval, \ optlen, \ @@ -358,7 +360,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled) \ + if (cgroup_bpf_enabled(BPF_CGROUP_GETSOCKOPT)) \ get_user(__ret, optlen); \ __ret; \ }) @@ -367,7 +369,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, max_optlen, retval) \ ({ \ int __ret = retval; \ - if (cgroup_bpf_enabled) \ + if (cgroup_bpf_enabled(BPF_CGROUP_GETSOCKOPT)) \ if (!(sock)->sk_prot->bpf_bypass_getsockopt || \ !INDIRECT_CALL_INET_1((sock)->sk_prot->bpf_bypass_getsockopt, \ tcp_bpf_bypass_getsockopt, \ @@ -382,7 +384,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, optlen, retval) \ ({ \ int __ret = retval; \ - if (cgroup_bpf_enabled) \ + if (cgroup_bpf_enabled(BPF_CGROUP_GETSOCKOPT)) \ __ret = __cgroup_bpf_run_filter_getsockopt_kern( \ sock, level, optname, optval, optlen, retval); \ __ret; \ @@ -444,7 +446,7 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, return 0; } -#define cgroup_bpf_enabled (0) +#define cgroup_bpf_enabled(type) (0) #define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, type, t_ctx) ({ 0; }) #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (0) #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; }) -- cgit v1.2.3 From 8063e184e49011f6f3f34f6c358dc8a83890bb5b Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Wed, 27 Jan 2021 14:15:01 -0800 Subject: skmsg: Make sk_psock_destroy() static sk_psock_destroy() is a RCU callback, I can't see any reason why it could be used outside. Signed-off-by: Cong Wang Signed-off-by: Daniel Borkmann Cc: John Fastabend Cc: Jakub Sitnicki Cc: Lorenz Bauer Link: https://lore.kernel.org/bpf/20210127221501.46866-1-xiyou.wangcong@gmail.com --- include/linux/skmsg.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index fec0c5ac1c4f..8edbbf5f2f93 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -390,7 +390,6 @@ static inline struct sk_psock *sk_psock_get(struct sock *sk) } void sk_psock_stop(struct sock *sk, struct sk_psock *psock); -void sk_psock_destroy(struct rcu_head *rcu); void sk_psock_drop(struct sock *sk, struct sk_psock *psock); static inline void sk_psock_put(struct sock *sk, struct sk_psock *psock) -- cgit v1.2.3 From 772412176fb98493158929b220fe250127f611af Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Wed, 27 Jan 2021 11:31:39 -0800 Subject: bpf: Allow rewriting to ports under ip_unprivileged_port_start At the moment, BPF_CGROUP_INET{4,6}_BIND hooks can rewrite user_port to the privileged ones (< ip_unprivileged_port_start), but it will be rejected later on in the __inet_bind or __inet6_bind. Let's add another return value to indicate that CAP_NET_BIND_SERVICE check should be ignored. Use the same idea as we currently use in cgroup/egress where bit #1 indicates CN. Instead, for cgroup/bind{4,6}, bit #1 indicates that CAP_NET_BIND_SERVICE should be bypassed. v5: - rename flags to be less confusing (Andrey Ignatov) - rework BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY to work on flags and accept BPF_RET_SET_CN (no behavioral changes) v4: - Add missing IPv6 support (Martin KaFai Lau) v3: - Update description (Martin KaFai Lau) - Fix capability restore in selftest (Martin KaFai Lau) v2: - Switch to explicit return code (Martin KaFai Lau) Signed-off-by: Stanislav Fomichev Signed-off-by: Alexei Starovoitov Reviewed-by: Martin KaFai Lau Acked-by: Andrey Ignatov Link: https://lore.kernel.org/bpf/20210127193140.3170382-1-sdf@google.com --- include/linux/bpf-cgroup.h | 38 ++++++++++++++++++++++++--------- include/linux/bpf.h | 52 +++++++++++++++++++++++++++++----------------- 2 files changed, 61 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 0748fd87969e..c42e02b4d84b 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -125,7 +125,8 @@ int __cgroup_bpf_run_filter_sk(struct sock *sk, int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, struct sockaddr *uaddr, enum bpf_attach_type type, - void *t_ctx); + void *t_ctx, + u32 *flags); int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, struct bpf_sock_ops_kern *sock_ops, @@ -231,30 +232,48 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, type) \ ({ \ + u32 __unused_flags; \ int __ret = 0; \ if (cgroup_bpf_enabled(type)) \ __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type, \ - NULL); \ + NULL, \ + &__unused_flags); \ __ret; \ }) #define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, type, t_ctx) \ ({ \ + u32 __unused_flags; \ int __ret = 0; \ if (cgroup_bpf_enabled(type)) { \ lock_sock(sk); \ __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type, \ - t_ctx); \ + t_ctx, \ + &__unused_flags); \ release_sock(sk); \ } \ __ret; \ }) -#define BPF_CGROUP_RUN_PROG_INET4_BIND_LOCK(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET4_BIND, NULL) - -#define BPF_CGROUP_RUN_PROG_INET6_BIND_LOCK(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET6_BIND, NULL) +/* BPF_CGROUP_INET4_BIND and BPF_CGROUP_INET6_BIND can return extra flags + * via upper bits of return code. The only flag that is supported + * (at bit position 0) is to indicate CAP_NET_BIND_SERVICE capability check + * should be bypassed (BPF_RET_BIND_NO_CAP_NET_BIND_SERVICE). + */ +#define BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, type, bind_flags) \ +({ \ + u32 __flags = 0; \ + int __ret = 0; \ + if (cgroup_bpf_enabled(type)) { \ + lock_sock(sk); \ + __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type, \ + NULL, &__flags); \ + release_sock(sk); \ + if (__flags & BPF_RET_BIND_NO_CAP_NET_BIND_SERVICE) \ + *bind_flags |= BIND_NO_CAP_NET_BIND_SERVICE; \ + } \ + __ret; \ +}) #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) \ ((cgroup_bpf_enabled(BPF_CGROUP_INET4_CONNECT) || \ @@ -453,8 +472,7 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_SOCK_RELEASE(sk) ({ 0; }) -#define BPF_CGROUP_RUN_PROG_INET4_BIND_LOCK(sk, uaddr) ({ 0; }) -#define BPF_CGROUP_RUN_PROG_INET6_BIND_LOCK(sk, uaddr) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, type, flags) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET6_POST_BIND(sk) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr) ({ 0; }) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 1aac2af12fed..321966fc35db 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1073,6 +1073,34 @@ int bpf_prog_array_copy(struct bpf_prog_array *old_array, struct bpf_prog *include_prog, struct bpf_prog_array **new_array); +/* BPF program asks to bypass CAP_NET_BIND_SERVICE in bind. */ +#define BPF_RET_BIND_NO_CAP_NET_BIND_SERVICE (1 << 0) +/* BPF program asks to set CN on the packet. */ +#define BPF_RET_SET_CN (1 << 0) + +#define BPF_PROG_RUN_ARRAY_FLAGS(array, ctx, func, ret_flags) \ + ({ \ + struct bpf_prog_array_item *_item; \ + struct bpf_prog *_prog; \ + struct bpf_prog_array *_array; \ + u32 _ret = 1; \ + u32 func_ret; \ + migrate_disable(); \ + rcu_read_lock(); \ + _array = rcu_dereference(array); \ + _item = &_array->items[0]; \ + while ((_prog = READ_ONCE(_item->prog))) { \ + bpf_cgroup_storage_set(_item->cgroup_storage); \ + func_ret = func(_prog, ctx); \ + _ret &= (func_ret & 1); \ + *(ret_flags) |= (func_ret >> 1); \ + _item++; \ + } \ + rcu_read_unlock(); \ + migrate_enable(); \ + _ret; \ + }) + #define __BPF_PROG_RUN_ARRAY(array, ctx, func, check_non_null) \ ({ \ struct bpf_prog_array_item *_item; \ @@ -1120,25 +1148,11 @@ _out: \ */ #define BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY(array, ctx, func) \ ({ \ - struct bpf_prog_array_item *_item; \ - struct bpf_prog *_prog; \ - struct bpf_prog_array *_array; \ - u32 ret; \ - u32 _ret = 1; \ - u32 _cn = 0; \ - migrate_disable(); \ - rcu_read_lock(); \ - _array = rcu_dereference(array); \ - _item = &_array->items[0]; \ - while ((_prog = READ_ONCE(_item->prog))) { \ - bpf_cgroup_storage_set(_item->cgroup_storage); \ - ret = func(_prog, ctx); \ - _ret &= (ret & 1); \ - _cn |= (ret & 2); \ - _item++; \ - } \ - rcu_read_unlock(); \ - migrate_enable(); \ + u32 _flags = 0; \ + bool _cn; \ + u32 _ret; \ + _ret = BPF_PROG_RUN_ARRAY_FLAGS(array, ctx, func, &_flags); \ + _cn = _flags & BPF_RET_SET_CN; \ if (_ret) \ _ret = (_cn ? NET_XMIT_CN : NET_XMIT_SUCCESS); \ else \ -- cgit v1.2.3 From 01f810ace9ed37255f27608a0864abebccf0aab3 Mon Sep 17 00:00:00 2001 From: Andrei Matei Date: Sat, 6 Feb 2021 20:10:24 -0500 Subject: bpf: Allow variable-offset stack access Before this patch, variable offset access to the stack was dissalowed for regular instructions, but was allowed for "indirect" accesses (i.e. helpers). This patch removes the restriction, allowing reading and writing to the stack through stack pointers with variable offsets. This makes stack-allocated buffers more usable in programs, and brings stack pointers closer to other types of pointers. The motivation is being able to use stack-allocated buffers for data manipulation. When the stack size limit is sufficient, allocating buffers on the stack is simpler than per-cpu arrays, or other alternatives. In unpriviledged programs, variable-offset reads and writes are disallowed (they were already disallowed for the indirect access case) because the speculative execution checking code doesn't support them. Additionally, when writing through a variable-offset stack pointer, if any pointers are in the accessible range, there's possilibities of later leaking pointers because the write cannot be tracked precisely. Writes with variable offset mark the whole range as initialized, even though we don't know which stack slots are actually written. This is in order to not reject future reads to these slots. Note that this doesn't affect writes done through helpers; like before, helpers need the whole stack range to be initialized to begin with. All the stack slots are in range are considered scalars after the write; variable-offset register spills are not tracked. For reads, all the stack slots in the variable range needs to be initialized (but see above about what writes do), otherwise the read is rejected. All register spilled in stack slots that might be read are marked as having been read, however reads through such pointers don't do register filling; the target register will always be either a scalar or a constant zero. Signed-off-by: Andrei Matei Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20210207011027.676572-2-andreimatei1@gmail.com --- include/linux/bpf.h | 5 +++++ include/linux/bpf_verifier.h | 3 ++- 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 321966fc35db..079162bbd387 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1290,6 +1290,11 @@ static inline bool bpf_allow_ptr_leaks(void) return perfmon_capable(); } +static inline bool bpf_allow_uninit_stack(void) +{ + return perfmon_capable(); +} + static inline bool bpf_allow_ptr_to_map_access(void) { return perfmon_capable(); diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index dfe6f85d97dd..532c97836d0d 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -195,7 +195,7 @@ struct bpf_func_state { * 0 = main function, 1 = first callee. */ u32 frameno; - /* subprog number == index within subprog_stack_depth + /* subprog number == index within subprog_info * zero == main subprog */ u32 subprogno; @@ -404,6 +404,7 @@ struct bpf_verifier_env { u32 used_btf_cnt; /* number of used BTF objects */ u32 id_gen; /* used to generate unique reg IDs */ bool allow_ptr_leaks; + bool allow_uninit_stack; bool allow_ptr_to_map_access; bool bpf_capable; bool bypass_spec_v1; -- cgit v1.2.3 From 700d4796ef59f5faf240d307839bd419e2b6bdff Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 9 Feb 2021 19:36:26 -0800 Subject: bpf: Optimize program stats Move bpf_prog_stats from prog->aux into prog to avoid one extra load in critical path of program execution. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210210033634.62081-2-alexei.starovoitov@gmail.com --- include/linux/bpf.h | 8 -------- include/linux/filter.h | 14 +++++++++++--- 2 files changed, 11 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 079162bbd387..5a388955e6b6 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -14,7 +14,6 @@ #include #include #include -#include #include #include #include @@ -507,12 +506,6 @@ enum bpf_cgroup_storage_type { */ #define MAX_BPF_FUNC_ARGS 12 -struct bpf_prog_stats { - u64 cnt; - u64 nsecs; - struct u64_stats_sync syncp; -} __aligned(2 * sizeof(u64)); - struct btf_func_model { u8 ret_size; u8 nr_args; @@ -845,7 +838,6 @@ struct bpf_prog_aux { u32 linfo_idx; u32 num_exentries; struct exception_table_entry *extable; - struct bpf_prog_stats __percpu *stats; union { struct work_struct work; struct rcu_head rcu; diff --git a/include/linux/filter.h b/include/linux/filter.h index 5b3137d7b690..cecb03c9d251 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -22,6 +22,7 @@ #include #include #include +#include #include @@ -539,6 +540,12 @@ struct bpf_binary_header { u8 image[] __aligned(BPF_IMAGE_ALIGNMENT); }; +struct bpf_prog_stats { + u64 cnt; + u64 nsecs; + struct u64_stats_sync syncp; +} __aligned(2 * sizeof(u64)); + struct bpf_prog { u16 pages; /* Number of allocated pages */ u16 jited:1, /* Is our filter JIT'ed? */ @@ -557,10 +564,11 @@ struct bpf_prog { u32 len; /* Number of filter blocks */ u32 jited_len; /* Size of jited insns in bytes */ u8 tag[BPF_TAG_SIZE]; - struct bpf_prog_aux *aux; /* Auxiliary fields */ - struct sock_fprog_kern *orig_prog; /* Original BPF program */ + struct bpf_prog_stats __percpu *stats; unsigned int (*bpf_func)(const void *ctx, const struct bpf_insn *insn); + struct bpf_prog_aux *aux; /* Auxiliary fields */ + struct sock_fprog_kern *orig_prog; /* Original BPF program */ /* Instructions for interpreter */ struct sock_filter insns[0]; struct bpf_insn insnsi[]; @@ -581,7 +589,7 @@ DECLARE_STATIC_KEY_FALSE(bpf_stats_enabled_key); struct bpf_prog_stats *__stats; \ u64 __start = sched_clock(); \ __ret = dfunc(ctx, (prog)->insnsi, (prog)->bpf_func); \ - __stats = this_cpu_ptr(prog->aux->stats); \ + __stats = this_cpu_ptr(prog->stats); \ u64_stats_update_begin(&__stats->syncp); \ __stats->cnt++; \ __stats->nsecs += sched_clock() - __start; \ -- cgit v1.2.3 From f2dd3b39467411c53703125a111f45b3672c1771 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 9 Feb 2021 19:36:28 -0800 Subject: bpf: Compute program stats for sleepable programs Since sleepable programs don't migrate from the cpu the excution stats can be computed for them as well. Reuse the same infrastructure for both sleepable and non-sleepable programs. run_cnt -> the number of times the program was executed. run_time_ns -> the program execution time in nanoseconds including the off-cpu time when the program was sleeping. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Acked-by: KP Singh Link: https://lore.kernel.org/bpf/20210210033634.62081-4-alexei.starovoitov@gmail.com --- include/linux/bpf.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 5a388955e6b6..e1840ceaf55f 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -563,8 +563,8 @@ int arch_prepare_bpf_trampoline(void *image, void *image_end, /* these two functions are called from generated trampoline */ u64 notrace __bpf_prog_enter(void); void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start); -void notrace __bpf_prog_enter_sleepable(void); -void notrace __bpf_prog_exit_sleepable(void); +u64 notrace __bpf_prog_enter_sleepable(void); +void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start); struct bpf_ksym { unsigned long start; -- cgit v1.2.3 From ca06f55b90020cd97f4cc6d52db95436162e7dcf Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 9 Feb 2021 19:36:29 -0800 Subject: bpf: Add per-program recursion prevention mechanism Since both sleepable and non-sleepable programs execute under migrate_disable add recursion prevention mechanism to both types of programs when they're executed via bpf trampoline. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210210033634.62081-5-alexei.starovoitov@gmail.com --- include/linux/bpf.h | 6 +++--- include/linux/filter.h | 1 + 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e1840ceaf55f..1c8ea682c007 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -529,7 +529,7 @@ struct btf_func_model { /* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50 * bytes on x86. Pick a number to fit into BPF_IMAGE_SIZE / 2 */ -#define BPF_MAX_TRAMP_PROGS 40 +#define BPF_MAX_TRAMP_PROGS 38 struct bpf_tramp_progs { struct bpf_prog *progs[BPF_MAX_TRAMP_PROGS]; @@ -561,9 +561,9 @@ int arch_prepare_bpf_trampoline(void *image, void *image_end, struct bpf_tramp_progs *tprogs, void *orig_call); /* these two functions are called from generated trampoline */ -u64 notrace __bpf_prog_enter(void); +u64 notrace __bpf_prog_enter(struct bpf_prog *prog); void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start); -u64 notrace __bpf_prog_enter_sleepable(void); +u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog); void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start); struct bpf_ksym { diff --git a/include/linux/filter.h b/include/linux/filter.h index cecb03c9d251..6a06f3c69f4e 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -565,6 +565,7 @@ struct bpf_prog { u32 jited_len; /* Size of jited insns in bytes */ u8 tag[BPF_TAG_SIZE]; struct bpf_prog_stats __percpu *stats; + int __percpu *active; unsigned int (*bpf_func)(const void *ctx, const struct bpf_insn *insn); struct bpf_prog_aux *aux; /* Auxiliary fields */ -- cgit v1.2.3 From 9ed9e9ba2337205311398a312796c213737bac35 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 9 Feb 2021 19:36:31 -0800 Subject: bpf: Count the number of times recursion was prevented Add per-program counter for number of times recursion prevention mechanism was triggered and expose it via show_fdinfo and bpf_prog_info. Teach bpftool to print it. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210210033634.62081-7-alexei.starovoitov@gmail.com --- include/linux/filter.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 6a06f3c69f4e..3b00fc906ccd 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -543,6 +543,7 @@ struct bpf_binary_header { struct bpf_prog_stats { u64 cnt; u64 nsecs; + u64 misses; struct u64_stats_sync syncp; } __aligned(2 * sizeof(u64)); -- cgit v1.2.3 From c5dbb89fc2ac013afe67b9e4fcb3743c02b567cd Mon Sep 17 00:00:00 2001 From: Florent Revest Date: Wed, 10 Feb 2021 12:14:03 +0100 Subject: bpf: Expose bpf_get_socket_cookie to tracing programs This needs a new helper that: - can work in a sleepable context (using sock_gen_cookie) - takes a struct sock pointer and checks that it's not NULL Signed-off-by: Florent Revest Signed-off-by: Alexei Starovoitov Acked-by: KP Singh Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210210111406.785541-2-revest@chromium.org --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 1c8ea682c007..cccaef1088ea 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1885,6 +1885,7 @@ extern const struct bpf_func_proto bpf_per_cpu_ptr_proto; extern const struct bpf_func_proto bpf_this_cpu_ptr_proto; extern const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto; extern const struct bpf_func_proto bpf_sock_from_file_proto; +extern const struct bpf_func_proto bpf_get_socket_ptr_cookie_proto; const struct bpf_func_proto *bpf_tracing_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); -- cgit v1.2.3 From 5f7d57280c1982d993d5f4ff0edac310f820f607 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Tue, 9 Feb 2021 14:38:29 +0100 Subject: bpf: Drop MTU check when doing TC-BPF redirect to ingress The use-case for dropping the MTU check when TC-BPF does redirect to ingress, is described by Eyal Birger in email[0]. The summary is the ability to increase packet size (e.g. with IPv6 headers for NAT64) and ingress redirect packet and let normal netstack fragment packet as needed. [0] https://lore.kernel.org/netdev/CAHsH6Gug-hsLGHQ6N0wtixdOa85LDZ3HNRHVd0opR=19Qo4W4Q@mail.gmail.com/ V15: - missing static for function declaration V9: - Make net_device "up" (IFF_UP) check explicit in skb_do_redirect V4: - Keep net_device "up" (IFF_UP) check. - Adjustment to handle bpf_redirect_peer() helper Signed-off-by: Jesper Dangaard Brouer Signed-off-by: Daniel Borkmann Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/161287790971.790810.11785274340154740591.stgit@firesoul --- include/linux/netdevice.h | 32 ++++++++++++++++++++++++++++++-- 1 file changed, 30 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ef517254367d..b9bcbfde7849 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3931,14 +3931,42 @@ int xdp_umem_query(struct net_device *dev, u16 queue_id); int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb); int dev_forward_skb(struct net_device *dev, struct sk_buff *skb); +int dev_forward_skb_nomtu(struct net_device *dev, struct sk_buff *skb); bool is_skb_forwardable(const struct net_device *dev, const struct sk_buff *skb); +static __always_inline bool __is_skb_forwardable(const struct net_device *dev, + const struct sk_buff *skb, + const bool check_mtu) +{ + const u32 vlan_hdr_len = 4; /* VLAN_HLEN */ + unsigned int len; + + if (!(dev->flags & IFF_UP)) + return false; + + if (!check_mtu) + return true; + + len = dev->mtu + dev->hard_header_len + vlan_hdr_len; + if (skb->len <= len) + return true; + + /* if TSO is enabled, we don't care about the length as the packet + * could be forwarded without being segmented before + */ + if (skb_is_gso(skb)) + return true; + + return false; +} + static __always_inline int ____dev_forward_skb(struct net_device *dev, - struct sk_buff *skb) + struct sk_buff *skb, + const bool check_mtu) { if (skb_orphan_frags(skb, GFP_ATOMIC) || - unlikely(!is_skb_forwardable(dev, skb))) { + unlikely(!__is_skb_forwardable(dev, skb, check_mtu))) { atomic_long_inc(&dev->rx_dropped); kfree_skb(skb); return NET_RX_DROP; -- cgit v1.2.3 From e5069b9c23b3857db986c58801bebe450cff3392 Mon Sep 17 00:00:00 2001 From: Dmitrii Banshchikov Date: Sat, 13 Feb 2021 00:56:41 +0400 Subject: bpf: Support pointers in global func args Add an ability to pass a pointer to a type with known size in arguments of a global function. Such pointers may be used to overcome the limit on the maximum number of arguments, avoid expensive and tricky workarounds and to have multiple output arguments. A referenced type may contain pointers but indirect access through them isn't supported. The implementation consists of two parts. If a global function has an argument that is a pointer to a type with known size then: 1) In btf_check_func_arg_match(): check that the corresponding register points to NULL or to a valid memory region that is large enough to contain the expected argument's type. 2) In btf_prepare_func_args(): set the corresponding register type to PTR_TO_MEM_OR_NULL and its size to the size of the expected type. Only global functions are supported because allowance of pointers for static functions might break validation. Consider the following scenario. A static function has a pointer argument. A caller passes pointer to its stack memory. Because the callee can change referenced memory verifier cannot longer assume any particular slot type of the caller's stack memory hence the slot type is changed to SLOT_MISC. If there is an operation that relies on slot type other than SLOT_MISC then verifier won't be able to infer safety of the operation. When verifier sees a static function that has a pointer argument different from PTR_TO_CTX then it skips arguments check and continues with "inline" validation with more information available. The operation that relies on the particular slot type now succeeds. Because global functions were not allowed to have pointer arguments different from PTR_TO_CTX it's not possible to break existing and valid code. Signed-off-by: Dmitrii Banshchikov Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210212205642.620788-4-me@ubique.spb.ru --- include/linux/bpf_verifier.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 532c97836d0d..971b33aca13d 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -471,6 +471,8 @@ bpf_prog_offload_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt); int check_ctx_reg(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int regno); +int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, + u32 regno, u32 mem_size); /* this lives here instead of in bpf.h because it needs to dereference tgt_prog */ static inline u64 bpf_trampoline_compute_key(const struct bpf_prog *tgt_prog, -- cgit v1.2.3