From e2b2cd592adbd303bcc02451d32fedd511000fb0 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 20 Sep 2023 23:31:38 +0200 Subject: bpf: Add missed value to kprobe_multi link info Add missed value to kprobe_multi link info to hold the stats of missed kprobe_multi probe. The missed counter gets incremented when fprobe fails the recursion check or there's no rethook available for return probe. In either case the attached bpf program is not executed. Signed-off-by: Jiri Olsa Signed-off-by: Andrii Nakryiko Tested-by: Song Liu Reviewed-by: Song Liu Acked-by: Hou Tao Link: https://lore.kernel.org/bpf/20230920213145.1941596-3-jolsa@kernel.org --- include/uapi/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 5f13db15a3c7..1da5b1bcce71 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -6532,6 +6532,7 @@ struct bpf_link_info { __aligned_u64 addrs; __u32 count; /* in/out: kprobe_multi function count */ __u32 flags; + __u64 missed; } kprobe_multi; struct { __u32 type; /* enum bpf_perf_event_type */ -- cgit v1.2.3 From 3acf8ace68230e9558cf916847f1cc9f208abdf1 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 20 Sep 2023 23:31:39 +0200 Subject: bpf: Add missed value to kprobe perf link info Add missed value to kprobe attached through perf link info to hold the stats of missed kprobe handler execution. The kprobe's missed counter gets incremented when kprobe handler is not executed due to another kprobe running on the same cpu. Signed-off-by: Jiri Olsa Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20230920213145.1941596-4-jolsa@kernel.org --- include/linux/trace_events.h | 6 ++++-- include/uapi/linux/bpf.h | 1 + 2 files changed, 5 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 21ae37e49319..5eb88a66eb68 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -761,7 +761,8 @@ struct bpf_raw_event_map *bpf_get_raw_tracepoint(const char *name); void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp); int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, u32 *fd_type, const char **buf, - u64 *probe_offset, u64 *probe_addr); + u64 *probe_offset, u64 *probe_addr, + unsigned long *missed); int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); #else @@ -801,7 +802,7 @@ static inline void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp) static inline int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, u32 *fd_type, const char **buf, u64 *probe_offset, - u64 *probe_addr) + u64 *probe_addr, unsigned long *missed) { return -EOPNOTSUPP; } @@ -877,6 +878,7 @@ extern void perf_kprobe_destroy(struct perf_event *event); extern int bpf_get_kprobe_info(const struct perf_event *event, u32 *fd_type, const char **symbol, u64 *probe_offset, u64 *probe_addr, + unsigned long *missed, bool perf_type_tracepoint); #endif #ifdef CONFIG_UPROBE_EVENTS diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 1da5b1bcce71..70bfa997e896 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -6548,6 +6548,7 @@ struct bpf_link_info { __u32 name_len; __u32 offset; /* offset from func_name */ __u64 addr; + __u64 missed; } kprobe; /* BPF_PERF_EVENT_KPROBE, BPF_PERF_EVENT_KRETPROBE */ struct { __aligned_u64 tp_name; /* in/out */ -- cgit v1.2.3 From dd8657894c11b03c6eb0fd53fe9d7fec2072d18b Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 20 Sep 2023 23:31:40 +0200 Subject: bpf: Count missed stats in trace_call_bpf Increase misses stats in case bpf array execution is skipped because of recursion check in trace_call_bpf. Adding bpf_prog_inc_misses_counters that increase misses counts for all bpf programs in bpf_prog_array. Signed-off-by: Jiri Olsa Signed-off-by: Andrii Nakryiko Tested-by: Song Liu Reviewed-by: Song Liu Link: https://lore.kernel.org/bpf/20230920213145.1941596-5-jolsa@kernel.org --- include/linux/bpf.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 30063a760b5a..a82efd34b741 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2922,6 +2922,22 @@ static inline int sock_map_bpf_prog_query(const union bpf_attr *attr, #endif /* CONFIG_BPF_SYSCALL */ #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ +static __always_inline void +bpf_prog_inc_misses_counters(const struct bpf_prog_array *array) +{ + const struct bpf_prog_array_item *item; + struct bpf_prog *prog; + + if (unlikely(!array)) + return; + + item = &array->items[0]; + while ((prog = READ_ONCE(item->prog))) { + bpf_prog_inc_misses_counter(prog); + item++; + } +} + #if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) void bpf_sk_reuseport_detach(struct sock *sk); int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key, -- cgit v1.2.3 From 9c8c3fa3a52bc55696ccc4dfcb8a49f969b5fb0e Mon Sep 17 00:00:00 2001 From: Akihiko Odaki Date: Thu, 5 Oct 2023 16:21:36 +0900 Subject: bpf: Fix the comment for bpf_restore_data_end() The comment used to say: > Restore data saved by bpf_compute_data_pointers(). But bpf_compute_data_pointers() does not save the data; bpf_compute_and_save_data_end() does. Signed-off-by: Akihiko Odaki Acked-by: Stanislav Fomichev Link: https://lore.kernel.org/r/20231005072137.29870-1-akihiko.odaki@daynix.com Signed-off-by: Martin KaFai Lau --- include/linux/filter.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index 27406aee2d40..ff7ecc89d3dd 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -736,7 +736,7 @@ static inline void bpf_compute_and_save_data_end( cb->data_end = skb->data + skb_headlen(skb); } -/* Restore data saved by bpf_compute_data_pointers(). */ +/* Restore data saved by bpf_compute_and_save_data_end(). */ static inline void bpf_restore_data_end( struct sk_buff *skb, void *saved_data_end) { -- cgit v1.2.3 From bc5bc309db45a7ab218ce8259ba9bc7659be61ca Mon Sep 17 00:00:00 2001 From: Yafang Shao Date: Thu, 5 Oct 2023 08:41:23 +0000 Subject: bpf: Inherit system settings for CPU security mitigations Currently, there exists a system-wide setting related to CPU security mitigations, denoted as 'mitigations='. When set to 'mitigations=off', it deactivates all optional CPU mitigations. Therefore, if we implement a system-wide 'mitigations=off' setting, it should inherently bypass Spectre v1 and Spectre v4 in the BPF subsystem. Please note that there is also a more specific 'nospectre_v1' setting on x86 and ppc architectures, though it is not currently exported. For the time being, let's disregard more fine-grained options. This idea emerged during our discussion about potential Spectre v1 attacks with Luis [0]. [0] https://lore.kernel.org/bpf/b4fc15f7-b204-767e-ebb9-fdb4233961fb@iogearbox.net Signed-off-by: Yafang Shao Signed-off-by: Daniel Borkmann Acked-by: Stanislav Fomichev Acked-by: Song Liu Acked-by: KP Singh Cc: Luis Gerhorst Link: https://lore.kernel.org/bpf/20231005084123.1338-1-laoar.shao@gmail.com --- include/linux/bpf.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index a82efd34b741..61bde4520f5c 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2164,12 +2164,12 @@ static inline bool bpf_allow_uninit_stack(void) static inline bool bpf_bypass_spec_v1(void) { - return perfmon_capable(); + return perfmon_capable() || cpu_mitigations_off(); } static inline bool bpf_bypass_spec_v4(void) { - return perfmon_capable(); + return perfmon_capable() || cpu_mitigations_off(); } int bpf_map_new_fd(struct bpf_map *map, int flags); -- cgit v1.2.3 From d6247ecb6c1e17d7a33317090627f5bfe563cbb2 Mon Sep 17 00:00:00 2001 From: David Vernet Date: Wed, 4 Oct 2023 11:23:38 -0500 Subject: bpf: Add ability to pin bpf timer to calling CPU BPF supports creating high resolution timers using bpf_timer_* helper functions. Currently, only the BPF_F_TIMER_ABS flag is supported, which specifies that the timeout should be interpreted as absolute time. It would also be useful to be able to pin that timer to a core. For example, if you wanted to make a subset of cores run without timer interrupts, and only have the timer be invoked on a single core. This patch adds support for this with a new BPF_F_TIMER_CPU_PIN flag. When specified, the HRTIMER_MODE_PINNED flag is passed to hrtimer_start(). A subsequent patch will update selftests to validate. Signed-off-by: David Vernet Signed-off-by: Daniel Borkmann Acked-by: Song Liu Acked-by: Hou Tao Link: https://lore.kernel.org/bpf/20231004162339.200702-2-void@manifault.com --- include/uapi/linux/bpf.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 70bfa997e896..a7d4a1a69f21 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5096,6 +5096,8 @@ union bpf_attr { * **BPF_F_TIMER_ABS** * Start the timer in absolute expire value instead of the * default relative one. + * **BPF_F_TIMER_CPU_PIN** + * Timer will be pinned to the CPU of the caller. * * Return * 0 on success. @@ -7309,9 +7311,11 @@ struct bpf_core_relo { * Flags to control bpf_timer_start() behaviour. * - BPF_F_TIMER_ABS: Timeout passed is absolute time, by default it is * relative to current time. + * - BPF_F_TIMER_CPU_PIN: Timer will be pinned to the CPU of the caller. */ enum { BPF_F_TIMER_ABS = (1ULL << 0), + BPF_F_TIMER_CPU_PIN = (1ULL << 1), }; /* BPF numbers iterator state */ -- cgit v1.2.3 From dab4e1f06cabb6834de14264394ccab197007302 Mon Sep 17 00:00:00 2001 From: Martynas Pumputis Date: Sat, 7 Oct 2023 10:14:14 +0200 Subject: bpf: Derive source IP addr via bpf_*_fib_lookup() Extend the bpf_fib_lookup() helper by making it to return the source IPv4/IPv6 address if the BPF_FIB_LOOKUP_SRC flag is set. For example, the following snippet can be used to derive the desired source IP address: struct bpf_fib_lookup p = { .ipv4_dst = ip4->daddr }; ret = bpf_skb_fib_lookup(skb, p, sizeof(p), BPF_FIB_LOOKUP_SRC | BPF_FIB_LOOKUP_SKIP_NEIGH); if (ret != BPF_FIB_LKUP_RET_SUCCESS) return TC_ACT_SHOT; /* the p.ipv4_src now contains the source address */ The inability to derive the proper source address may cause malfunctions in BPF-based dataplanes for hosts containing netdevs with more than one routable IP address or for multi-homed hosts. For example, Cilium implements packet masquerading in BPF. If an egressing netdev to which the Cilium's BPF prog is attached has multiple IP addresses, then only one [hardcoded] IP address can be used for masquerading. This breaks connectivity if any other IP address should have been selected instead, for example, when a public and private addresses are attached to the same egress interface. The change was tested with Cilium [1]. Nikolay Aleksandrov helped to figure out the IPv6 addr selection. [1]: https://github.com/cilium/cilium/pull/28283 Signed-off-by: Martynas Pumputis Link: https://lore.kernel.org/r/20231007081415.33502-2-m@lambda.lt Signed-off-by: Martin KaFai Lau --- include/net/ipv6_stubs.h | 5 +++++ include/uapi/linux/bpf.h | 10 ++++++++++ 2 files changed, 15 insertions(+) (limited to 'include') diff --git a/include/net/ipv6_stubs.h b/include/net/ipv6_stubs.h index c48186bf4737..21da31e1dff5 100644 --- a/include/net/ipv6_stubs.h +++ b/include/net/ipv6_stubs.h @@ -85,6 +85,11 @@ struct ipv6_bpf_stub { sockptr_t optval, unsigned int optlen); int (*ipv6_getsockopt)(struct sock *sk, int level, int optname, sockptr_t optval, sockptr_t optlen); + int (*ipv6_dev_get_saddr)(struct net *net, + const struct net_device *dst_dev, + const struct in6_addr *daddr, + unsigned int prefs, + struct in6_addr *saddr); }; extern const struct ipv6_bpf_stub *ipv6_bpf_stub __read_mostly; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index a7d4a1a69f21..e0aa457f94a9 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3264,6 +3264,11 @@ union bpf_attr { * and *params*->smac will not be set as output. A common * use case is to call **bpf_redirect_neigh**\ () after * doing **bpf_fib_lookup**\ (). + * **BPF_FIB_LOOKUP_SRC** + * Derive and set source IP addr in *params*->ipv{4,6}_src + * for the nexthop. If the src addr cannot be derived, + * **BPF_FIB_LKUP_RET_NO_SRC_ADDR** is returned. In this + * case, *params*->dmac and *params*->smac are not set either. * * *ctx* is either **struct xdp_md** for XDP programs or * **struct sk_buff** tc cls_act programs. @@ -6964,6 +6969,7 @@ enum { BPF_FIB_LOOKUP_OUTPUT = (1U << 1), BPF_FIB_LOOKUP_SKIP_NEIGH = (1U << 2), BPF_FIB_LOOKUP_TBID = (1U << 3), + BPF_FIB_LOOKUP_SRC = (1U << 4), }; enum { @@ -6976,6 +6982,7 @@ enum { BPF_FIB_LKUP_RET_UNSUPP_LWT, /* fwd requires encapsulation */ BPF_FIB_LKUP_RET_NO_NEIGH, /* no neighbor entry for nh */ BPF_FIB_LKUP_RET_FRAG_NEEDED, /* fragmentation required to fwd */ + BPF_FIB_LKUP_RET_NO_SRC_ADDR, /* failed to derive IP src addr */ }; struct bpf_fib_lookup { @@ -7010,6 +7017,9 @@ struct bpf_fib_lookup { __u32 rt_metric; }; + /* input: source address to consider for lookup + * output: source address result from lookup + */ union { __be32 ipv4_src; __u32 ipv6_src[4]; /* in6_addr; network order */ -- cgit v1.2.3 From fefba7d1ae198dcbf8b3b432de46a4e29f8dbd8c Mon Sep 17 00:00:00 2001 From: Daan De Meyer Date: Wed, 11 Oct 2023 20:51:04 +0200 Subject: bpf: Propagate modified uaddrlen from cgroup sockaddr programs As prep for adding unix socket support to the cgroup sockaddr hooks, let's propagate the sockaddr length back to the caller after running a bpf cgroup sockaddr hook program. While not important for AF_INET or AF_INET6, the sockaddr length is important when working with AF_UNIX sockaddrs as the size of the sockaddr cannot be determined just from the address family or the sockaddr's contents. __cgroup_bpf_run_filter_sock_addr() is modified to take the uaddrlen as an input/output argument. After running the program, the modified sockaddr length is stored in the uaddrlen pointer. Signed-off-by: Daan De Meyer Link: https://lore.kernel.org/r/20231011185113.140426-3-daan.j.demeyer@gmail.com Signed-off-by: Martin KaFai Lau --- include/linux/bpf-cgroup.h | 73 +++++++++++++++++++++++----------------------- include/linux/filter.h | 1 + 2 files changed, 38 insertions(+), 36 deletions(-) (limited to 'include') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 8506690dbb9c..31561e789715 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -120,6 +120,7 @@ int __cgroup_bpf_run_filter_sk(struct sock *sk, int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, struct sockaddr *uaddr, + int *uaddrlen, enum cgroup_bpf_attach_type atype, void *t_ctx, u32 *flags); @@ -230,22 +231,22 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk, #define BPF_CGROUP_RUN_PROG_INET6_POST_BIND(sk) \ BPF_CGROUP_RUN_SK_PROG(sk, CGROUP_INET6_POST_BIND) -#define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, atype) \ +#define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, uaddrlen, atype) \ ({ \ int __ret = 0; \ if (cgroup_bpf_enabled(atype)) \ - __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, atype, \ - NULL, NULL); \ + __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, uaddrlen, \ + atype, NULL, NULL); \ __ret; \ }) -#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, atype, t_ctx) \ +#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, atype, t_ctx) \ ({ \ int __ret = 0; \ if (cgroup_bpf_enabled(atype)) { \ lock_sock(sk); \ - __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, atype, \ - t_ctx, NULL); \ + __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, uaddrlen, \ + atype, t_ctx, NULL); \ release_sock(sk); \ } \ __ret; \ @@ -256,14 +257,14 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk, * (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, atype, bind_flags) \ +#define BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, uaddrlen, atype, bind_flags) \ ({ \ u32 __flags = 0; \ int __ret = 0; \ if (cgroup_bpf_enabled(atype)) { \ lock_sock(sk); \ - __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, atype, \ - NULL, &__flags); \ + __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, uaddrlen, \ + atype, NULL, &__flags); \ release_sock(sk); \ if (__flags & BPF_RET_BIND_NO_CAP_NET_BIND_SERVICE) \ *bind_flags |= BIND_NO_CAP_NET_BIND_SERVICE; \ @@ -276,29 +277,29 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk, cgroup_bpf_enabled(CGROUP_INET6_CONNECT)) && \ (sk)->sk_prot->pre_connect) -#define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG(sk, uaddr, CGROUP_INET4_CONNECT) +#define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr, uaddrlen) \ + BPF_CGROUP_RUN_SA_PROG(sk, uaddr, uaddrlen, CGROUP_INET4_CONNECT) -#define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG(sk, uaddr, CGROUP_INET6_CONNECT) +#define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr, uaddrlen) \ + BPF_CGROUP_RUN_SA_PROG(sk, uaddr, uaddrlen, CGROUP_INET6_CONNECT) -#define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_INET4_CONNECT, NULL) +#define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr, uaddrlen) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_INET4_CONNECT, NULL) -#define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_INET6_CONNECT, NULL) +#define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr, uaddrlen) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_INET6_CONNECT, NULL) -#define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, t_ctx) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_UDP4_SENDMSG, t_ctx) +#define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP4_SENDMSG, t_ctx) -#define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, t_ctx) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_UDP6_SENDMSG, t_ctx) +#define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP6_SENDMSG, t_ctx) -#define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_UDP4_RECVMSG, NULL) +#define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr, uaddrlen) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP4_RECVMSG, NULL) -#define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_UDP6_RECVMSG, NULL) +#define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr, uaddrlen) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP6_RECVMSG, NULL) /* The SOCK_OPS"_SK" macro should be used when sock_ops->sk is not a * fullsock and its parent fullsock cannot be traced by @@ -477,24 +478,24 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, } #define cgroup_bpf_enabled(atype) (0) -#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, atype, t_ctx) ({ 0; }) -#define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, atype) ({ 0; }) +#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, atype, t_ctx) ({ 0; }) +#define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, uaddrlen, atype) ({ 0; }) #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (0) #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; }) #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_INET_BIND_LOCK(sk, uaddr, atype, flags) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, uaddrlen, atype, 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; }) -#define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr) ({ 0; }) -#define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr) ({ 0; }) -#define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr) ({ 0; }) -#define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, t_ctx) ({ 0; }) -#define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, t_ctx) ({ 0; }) -#define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr) ({ 0; }) -#define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr, uaddrlen) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr, uaddrlen) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr, uaddrlen) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr, uaddrlen) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr, uaddrlen) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr, uaddrlen) ({ 0; }) #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; }) diff --git a/include/linux/filter.h b/include/linux/filter.h index ff7ecc89d3dd..bcd2bc15ff56 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1335,6 +1335,7 @@ struct bpf_sock_addr_kern { */ u64 tmp_reg; void *t_ctx; /* Attach type specific context. */ + u32 uaddrlen; }; struct bpf_sock_ops_kern { -- cgit v1.2.3 From 859051dd165ec6cc915f0f2114699021144fd249 Mon Sep 17 00:00:00 2001 From: Daan De Meyer Date: Wed, 11 Oct 2023 20:51:06 +0200 Subject: bpf: Implement cgroup sockaddr hooks for unix sockets These hooks allows intercepting connect(), getsockname(), getpeername(), sendmsg() and recvmsg() for unix sockets. The unix socket hooks get write access to the address length because the address length is not fixed when dealing with unix sockets and needs to be modified when a unix socket address is modified by the hook. Because abstract socket unix addresses start with a NUL byte, we cannot recalculate the socket address in kernelspace after running the hook by calculating the length of the unix socket path using strlen(). These hooks can be used when users want to multiplex syscall to a single unix socket to multiple different processes behind the scenes by redirecting the connect() and other syscalls to process specific sockets. We do not implement support for intercepting bind() because when using bind() with unix sockets with a pathname address, this creates an inode in the filesystem which must be cleaned up. If we rewrite the address, the user might try to clean up the wrong file, leaking the socket in the filesystem where it is never cleaned up. Until we figure out a solution for this (and a use case for intercepting bind()), we opt to not allow rewriting the sockaddr in bind() calls. We also implement recvmsg() support for connected streams so that after a connect() that is modified by a sockaddr hook, any corresponding recmvsg() on the connected socket can also be modified to make the connected program think it is connected to the "intended" remote. Reviewed-by: Kuniyuki Iwashima Signed-off-by: Daan De Meyer Link: https://lore.kernel.org/r/20231011185113.140426-5-daan.j.demeyer@gmail.com Signed-off-by: Martin KaFai Lau --- include/linux/bpf-cgroup-defs.h | 5 +++++ include/linux/bpf-cgroup.h | 17 +++++++++++++++++ include/uapi/linux/bpf.h | 13 +++++++++---- 3 files changed, 31 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/bpf-cgroup-defs.h b/include/linux/bpf-cgroup-defs.h index 7b121bd780eb..0985221d5478 100644 --- a/include/linux/bpf-cgroup-defs.h +++ b/include/linux/bpf-cgroup-defs.h @@ -28,19 +28,24 @@ enum cgroup_bpf_attach_type { CGROUP_INET6_BIND, CGROUP_INET4_CONNECT, CGROUP_INET6_CONNECT, + CGROUP_UNIX_CONNECT, CGROUP_INET4_POST_BIND, CGROUP_INET6_POST_BIND, CGROUP_UDP4_SENDMSG, CGROUP_UDP6_SENDMSG, + CGROUP_UNIX_SENDMSG, CGROUP_SYSCTL, CGROUP_UDP4_RECVMSG, CGROUP_UDP6_RECVMSG, + CGROUP_UNIX_RECVMSG, CGROUP_GETSOCKOPT, CGROUP_SETSOCKOPT, CGROUP_INET4_GETPEERNAME, CGROUP_INET6_GETPEERNAME, + CGROUP_UNIX_GETPEERNAME, CGROUP_INET4_GETSOCKNAME, CGROUP_INET6_GETSOCKNAME, + CGROUP_UNIX_GETSOCKNAME, CGROUP_INET_SOCK_RELEASE, CGROUP_LSM_START, CGROUP_LSM_END = CGROUP_LSM_START + CGROUP_LSM_NUM - 1, diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 31561e789715..98b8cea904fe 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -48,19 +48,24 @@ to_cgroup_bpf_attach_type(enum bpf_attach_type attach_type) CGROUP_ATYPE(CGROUP_INET6_BIND); CGROUP_ATYPE(CGROUP_INET4_CONNECT); CGROUP_ATYPE(CGROUP_INET6_CONNECT); + CGROUP_ATYPE(CGROUP_UNIX_CONNECT); CGROUP_ATYPE(CGROUP_INET4_POST_BIND); CGROUP_ATYPE(CGROUP_INET6_POST_BIND); CGROUP_ATYPE(CGROUP_UDP4_SENDMSG); CGROUP_ATYPE(CGROUP_UDP6_SENDMSG); + CGROUP_ATYPE(CGROUP_UNIX_SENDMSG); CGROUP_ATYPE(CGROUP_SYSCTL); CGROUP_ATYPE(CGROUP_UDP4_RECVMSG); CGROUP_ATYPE(CGROUP_UDP6_RECVMSG); + CGROUP_ATYPE(CGROUP_UNIX_RECVMSG); CGROUP_ATYPE(CGROUP_GETSOCKOPT); CGROUP_ATYPE(CGROUP_SETSOCKOPT); CGROUP_ATYPE(CGROUP_INET4_GETPEERNAME); CGROUP_ATYPE(CGROUP_INET6_GETPEERNAME); + CGROUP_ATYPE(CGROUP_UNIX_GETPEERNAME); CGROUP_ATYPE(CGROUP_INET4_GETSOCKNAME); CGROUP_ATYPE(CGROUP_INET6_GETSOCKNAME); + CGROUP_ATYPE(CGROUP_UNIX_GETSOCKNAME); CGROUP_ATYPE(CGROUP_INET_SOCK_RELEASE); default: return CGROUP_BPF_ATTACH_TYPE_INVALID; @@ -289,18 +294,27 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk, #define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr, uaddrlen) \ BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_INET6_CONNECT, NULL) +#define BPF_CGROUP_RUN_PROG_UNIX_CONNECT_LOCK(sk, uaddr, uaddrlen) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UNIX_CONNECT, NULL) + #define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) \ BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP4_SENDMSG, t_ctx) #define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) \ BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP6_SENDMSG, t_ctx) +#define BPF_CGROUP_RUN_PROG_UNIX_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UNIX_SENDMSG, t_ctx) + #define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr, uaddrlen) \ BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP4_RECVMSG, NULL) #define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr, uaddrlen) \ BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP6_RECVMSG, NULL) +#define BPF_CGROUP_RUN_PROG_UNIX_RECVMSG_LOCK(sk, uaddr, uaddrlen) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UNIX_RECVMSG, NULL) + /* The SOCK_OPS"_SK" macro should be used when sock_ops->sk is not a * fullsock and its parent fullsock cannot be traced by * sk_to_full_sk(). @@ -492,10 +506,13 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, #define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr, uaddrlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr, uaddrlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr, uaddrlen) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_UNIX_CONNECT_LOCK(sk, uaddr, uaddrlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) ({ 0; }) #define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_UNIX_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) ({ 0; }) #define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr, uaddrlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr, uaddrlen) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_UNIX_RECVMSG_LOCK(sk, uaddr, uaddrlen) ({ 0; }) #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; }) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index e0aa457f94a9..7ba61b75bc0e 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1047,6 +1047,11 @@ enum bpf_attach_type { BPF_TCX_INGRESS, BPF_TCX_EGRESS, BPF_TRACE_UPROBE_MULTI, + BPF_CGROUP_UNIX_CONNECT, + BPF_CGROUP_UNIX_SENDMSG, + BPF_CGROUP_UNIX_RECVMSG, + BPF_CGROUP_UNIX_GETPEERNAME, + BPF_CGROUP_UNIX_GETSOCKNAME, __MAX_BPF_ATTACH_TYPE }; @@ -2704,8 +2709,8 @@ union bpf_attr { * *bpf_socket* should be one of the following: * * * **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**. - * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT** - * and **BPF_CGROUP_INET6_CONNECT**. + * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**, + * **BPF_CGROUP_INET6_CONNECT** and **BPF_CGROUP_UNIX_CONNECT**. * * This helper actually implements a subset of **setsockopt()**. * It supports the following *level*\ s: @@ -2943,8 +2948,8 @@ union bpf_attr { * *bpf_socket* should be one of the following: * * * **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**. - * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT** - * and **BPF_CGROUP_INET6_CONNECT**. + * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**, + * **BPF_CGROUP_INET6_CONNECT** and **BPF_CGROUP_UNIX_CONNECT**. * * This helper actually implements a subset of **getsockopt()**. * It supports the same set of *optname*\ s that is supported by -- cgit v1.2.3 From 236334aeec0f93217cf9235f2004e61a0a1a5985 Mon Sep 17 00:00:00 2001 From: Yafang Shao Date: Fri, 13 Oct 2023 08:39:16 +0000 Subject: bpf: Avoid unnecessary audit log for CPU security mitigations Check cpu_mitigations_off() first to avoid calling capable() if it is off. This can avoid unnecessary audit log. Fixes: bc5bc309db45 ("bpf: Inherit system settings for CPU security mitigations") Suggested-by: Andrii Nakryiko Signed-off-by: Yafang Shao Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/CAEf4Bza6UVUWqcWQ-66weZ-nMDr+TFU3Mtq=dumZFD-pSqU7Ow@mail.gmail.com/ Link: https://lore.kernel.org/bpf/20231013083916.4199-1-laoar.shao@gmail.com --- include/linux/bpf.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 61bde4520f5c..f0891ba24cb1 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2164,12 +2164,12 @@ static inline bool bpf_allow_uninit_stack(void) static inline bool bpf_bypass_spec_v1(void) { - return perfmon_capable() || cpu_mitigations_off(); + return cpu_mitigations_off() || perfmon_capable(); } static inline bool bpf_bypass_spec_v4(void) { - return perfmon_capable() || cpu_mitigations_off(); + return cpu_mitigations_off() || perfmon_capable(); } int bpf_map_new_fd(struct bpf_map *map, int flags); -- cgit v1.2.3