From 577c06af8188d1f6919ef7b62fc1b78fb1b86eb7 Mon Sep 17 00:00:00 2001 From: Ilya Leoshkevich Date: Tue, 19 Sep 2023 12:09:03 +0200 Subject: bpf: Disable zero-extension for BPF_MEMSX On the architectures that use bpf_jit_needs_zext(), e.g., s390x, the verifier incorrectly inserts a zero-extension after BPF_MEMSX, leading to miscompilations like the one below: 24: 89 1a ff fe 00 00 00 00 "r1 = *(s16 *)(r10 - 2);" # zext_dst set 0x3ff7fdb910e: lgh %r2,-2(%r13,%r0) # load halfword 0x3ff7fdb9114: llgfr %r2,%r2 # wrong! 25: 65 10 00 03 00 00 7f ff if r1 s> 32767 goto +3 # check_cond_jmp_op() Disable such zero-extensions. The JITs need to insert sign-extension themselves, if necessary. Suggested-by: Puranjay Mohan Signed-off-by: Ilya Leoshkevich Reviewed-by: Puranjay Mohan Link: https://lore.kernel.org/r/20230919101336.2223655-2-iii@linux.ibm.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/bpf') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 38f8718f1602..eed7350e15f4 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -3114,7 +3114,7 @@ static bool is_reg64(struct bpf_verifier_env *env, struct bpf_insn *insn, if (class == BPF_LDX) { if (t != SRC_OP) - return BPF_SIZE(code) == BPF_DW; + return BPF_SIZE(code) == BPF_DW || BPF_MODE(code) == BPF_MEMSX; /* LDX source must be ptr. */ return true; } -- 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 + kernel/bpf/syscall.c | 14 ++++++++------ kernel/trace/bpf_trace.c | 5 +++-- kernel/trace/trace_kprobe.c | 14 +++++++++++--- tools/include/uapi/linux/bpf.h | 1 + 6 files changed, 28 insertions(+), 13 deletions(-) (limited to 'kernel/bpf') 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 */ diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 85c1d908f70f..6b5280f14a53 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -3374,7 +3374,7 @@ static void bpf_perf_link_dealloc(struct bpf_link *link) static int bpf_perf_link_fill_common(const struct perf_event *event, char __user *uname, u32 ulen, u64 *probe_offset, u64 *probe_addr, - u32 *fd_type) + u32 *fd_type, unsigned long *missed) { const char *buf; u32 prog_id; @@ -3385,7 +3385,7 @@ static int bpf_perf_link_fill_common(const struct perf_event *event, return -EINVAL; err = bpf_get_perf_event_info(event, &prog_id, fd_type, &buf, - probe_offset, probe_addr); + probe_offset, probe_addr, missed); if (err) return err; if (!uname) @@ -3408,6 +3408,7 @@ static int bpf_perf_link_fill_common(const struct perf_event *event, static int bpf_perf_link_fill_kprobe(const struct perf_event *event, struct bpf_link_info *info) { + unsigned long missed; char __user *uname; u64 addr, offset; u32 ulen, type; @@ -3416,7 +3417,7 @@ static int bpf_perf_link_fill_kprobe(const struct perf_event *event, uname = u64_to_user_ptr(info->perf_event.kprobe.func_name); ulen = info->perf_event.kprobe.name_len; err = bpf_perf_link_fill_common(event, uname, ulen, &offset, &addr, - &type); + &type, &missed); if (err) return err; if (type == BPF_FD_TYPE_KRETPROBE) @@ -3425,6 +3426,7 @@ static int bpf_perf_link_fill_kprobe(const struct perf_event *event, info->perf_event.type = BPF_PERF_EVENT_KPROBE; info->perf_event.kprobe.offset = offset; + info->perf_event.kprobe.missed = missed; if (!kallsyms_show_value(current_cred())) addr = 0; info->perf_event.kprobe.addr = addr; @@ -3444,7 +3446,7 @@ static int bpf_perf_link_fill_uprobe(const struct perf_event *event, uname = u64_to_user_ptr(info->perf_event.uprobe.file_name); ulen = info->perf_event.uprobe.name_len; err = bpf_perf_link_fill_common(event, uname, ulen, &offset, &addr, - &type); + &type, NULL); if (err) return err; @@ -3480,7 +3482,7 @@ static int bpf_perf_link_fill_tracepoint(const struct perf_event *event, uname = u64_to_user_ptr(info->perf_event.tracepoint.tp_name); ulen = info->perf_event.tracepoint.name_len; info->perf_event.type = BPF_PERF_EVENT_TRACEPOINT; - return bpf_perf_link_fill_common(event, uname, ulen, NULL, NULL, NULL); + return bpf_perf_link_fill_common(event, uname, ulen, NULL, NULL, NULL, NULL); } static int bpf_perf_link_fill_perf_event(const struct perf_event *event, @@ -4813,7 +4815,7 @@ static int bpf_task_fd_query(const union bpf_attr *attr, err = bpf_get_perf_event_info(event, &prog_id, &fd_type, &buf, &probe_offset, - &probe_addr); + &probe_addr, NULL); if (!err) err = bpf_task_fd_query_copy(attr, uattr, prog_id, fd_type, buf, diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 6aec6e7d612a..f6a7d2524949 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2384,7 +2384,8 @@ int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *prog) 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) { bool is_tracepoint, is_syscall_tp; struct bpf_prog *prog; @@ -2419,7 +2420,7 @@ int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, #ifdef CONFIG_KPROBE_EVENTS if (flags & TRACE_EVENT_FL_KPROBE) err = bpf_get_kprobe_info(event, fd_type, buf, - probe_offset, probe_addr, + probe_offset, probe_addr, missed, event->attr.type == PERF_TYPE_TRACEPOINT); #endif #ifdef CONFIG_UPROBE_EVENTS diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 3d7a180a8427..961a78ffd6d2 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -1189,6 +1189,12 @@ static const struct file_operations kprobe_events_ops = { .write = probes_write, }; +static unsigned long trace_kprobe_missed(struct trace_kprobe *tk) +{ + return trace_kprobe_is_return(tk) ? + tk->rp.kp.nmissed + tk->rp.nmissed : tk->rp.kp.nmissed; +} + /* Probes profiling interfaces */ static int probes_profile_seq_show(struct seq_file *m, void *v) { @@ -1200,8 +1206,7 @@ static int probes_profile_seq_show(struct seq_file *m, void *v) return 0; tk = to_trace_kprobe(ev); - nmissed = trace_kprobe_is_return(tk) ? - tk->rp.kp.nmissed + tk->rp.nmissed : tk->rp.kp.nmissed; + nmissed = trace_kprobe_missed(tk); seq_printf(m, " %-44s %15lu %15lu\n", trace_probe_name(&tk->tp), trace_kprobe_nhit(tk), @@ -1547,7 +1552,8 @@ NOKPROBE_SYMBOL(kretprobe_perf_func); int bpf_get_kprobe_info(const struct perf_event *event, u32 *fd_type, const char **symbol, u64 *probe_offset, - u64 *probe_addr, bool perf_type_tracepoint) + u64 *probe_addr, unsigned long *missed, + bool perf_type_tracepoint) { const char *pevent = trace_event_name(event->tp_event); const char *group = event->tp_event->class->system; @@ -1566,6 +1572,8 @@ int bpf_get_kprobe_info(const struct perf_event *event, u32 *fd_type, *probe_addr = kallsyms_show_value(current_cred()) ? (unsigned long)tk->rp.kp.addr : 0; *symbol = tk->symbol; + if (missed) + *missed = trace_kprobe_missed(tk); return 0; } #endif /* CONFIG_PERF_EVENTS */ diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 1da5b1bcce71..70bfa997e896 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/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 84cb9cbd911a3e06c1ff31572706ba0ee3499b19 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 6 Oct 2023 13:17:00 -0700 Subject: bpf: Annotate struct bpf_stack_map with __counted_by Prepare for the coming implementation by GCC and Clang of the __counted_by attribute. Flexible array members annotated with __counted_by can have their accesses bounds-checked at run-time via CONFIG_UBSAN_BOUNDS (for array indexing) and CONFIG_FORTIFY_SOURCE (for strcpy/memcpy-family functions). As found with Coccinelle [1], add __counted_by for struct bpf_stack_map. Signed-off-by: Kees Cook Signed-off-by: Daniel Borkmann Acked-by: Stanislav Fomichev Link: https://github.com/kees/kernel-tools/blob/trunk/coccinelle/examples/counted_by.cocci [1] Link: https://lore.kernel.org/bpf/20231006201657.work.531-kees@kernel.org --- kernel/bpf/stackmap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/bpf') diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 458bb80b14d5..d6b277482085 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -28,7 +28,7 @@ struct bpf_stack_map { void *elems; struct pcpu_freelist freelist; u32 n_buckets; - struct stack_map_bucket *buckets[]; + struct stack_map_bucket *buckets[] __counted_by(n_buckets); }; static inline bool stack_map_use_build_id(struct bpf_map *map) -- 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 ++++ kernel/bpf/helpers.c | 5 ++++- tools/include/uapi/linux/bpf.h | 4 ++++ 3 files changed, 12 insertions(+), 1 deletion(-) (limited to 'kernel/bpf') 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 */ diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index dd1c69ee3375..d2840dd5b00d 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1272,7 +1272,7 @@ BPF_CALL_3(bpf_timer_start, struct bpf_timer_kern *, timer, u64, nsecs, u64, fla if (in_nmi()) return -EOPNOTSUPP; - if (flags > BPF_F_TIMER_ABS) + if (flags & ~(BPF_F_TIMER_ABS | BPF_F_TIMER_CPU_PIN)) return -EINVAL; __bpf_spin_lock_irqsave(&timer->lock); t = timer->timer; @@ -1286,6 +1286,9 @@ BPF_CALL_3(bpf_timer_start, struct bpf_timer_kern *, timer, u64, nsecs, u64, fla else mode = HRTIMER_MODE_REL_SOFT; + if (flags & BPF_F_TIMER_CPU_PIN) + mode |= HRTIMER_MODE_PINNED; + hrtimer_start(&t->timer, ns_to_ktime(nsecs), mode); out: __bpf_spin_unlock_irqrestore(&timer->lock); diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 70bfa997e896..a7d4a1a69f21 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/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 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 + kernel/bpf/cgroup.c | 17 +++++++++-- net/ipv4/af_inet.c | 7 +++-- net/ipv4/ping.c | 2 +- net/ipv4/tcp_ipv4.c | 2 +- net/ipv4/udp.c | 9 ++++-- net/ipv6/af_inet6.c | 9 +++--- net/ipv6/ping.c | 2 +- net/ipv6/tcp_ipv6.c | 2 +- net/ipv6/udp.c | 6 ++-- 11 files changed, 76 insertions(+), 54 deletions(-) (limited to 'kernel/bpf') 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 { diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 03b3d4492980..ac37bd53aee0 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1450,6 +1450,9 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk); * provided by user sockaddr * @sk: sock struct that will use sockaddr * @uaddr: sockaddr struct provided by user + * @uaddrlen: Pointer to the size of the sockaddr struct provided by user. It is + * read-only for AF_INET[6] uaddr but can be modified for AF_UNIX + * uaddr. * @atype: The type of program to be executed * @t_ctx: Pointer to attach type specific context * @flags: Pointer to u32 which contains higher bits of BPF program @@ -1462,6 +1465,7 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_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) @@ -1473,6 +1477,7 @@ int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, }; struct sockaddr_storage unspec; struct cgroup *cgrp; + int ret; /* Check socket family since not all sockets represent network * endpoint (e.g. AF_UNIX). @@ -1483,11 +1488,19 @@ int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, if (!ctx.uaddr) { memset(&unspec, 0, sizeof(unspec)); ctx.uaddr = (struct sockaddr *)&unspec; + ctx.uaddrlen = 0; + } else { + ctx.uaddrlen = *uaddrlen; } cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); - return bpf_prog_run_array_cg(&cgrp->bpf, atype, &ctx, bpf_prog_run, - 0, flags); + ret = bpf_prog_run_array_cg(&cgrp->bpf, atype, &ctx, bpf_prog_run, + 0, flags); + + if (!ret && uaddr) + *uaddrlen = ctx.uaddrlen; + + return ret; } EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_addr); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 3d2e30e20473..7e27ad37b939 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -452,7 +452,7 @@ int inet_bind_sk(struct sock *sk, struct sockaddr *uaddr, int addr_len) /* BPF prog is run before any checks are done so that if the prog * changes context in a wrong way it will be caught. */ - err = BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, + err = BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, &addr_len, CGROUP_INET4_BIND, &flags); if (err) return err; @@ -788,6 +788,7 @@ int inet_getname(struct socket *sock, struct sockaddr *uaddr, struct sock *sk = sock->sk; struct inet_sock *inet = inet_sk(sk); DECLARE_SOCKADDR(struct sockaddr_in *, sin, uaddr); + int sin_addr_len = sizeof(*sin); sin->sin_family = AF_INET; lock_sock(sk); @@ -800,7 +801,7 @@ int inet_getname(struct socket *sock, struct sockaddr *uaddr, } sin->sin_port = inet->inet_dport; sin->sin_addr.s_addr = inet->inet_daddr; - BPF_CGROUP_RUN_SA_PROG(sk, (struct sockaddr *)sin, + BPF_CGROUP_RUN_SA_PROG(sk, (struct sockaddr *)sin, &sin_addr_len, CGROUP_INET4_GETPEERNAME); } else { __be32 addr = inet->inet_rcv_saddr; @@ -808,7 +809,7 @@ int inet_getname(struct socket *sock, struct sockaddr *uaddr, addr = inet->inet_saddr; sin->sin_port = inet->inet_sport; sin->sin_addr.s_addr = addr; - BPF_CGROUP_RUN_SA_PROG(sk, (struct sockaddr *)sin, + BPF_CGROUP_RUN_SA_PROG(sk, (struct sockaddr *)sin, &sin_addr_len, CGROUP_INET4_GETSOCKNAME); } release_sock(sk); diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 4dd809b7b188..2887177822c9 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -301,7 +301,7 @@ static int ping_pre_connect(struct sock *sk, struct sockaddr *uaddr, if (addr_len < sizeof(struct sockaddr_in)) return -EINVAL; - return BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr); + return BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr, &addr_len); } /* Checks the bind address and possibly modifies sk->sk_bound_dev_if. */ diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index f13eb7e23d03..7c18dd3ce011 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -194,7 +194,7 @@ static int tcp_v4_pre_connect(struct sock *sk, struct sockaddr *uaddr, sock_owned_by_me(sk); - return BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr); + return BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr, &addr_len); } /* This will initiate an outgoing connection. */ diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index c3ff984b6354..7b21a51dd25a 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1143,7 +1143,9 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (cgroup_bpf_enabled(CGROUP_UDP4_SENDMSG) && !connected) { err = BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, - (struct sockaddr *)usin, &ipc.addr); + (struct sockaddr *)usin, + &msg->msg_namelen, + &ipc.addr); if (err) goto out_free; if (usin) { @@ -1865,7 +1867,8 @@ try_again: *addr_len = sizeof(*sin); BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, - (struct sockaddr *)sin); + (struct sockaddr *)sin, + addr_len); } if (udp_test_bit(GRO_ENABLED, sk)) @@ -1904,7 +1907,7 @@ int udp_pre_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (addr_len < sizeof(struct sockaddr_in)) return -EINVAL; - return BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr); + return BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr, &addr_len); } EXPORT_SYMBOL(udp_pre_connect); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 6337fb4504fd..c35d302a3da9 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -454,7 +454,7 @@ int inet6_bind_sk(struct sock *sk, struct sockaddr *uaddr, int addr_len) /* BPF prog is run before any checks are done so that if the prog * changes context in a wrong way it will be caught. */ - err = BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, + err = BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, &addr_len, CGROUP_INET6_BIND, &flags); if (err) return err; @@ -520,6 +520,7 @@ int inet6_getname(struct socket *sock, struct sockaddr *uaddr, int peer) { struct sockaddr_in6 *sin = (struct sockaddr_in6 *)uaddr; + int sin_addr_len = sizeof(*sin); struct sock *sk = sock->sk; struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); @@ -539,7 +540,7 @@ int inet6_getname(struct socket *sock, struct sockaddr *uaddr, sin->sin6_addr = sk->sk_v6_daddr; if (inet6_test_bit(SNDFLOW, sk)) sin->sin6_flowinfo = np->flow_label; - BPF_CGROUP_RUN_SA_PROG(sk, (struct sockaddr *)sin, + BPF_CGROUP_RUN_SA_PROG(sk, (struct sockaddr *)sin, &sin_addr_len, CGROUP_INET6_GETPEERNAME); } else { if (ipv6_addr_any(&sk->sk_v6_rcv_saddr)) @@ -547,13 +548,13 @@ int inet6_getname(struct socket *sock, struct sockaddr *uaddr, else sin->sin6_addr = sk->sk_v6_rcv_saddr; sin->sin6_port = inet->inet_sport; - BPF_CGROUP_RUN_SA_PROG(sk, (struct sockaddr *)sin, + BPF_CGROUP_RUN_SA_PROG(sk, (struct sockaddr *)sin, &sin_addr_len, CGROUP_INET6_GETSOCKNAME); } sin->sin6_scope_id = ipv6_iface_scope_id(&sin->sin6_addr, sk->sk_bound_dev_if); release_sock(sk); - return sizeof(*sin); + return sin_addr_len; } EXPORT_SYMBOL(inet6_getname); diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index e8fb0d275cc2..d2098dd4ceae 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -56,7 +56,7 @@ static int ping_v6_pre_connect(struct sock *sk, struct sockaddr *uaddr, if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; - return BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr); + return BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr, &addr_len); } static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 94afb8d0f2d0..3a1e76a2d33e 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -135,7 +135,7 @@ static int tcp_v6_pre_connect(struct sock *sk, struct sockaddr *uaddr, sock_owned_by_me(sk); - return BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr); + return BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr, &addr_len); } static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 5e9312eefed0..622b10a549f7 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -410,7 +410,8 @@ try_again: *addr_len = sizeof(*sin6); BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, - (struct sockaddr *)sin6); + (struct sockaddr *)sin6, + addr_len); } if (udp_test_bit(GRO_ENABLED, sk)) @@ -1157,7 +1158,7 @@ static int udpv6_pre_connect(struct sock *sk, struct sockaddr *uaddr, if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; - return BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr); + return BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr, &addr_len); } /** @@ -1510,6 +1511,7 @@ do_udp_sendmsg: if (cgroup_bpf_enabled(CGROUP_UDP6_SENDMSG) && !connected) { err = BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, (struct sockaddr *)sin6, + &addr_len, &fl6->saddr); if (err) goto out_no_dst; -- cgit v1.2.3 From 53e380d21441909b12b6e0782b77187ae4b971c4 Mon Sep 17 00:00:00 2001 From: Daan De Meyer Date: Wed, 11 Oct 2023 20:51:05 +0200 Subject: bpf: Add bpf_sock_addr_set_sun_path() to allow writing unix sockaddr from bpf As prep for adding unix socket support to the cgroup sockaddr hooks, let's add a kfunc bpf_sock_addr_set_sun_path() that allows modifying a unix sockaddr from bpf. While this is already possible for AF_INET and AF_INET6, we'll need this kfunc when we add unix socket support since modifying the address for those requires modifying both the address and the sockaddr length. Signed-off-by: Daan De Meyer Link: https://lore.kernel.org/r/20231011185113.140426-4-daan.j.demeyer@gmail.com Signed-off-by: Martin KaFai Lau --- kernel/bpf/btf.c | 1 + net/core/filter.c | 35 ++++++++++++++++++++++++++++++++++- 2 files changed, 35 insertions(+), 1 deletion(-) (limited to 'kernel/bpf') diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 69101200c124..15d71d2986d3 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -7850,6 +7850,7 @@ static int bpf_prog_type_to_kfunc_hook(enum bpf_prog_type prog_type) case BPF_PROG_TYPE_SYSCALL: return BTF_KFUNC_HOOK_SYSCALL; case BPF_PROG_TYPE_CGROUP_SKB: + case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: return BTF_KFUNC_HOOK_CGROUP_SKB; case BPF_PROG_TYPE_SCHED_ACT: return BTF_KFUNC_HOOK_SCHED_ACT; diff --git a/net/core/filter.c b/net/core/filter.c index 3880bf0b740d..ff0bd9f20b95 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -81,6 +81,7 @@ #include #include #include +#include static const struct bpf_func_proto * bpf_sk_base_func_proto(enum bpf_func_id func_id); @@ -11768,6 +11769,27 @@ __bpf_kfunc int bpf_dynptr_from_xdp(struct xdp_buff *xdp, u64 flags, return 0; } + +__bpf_kfunc int bpf_sock_addr_set_sun_path(struct bpf_sock_addr_kern *sa_kern, + const u8 *sun_path, u32 sun_path__sz) +{ + struct sockaddr_un *un; + + if (sa_kern->sk->sk_family != AF_UNIX) + return -EINVAL; + + /* We do not allow changing the address to unnamed or larger than the + * maximum allowed address size for a unix sockaddr. + */ + if (sun_path__sz == 0 || sun_path__sz > UNIX_PATH_MAX) + return -EINVAL; + + un = (struct sockaddr_un *)sa_kern->uaddr; + memcpy(un->sun_path, sun_path, sun_path__sz); + sa_kern->uaddrlen = offsetof(struct sockaddr_un, sun_path) + sun_path__sz; + + return 0; +} __diag_pop(); int bpf_dynptr_from_skb_rdonly(struct sk_buff *skb, u64 flags, @@ -11792,6 +11814,10 @@ BTF_SET8_START(bpf_kfunc_check_set_xdp) BTF_ID_FLAGS(func, bpf_dynptr_from_xdp) BTF_SET8_END(bpf_kfunc_check_set_xdp) +BTF_SET8_START(bpf_kfunc_check_set_sock_addr) +BTF_ID_FLAGS(func, bpf_sock_addr_set_sun_path) +BTF_SET8_END(bpf_kfunc_check_set_sock_addr) + static const struct btf_kfunc_id_set bpf_kfunc_set_skb = { .owner = THIS_MODULE, .set = &bpf_kfunc_check_set_skb, @@ -11802,6 +11828,11 @@ static const struct btf_kfunc_id_set bpf_kfunc_set_xdp = { .set = &bpf_kfunc_check_set_xdp, }; +static const struct btf_kfunc_id_set bpf_kfunc_set_sock_addr = { + .owner = THIS_MODULE, + .set = &bpf_kfunc_check_set_sock_addr, +}; + static int __init bpf_kfunc_init(void) { int ret; @@ -11816,7 +11847,9 @@ static int __init bpf_kfunc_init(void) ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_LWT_XMIT, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_LWT_SEG6LOCAL, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_NETFILTER, &bpf_kfunc_set_skb); - return ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &bpf_kfunc_set_xdp); + ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &bpf_kfunc_set_xdp); + return ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_CGROUP_SOCK_ADDR, + &bpf_kfunc_set_sock_addr); } late_initcall(bpf_kfunc_init); -- 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 +++++++++---- kernel/bpf/cgroup.c | 11 +++++++++-- kernel/bpf/syscall.c | 15 +++++++++++++++ kernel/bpf/verifier.c | 5 ++++- net/core/filter.c | 14 ++++++++++++-- net/unix/af_unix.c | 35 ++++++++++++++++++++++++++++++++++- tools/include/uapi/linux/bpf.h | 13 +++++++++---- 9 files changed, 114 insertions(+), 14 deletions(-) (limited to 'kernel/bpf') 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 diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index ac37bd53aee0..74ad2215e1ba 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1458,7 +1458,7 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk); * @flags: Pointer to u32 which contains higher bits of BPF program * return value (OR'ed together). * - * socket is expected to be of type INET or INET6. + * socket is expected to be of type INET, INET6 or UNIX. * * This function will return %-EPERM if an attached program is found and * returned value != 1 during execution. In all other cases, 0 is returned. @@ -1482,7 +1482,8 @@ int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, /* Check socket family since not all sockets represent network * endpoint (e.g. AF_UNIX). */ - if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6) + if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6 && + sk->sk_family != AF_UNIX) return 0; if (!ctx.uaddr) { @@ -2533,10 +2534,13 @@ cgroup_common_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_CGROUP_SOCK_OPS: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: + case BPF_CGROUP_UNIX_RECVMSG: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: + case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: + case BPF_CGROUP_UNIX_GETSOCKNAME: return NULL; default: return &bpf_get_retval_proto; @@ -2548,10 +2552,13 @@ cgroup_common_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_CGROUP_SOCK_OPS: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: + case BPF_CGROUP_UNIX_RECVMSG: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: + case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: + case BPF_CGROUP_UNIX_GETSOCKNAME: return NULL; default: return &bpf_set_retval_proto; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 6b5280f14a53..8677837f3deb 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2446,14 +2446,19 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type, case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: + case BPF_CGROUP_UNIX_CONNECT: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: + case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: + case BPF_CGROUP_UNIX_GETSOCKNAME: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP6_SENDMSG: + case BPF_CGROUP_UNIX_SENDMSG: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: + case BPF_CGROUP_UNIX_RECVMSG: return 0; default: return -EINVAL; @@ -3678,14 +3683,19 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type) case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: + case BPF_CGROUP_UNIX_CONNECT: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: + case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: + case BPF_CGROUP_UNIX_GETSOCKNAME: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP6_SENDMSG: + case BPF_CGROUP_UNIX_SENDMSG: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: + case BPF_CGROUP_UNIX_RECVMSG: return BPF_PROG_TYPE_CGROUP_SOCK_ADDR; case BPF_CGROUP_SOCK_OPS: return BPF_PROG_TYPE_SOCK_OPS; @@ -3942,14 +3952,19 @@ static int bpf_prog_query(const union bpf_attr *attr, case BPF_CGROUP_INET6_POST_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: + case BPF_CGROUP_UNIX_CONNECT: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: + case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: + case BPF_CGROUP_UNIX_GETSOCKNAME: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP6_SENDMSG: + case BPF_CGROUP_UNIX_SENDMSG: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: + case BPF_CGROUP_UNIX_RECVMSG: case BPF_CGROUP_SOCK_OPS: case BPF_CGROUP_DEVICE: case BPF_CGROUP_SYSCTL: diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index eed7350e15f4..e777f50401b6 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -14797,10 +14797,13 @@ static int check_return_code(struct bpf_verifier_env *env, int regno) case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: if (env->prog->expected_attach_type == BPF_CGROUP_UDP4_RECVMSG || env->prog->expected_attach_type == BPF_CGROUP_UDP6_RECVMSG || + env->prog->expected_attach_type == BPF_CGROUP_UNIX_RECVMSG || env->prog->expected_attach_type == BPF_CGROUP_INET4_GETPEERNAME || env->prog->expected_attach_type == BPF_CGROUP_INET6_GETPEERNAME || + env->prog->expected_attach_type == BPF_CGROUP_UNIX_GETPEERNAME || env->prog->expected_attach_type == BPF_CGROUP_INET4_GETSOCKNAME || - env->prog->expected_attach_type == BPF_CGROUP_INET6_GETSOCKNAME) + env->prog->expected_attach_type == BPF_CGROUP_INET6_GETSOCKNAME || + env->prog->expected_attach_type == BPF_CGROUP_UNIX_GETSOCKNAME) range = tnum_range(1, 1); if (env->prog->expected_attach_type == BPF_CGROUP_INET4_BIND || env->prog->expected_attach_type == BPF_CGROUP_INET6_BIND) diff --git a/net/core/filter.c b/net/core/filter.c index ff0bd9f20b95..cc2e4babc85f 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -7875,14 +7875,19 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: + case BPF_CGROUP_UNIX_CONNECT: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: + case BPF_CGROUP_UNIX_RECVMSG: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP6_SENDMSG: + case BPF_CGROUP_UNIX_SENDMSG: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: + case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: + case BPF_CGROUP_UNIX_GETSOCKNAME: return &bpf_sock_addr_setsockopt_proto; default: return NULL; @@ -7893,14 +7898,19 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: + case BPF_CGROUP_UNIX_CONNECT: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: + case BPF_CGROUP_UNIX_RECVMSG: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP6_SENDMSG: + case BPF_CGROUP_UNIX_SENDMSG: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: + case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: + case BPF_CGROUP_UNIX_GETSOCKNAME: return &bpf_sock_addr_getsockopt_proto; default: return NULL; @@ -8948,8 +8958,8 @@ static bool sock_addr_is_valid_access(int off, int size, if (off % size != 0) return false; - /* Disallow access to IPv6 fields from IPv4 contex and vise - * versa. + /* Disallow access to fields not belonging to the attach type's address + * family. */ switch (off) { case bpf_ctx_range(struct bpf_sock_addr, user_ip4): diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 3e8a04a13668..e10d07c76044 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -116,6 +116,7 @@ #include #include #include +#include #include "scm.h" @@ -1381,6 +1382,10 @@ static int unix_dgram_connect(struct socket *sock, struct sockaddr *addr, if (err) goto out; + err = BPF_CGROUP_RUN_PROG_UNIX_CONNECT_LOCK(sk, addr, &alen); + if (err) + goto out; + if ((test_bit(SOCK_PASSCRED, &sock->flags) || test_bit(SOCK_PASSPIDFD, &sock->flags)) && !unix_sk(sk)->addr) { @@ -1490,6 +1495,10 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr, if (err) goto out; + err = BPF_CGROUP_RUN_PROG_UNIX_CONNECT_LOCK(sk, uaddr, &addr_len); + if (err) + goto out; + if ((test_bit(SOCK_PASSCRED, &sock->flags) || test_bit(SOCK_PASSPIDFD, &sock->flags)) && !u->addr) { err = unix_autobind(sk); @@ -1770,6 +1779,13 @@ static int unix_getname(struct socket *sock, struct sockaddr *uaddr, int peer) } else { err = addr->len; memcpy(sunaddr, addr->name, addr->len); + + if (peer) + BPF_CGROUP_RUN_SA_PROG(sk, uaddr, &err, + CGROUP_UNIX_GETPEERNAME); + else + BPF_CGROUP_RUN_SA_PROG(sk, uaddr, &err, + CGROUP_UNIX_GETSOCKNAME); } sock_put(sk); out: @@ -1922,6 +1938,13 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg, err = unix_validate_addr(sunaddr, msg->msg_namelen); if (err) goto out; + + err = BPF_CGROUP_RUN_PROG_UNIX_SENDMSG_LOCK(sk, + msg->msg_name, + &msg->msg_namelen, + NULL); + if (err) + goto out; } else { sunaddr = NULL; err = -ENOTCONN; @@ -2390,9 +2413,14 @@ int __unix_dgram_recvmsg(struct sock *sk, struct msghdr *msg, size_t size, EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND); - if (msg->msg_name) + if (msg->msg_name) { unix_copy_addr(msg, skb->sk); + BPF_CGROUP_RUN_PROG_UNIX_RECVMSG_LOCK(sk, + msg->msg_name, + &msg->msg_namelen); + } + if (size > skb->len - skip) size = skb->len - skip; else if (size < skb->len - skip) @@ -2744,6 +2772,11 @@ unlock: DECLARE_SOCKADDR(struct sockaddr_un *, sunaddr, state->msg->msg_name); unix_copy_addr(state->msg, skb->sk); + + BPF_CGROUP_RUN_PROG_UNIX_RECVMSG_LOCK(sk, + state->msg->msg_name, + &state->msg->msg_namelen); + sunaddr = NULL; } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index e0aa457f94a9..7ba61b75bc0e 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/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 f10ca5da5bd71e5cefed7995e75a7c873ce3816e Mon Sep 17 00:00:00 2001 From: Dave Marchevsky Date: Fri, 13 Oct 2023 13:44:22 -0700 Subject: bpf: Don't explicitly emit BTF for struct btf_iter_num Commit 6018e1f407cc ("bpf: implement numbers iterator") added the BTF_TYPE_EMIT line that this patch is modifying. The struct btf_iter_num doesn't exist, so only a forward declaration is emitted in BTF: FWD 'btf_iter_num' fwd_kind=struct That commit was probably hoping to ensure that struct bpf_iter_num is emitted in vmlinux BTF. A previous version of this patch changed the line to emit the correct type, but Yonghong confirmed that it would definitely be emitted regardless in [0], so this patch simply removes the line. This isn't marked "Fixes" because the extraneous btf_iter_num FWD wasn't causing any issues that I noticed, aside from mild confusion when I looked through the code. [0]: https://lore.kernel.org/bpf/25d08207-43e6-36a8-5e0f-47a913d4cda5@linux.dev/ Signed-off-by: Dave Marchevsky Signed-off-by: Andrii Nakryiko Acked-by: Yonghong Song Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20231013204426.1074286-2-davemarchevsky@fb.com --- kernel/bpf/bpf_iter.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'kernel/bpf') diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c index 96856f130cbf..833faa04461b 100644 --- a/kernel/bpf/bpf_iter.c +++ b/kernel/bpf/bpf_iter.c @@ -793,8 +793,6 @@ __bpf_kfunc int bpf_iter_num_new(struct bpf_iter_num *it, int start, int end) BUILD_BUG_ON(sizeof(struct bpf_iter_num_kern) != sizeof(struct bpf_iter_num)); BUILD_BUG_ON(__alignof__(struct bpf_iter_num_kern) != __alignof__(struct bpf_iter_num)); - BTF_TYPE_EMIT(struct btf_iter_num); - /* start == end is legit, it's an empty range and we'll just get NULL * on first (and any subsequent) bpf_iter_num_next() call */ -- cgit v1.2.3 From 4ac4546821584736798aaa9e97da9f6eaf689ea3 Mon Sep 17 00:00:00 2001 From: Dave Marchevsky Date: Fri, 13 Oct 2023 13:44:24 -0700 Subject: bpf: Introduce task_vma open-coded iterator kfuncs This patch adds kfuncs bpf_iter_task_vma_{new,next,destroy} which allow creation and manipulation of struct bpf_iter_task_vma in open-coded iterator style. BPF programs can use these kfuncs directly or through bpf_for_each macro for natural-looking iteration of all task vmas. The implementation borrows heavily from bpf_find_vma helper's locking - differing only in that it holds the mmap_read lock for all iterations while the helper only executes its provided callback on a maximum of 1 vma. Aside from locking, struct vma_iterator and vma_next do all the heavy lifting. A pointer to an inner data struct, struct bpf_iter_task_vma_data, is the only field in struct bpf_iter_task_vma. This is because the inner data struct contains a struct vma_iterator (not ptr), whose size is likely to change under us. If bpf_iter_task_vma_kern contained vma_iterator directly such a change would require change in opaque bpf_iter_task_vma struct's size. So better to allocate vma_iterator using BPF allocator, and since that alloc must already succeed, might as well allocate all iter fields, thereby freezing struct bpf_iter_task_vma size. Signed-off-by: Dave Marchevsky Signed-off-by: Andrii Nakryiko Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20231013204426.1074286-4-davemarchevsky@fb.com --- kernel/bpf/helpers.c | 3 ++ kernel/bpf/task_iter.c | 91 ++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 94 insertions(+) (limited to 'kernel/bpf') diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index d2840dd5b00d..62a53ebfedf9 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -2552,6 +2552,9 @@ BTF_ID_FLAGS(func, bpf_dynptr_slice_rdwr, KF_RET_NULL) BTF_ID_FLAGS(func, bpf_iter_num_new, KF_ITER_NEW) BTF_ID_FLAGS(func, bpf_iter_num_next, KF_ITER_NEXT | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_iter_num_destroy, KF_ITER_DESTROY) +BTF_ID_FLAGS(func, bpf_iter_task_vma_new, KF_ITER_NEW | KF_RCU) +BTF_ID_FLAGS(func, bpf_iter_task_vma_next, KF_ITER_NEXT | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_iter_task_vma_destroy, KF_ITER_DESTROY) BTF_ID_FLAGS(func, bpf_dynptr_adjust) BTF_ID_FLAGS(func, bpf_dynptr_is_null) BTF_ID_FLAGS(func, bpf_dynptr_is_rdonly) diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c index 7473068ed313..fef17628341f 100644 --- a/kernel/bpf/task_iter.c +++ b/kernel/bpf/task_iter.c @@ -7,7 +7,9 @@ #include #include #include +#include #include +#include #include "mmap_unlock_work.h" static const char * const iter_task_type_names[] = { @@ -803,6 +805,95 @@ const struct bpf_func_proto bpf_find_vma_proto = { .arg5_type = ARG_ANYTHING, }; +struct bpf_iter_task_vma_kern_data { + struct task_struct *task; + struct mm_struct *mm; + struct mmap_unlock_irq_work *work; + struct vma_iterator vmi; +}; + +struct bpf_iter_task_vma { + /* opaque iterator state; having __u64 here allows to preserve correct + * alignment requirements in vmlinux.h, generated from BTF + */ + __u64 __opaque[1]; +} __attribute__((aligned(8))); + +/* Non-opaque version of bpf_iter_task_vma */ +struct bpf_iter_task_vma_kern { + struct bpf_iter_task_vma_kern_data *data; +} __attribute__((aligned(8))); + +__diag_push(); +__diag_ignore_all("-Wmissing-prototypes", + "Global functions as their definitions will be in vmlinux BTF"); + +__bpf_kfunc int bpf_iter_task_vma_new(struct bpf_iter_task_vma *it, + struct task_struct *task, u64 addr) +{ + struct bpf_iter_task_vma_kern *kit = (void *)it; + bool irq_work_busy = false; + int err; + + BUILD_BUG_ON(sizeof(struct bpf_iter_task_vma_kern) != sizeof(struct bpf_iter_task_vma)); + BUILD_BUG_ON(__alignof__(struct bpf_iter_task_vma_kern) != __alignof__(struct bpf_iter_task_vma)); + + /* is_iter_reg_valid_uninit guarantees that kit hasn't been initialized + * before, so non-NULL kit->data doesn't point to previously + * bpf_mem_alloc'd bpf_iter_task_vma_kern_data + */ + kit->data = bpf_mem_alloc(&bpf_global_ma, sizeof(struct bpf_iter_task_vma_kern_data)); + if (!kit->data) + return -ENOMEM; + + kit->data->task = get_task_struct(task); + kit->data->mm = task->mm; + if (!kit->data->mm) { + err = -ENOENT; + goto err_cleanup_iter; + } + + /* kit->data->work == NULL is valid after bpf_mmap_unlock_get_irq_work */ + irq_work_busy = bpf_mmap_unlock_get_irq_work(&kit->data->work); + if (irq_work_busy || !mmap_read_trylock(kit->data->mm)) { + err = -EBUSY; + goto err_cleanup_iter; + } + + vma_iter_init(&kit->data->vmi, kit->data->mm, addr); + return 0; + +err_cleanup_iter: + if (kit->data->task) + put_task_struct(kit->data->task); + bpf_mem_free(&bpf_global_ma, kit->data); + /* NULL kit->data signals failed bpf_iter_task_vma initialization */ + kit->data = NULL; + return err; +} + +__bpf_kfunc struct vm_area_struct *bpf_iter_task_vma_next(struct bpf_iter_task_vma *it) +{ + struct bpf_iter_task_vma_kern *kit = (void *)it; + + if (!kit->data) /* bpf_iter_task_vma_new failed */ + return NULL; + return vma_next(&kit->data->vmi); +} + +__bpf_kfunc void bpf_iter_task_vma_destroy(struct bpf_iter_task_vma *it) +{ + struct bpf_iter_task_vma_kern *kit = (void *)it; + + if (kit->data) { + bpf_mmap_unlock_mm(kit->data->work, kit->data->mm); + put_task_struct(kit->data->task); + bpf_mem_free(&bpf_global_ma, kit->data); + } +} + +__diag_pop(); + DEFINE_PER_CPU(struct mmap_unlock_irq_work, mmap_unlock_work); static void do_mmap_read_unlock(struct irq_work *entry) -- cgit v1.2.3 From 72f8a1de4a7ecb23393a920dface58d5a96f42d8 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Wed, 11 Oct 2023 15:37:27 -0700 Subject: bpf: Disambiguate SCALAR register state output in verifier logs Currently the way that verifier prints SCALAR_VALUE register state (and PTR_TO_PACKET, which can have var_off and ranges info as well) is very ambiguous. In the name of brevity we are trying to eliminate "unnecessary" output of umin/umax, smin/smax, u32_min/u32_max, and s32_min/s32_max values, if possible. Current rules are that if any of those have their default value (which for mins is the minimal value of its respective types: 0, S32_MIN, or S64_MIN, while for maxs it's U32_MAX, S32_MAX, S64_MAX, or U64_MAX) *OR* if there is another min/max value that as matching value. E.g., if smin=100 and umin=100, we'll emit only umin=10, omitting smin altogether. This approach has a few problems, being both ambiguous and sort-of incorrect in some cases. Ambiguity is due to missing value could be either default value or value of umin/umax or smin/smax. This is especially confusing when we mix signed and unsigned ranges. Quite often, umin=0 and smin=0, and so we'll have only `umin=0` leaving anyone reading verifier log to guess whether smin is actually 0 or it's actually -9223372036854775808 (S64_MIN). And often times it's important to know, especially when debugging tricky issues. "Sort-of incorrectness" comes from mixing negative and positive values. E.g., if umin is some large positive number, it can be equal to smin which is, interpreted as signed value, is actually some negative value. Currently, that smin will be omitted and only umin will be emitted with a large positive value, giving an impression that smin is also positive. Anyway, ambiguity is the biggest issue making it impossible to have an exact understanding of register state, preventing any sort of automated testing of verifier state based on verifier log. This patch is attempting to rectify the situation by removing ambiguity, while minimizing the verboseness of register state output. The rules are straightforward: - if some of the values are missing, then it definitely has a default value. I.e., `umin=0` means that umin is zero, but smin is actually S64_MIN; - all the various boundaries that happen to have the same value are emitted in one equality separated sequence. E.g., if umin and smin are both 100, we'll emit `smin=umin=100`, making this explicit; - we do not mix negative and positive values together, and even if they happen to have the same bit-level value, they will be emitted separately with proper sign. I.e., if both umax and smax happen to be 0xffffffffffffffff, we'll emit them both separately as `smax=-1,umax=18446744073709551615`; - in the name of a bit more uniformity and consistency, {u32,s32}_{min,max} are renamed to {s,u}{min,max}32, which seems to improve readability. The above means that in case of all 4 ranges being, say, [50, 100] range, we'd previously see hugely ambiguous: R1=scalar(umin=50,umax=100) Now, we'll be more explicit: R1=scalar(smin=umin=smin32=umin32=50,smax=umax=smax32=umax32=100) This is slightly more verbose, but distinct from the case when we don't know anything about signed boundaries and 32-bit boundaries, which under new rules will match the old case: R1=scalar(umin=50,umax=100) Also, in the name of simplicity of implementation and consistency, order for {s,u}32_{min,max} are emitted *before* var_off. Previously they were emitted afterwards, for unclear reasons. This patch also includes a few fixes to selftests that expect exact register state to accommodate slight changes to verifier format. You can see that the changes are pretty minimal in common cases. Note, the special case when SCALAR_VALUE register is a known constant isn't changed, we'll emit constant value once, interpreted as signed value. Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Acked-by: John Fastabend Acked-by: Eduard Zingerman Link: https://lore.kernel.org/bpf/20231011223728.3188086-5-andrii@kernel.org --- kernel/bpf/verifier.c | 67 +++++++++++++++------- .../selftests/bpf/progs/exceptions_assert.c | 18 +++--- tools/testing/selftests/bpf/progs/verifier_ldsx.c | 2 +- 3 files changed, 55 insertions(+), 32 deletions(-) (limited to 'kernel/bpf') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index e777f50401b6..82ae14f32a01 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1342,6 +1342,50 @@ static void scrub_spilled_slot(u8 *stype) *stype = STACK_MISC; } +static void print_scalar_ranges(struct bpf_verifier_env *env, + const struct bpf_reg_state *reg, + const char **sep) +{ + struct { + const char *name; + u64 val; + bool omit; + } minmaxs[] = { + {"smin", reg->smin_value, reg->smin_value == S64_MIN}, + {"smax", reg->smax_value, reg->smax_value == S64_MAX}, + {"umin", reg->umin_value, reg->umin_value == 0}, + {"umax", reg->umax_value, reg->umax_value == U64_MAX}, + {"smin32", (s64)reg->s32_min_value, reg->s32_min_value == S32_MIN}, + {"smax32", (s64)reg->s32_max_value, reg->s32_max_value == S32_MAX}, + {"umin32", reg->u32_min_value, reg->u32_min_value == 0}, + {"umax32", reg->u32_max_value, reg->u32_max_value == U32_MAX}, + }, *m1, *m2, *mend = &minmaxs[ARRAY_SIZE(minmaxs)]; + bool neg1, neg2; + + for (m1 = &minmaxs[0]; m1 < mend; m1++) { + if (m1->omit) + continue; + + neg1 = m1->name[0] == 's' && (s64)m1->val < 0; + + verbose(env, "%s%s=", *sep, m1->name); + *sep = ","; + + for (m2 = m1 + 2; m2 < mend; m2 += 2) { + if (m2->omit || m2->val != m1->val) + continue; + /* don't mix negatives with positives */ + neg2 = m2->name[0] == 's' && (s64)m2->val < 0; + if (neg2 != neg1) + continue; + m2->omit = true; + verbose(env, "%s=", m2->name); + } + + verbose(env, m1->name[0] == 's' ? "%lld" : "%llu", m1->val); + } +} + static void print_verifier_state(struct bpf_verifier_env *env, const struct bpf_func_state *state, bool print_all) @@ -1405,34 +1449,13 @@ static void print_verifier_state(struct bpf_verifier_env *env, */ verbose_a("imm=%llx", reg->var_off.value); } else { - if (reg->smin_value != reg->umin_value && - reg->smin_value != S64_MIN) - verbose_a("smin=%lld", (long long)reg->smin_value); - if (reg->smax_value != reg->umax_value && - reg->smax_value != S64_MAX) - verbose_a("smax=%lld", (long long)reg->smax_value); - if (reg->umin_value != 0) - verbose_a("umin=%llu", (unsigned long long)reg->umin_value); - if (reg->umax_value != U64_MAX) - verbose_a("umax=%llu", (unsigned long long)reg->umax_value); + print_scalar_ranges(env, reg, &sep); if (!tnum_is_unknown(reg->var_off)) { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose_a("var_off=%s", tn_buf); } - if (reg->s32_min_value != reg->smin_value && - reg->s32_min_value != S32_MIN) - verbose_a("s32_min=%d", (int)(reg->s32_min_value)); - if (reg->s32_max_value != reg->smax_value && - reg->s32_max_value != S32_MAX) - verbose_a("s32_max=%d", (int)(reg->s32_max_value)); - if (reg->u32_min_value != reg->umin_value && - reg->u32_min_value != U32_MIN) - verbose_a("u32_min=%d", (int)(reg->u32_min_value)); - if (reg->u32_max_value != reg->umax_value && - reg->u32_max_value != U32_MAX) - verbose_a("u32_max=%d", (int)(reg->u32_max_value)); } #undef verbose_a diff --git a/tools/testing/selftests/bpf/progs/exceptions_assert.c b/tools/testing/selftests/bpf/progs/exceptions_assert.c index fa35832e6748..e1e5c54a6a11 100644 --- a/tools/testing/selftests/bpf/progs/exceptions_assert.c +++ b/tools/testing/selftests/bpf/progs/exceptions_assert.c @@ -31,35 +31,35 @@ check_assert(s64, eq, llong_max, LLONG_MAX); __msg(": R0_w=scalar(smax=2147483646) R10=fp0") check_assert(s64, lt, pos, INT_MAX); -__msg(": R0_w=scalar(umin=9223372036854775808,var_off=(0x8000000000000000; 0x7fffffffffffffff))") +__msg(": R0_w=scalar(smax=-1,umin=9223372036854775808,var_off=(0x8000000000000000; 0x7fffffffffffffff))") check_assert(s64, lt, zero, 0); -__msg(": R0_w=scalar(umin=9223372036854775808,umax=18446744071562067967,var_off=(0x8000000000000000; 0x7fffffffffffffff))") +__msg(": R0_w=scalar(smax=-2147483649,umin=9223372036854775808,umax=18446744071562067967,var_off=(0x8000000000000000; 0x7fffffffffffffff))") check_assert(s64, lt, neg, INT_MIN); __msg(": R0_w=scalar(smax=2147483647) R10=fp0") check_assert(s64, le, pos, INT_MAX); __msg(": R0_w=scalar(smax=0) R10=fp0") check_assert(s64, le, zero, 0); -__msg(": R0_w=scalar(umin=9223372036854775808,umax=18446744071562067968,var_off=(0x8000000000000000; 0x7fffffffffffffff))") +__msg(": R0_w=scalar(smax=-2147483648,umin=9223372036854775808,umax=18446744071562067968,var_off=(0x8000000000000000; 0x7fffffffffffffff))") check_assert(s64, le, neg, INT_MIN); -__msg(": R0_w=scalar(umin=2147483648,umax=9223372036854775807,var_off=(0x0; 0x7fffffffffffffff))") +__msg(": R0_w=scalar(smin=umin=2147483648,umax=9223372036854775807,var_off=(0x0; 0x7fffffffffffffff))") check_assert(s64, gt, pos, INT_MAX); -__msg(": R0_w=scalar(umin=1,umax=9223372036854775807,var_off=(0x0; 0x7fffffffffffffff))") +__msg(": R0_w=scalar(smin=umin=1,umax=9223372036854775807,var_off=(0x0; 0x7fffffffffffffff))") check_assert(s64, gt, zero, 0); __msg(": R0_w=scalar(smin=-2147483647) R10=fp0") check_assert(s64, gt, neg, INT_MIN); -__msg(": R0_w=scalar(umin=2147483647,umax=9223372036854775807,var_off=(0x0; 0x7fffffffffffffff))") +__msg(": R0_w=scalar(smin=umin=2147483647,umax=9223372036854775807,var_off=(0x0; 0x7fffffffffffffff))") check_assert(s64, ge, pos, INT_MAX); -__msg(": R0_w=scalar(umax=9223372036854775807,var_off=(0x0; 0x7fffffffffffffff)) R10=fp0") +__msg(": R0_w=scalar(smin=0,umax=9223372036854775807,var_off=(0x0; 0x7fffffffffffffff)) R10=fp0") check_assert(s64, ge, zero, 0); __msg(": R0_w=scalar(smin=-2147483648) R10=fp0") check_assert(s64, ge, neg, INT_MIN); SEC("?tc") __log_level(2) __failure -__msg(": R0=0 R1=ctx(off=0,imm=0) R2=scalar(smin=-2147483646,smax=2147483645) R10=fp0") +__msg(": R0=0 R1=ctx(off=0,imm=0) R2=scalar(smin=smin32=-2147483646,smax=smax32=2147483645) R10=fp0") int check_assert_range_s64(struct __sk_buff *ctx) { struct bpf_sock *sk = ctx->sk; @@ -75,7 +75,7 @@ int check_assert_range_s64(struct __sk_buff *ctx) SEC("?tc") __log_level(2) __failure -__msg(": R1=ctx(off=0,imm=0) R2=scalar(umin=4096,umax=8192,var_off=(0x0; 0x3fff))") +__msg(": R1=ctx(off=0,imm=0) R2=scalar(smin=umin=smin32=umin32=4096,smax=umax=smax32=umax32=8192,var_off=(0x0; 0x3fff))") int check_assert_range_u64(struct __sk_buff *ctx) { u64 num = ctx->len; diff --git a/tools/testing/selftests/bpf/progs/verifier_ldsx.c b/tools/testing/selftests/bpf/progs/verifier_ldsx.c index f90016a57eec..375525329637 100644 --- a/tools/testing/selftests/bpf/progs/verifier_ldsx.c +++ b/tools/testing/selftests/bpf/progs/verifier_ldsx.c @@ -64,7 +64,7 @@ __naked void ldsx_s32(void) SEC("socket") __description("LDSX, S8 range checking, privileged") __log_level(2) __success __retval(1) -__msg("R1_w=scalar(smin=-128,smax=127)") +__msg("R1_w=scalar(smin=smin32=-128,smax=smax32=127)") __naked void ldsx_s8_range_priv(void) { asm volatile ( -- cgit v1.2.3 From 1a8a315f008a58f54fecb012b928aa6a494435b3 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Wed, 11 Oct 2023 15:37:28 -0700 Subject: bpf: Ensure proper register state printing for cond jumps Verifier emits relevant register state involved in any given instruction next to it after `;` to the right, if possible. Or, worst case, on the separate line repeating instruction index. E.g., a nice and simple case would be: 2: (d5) if r0 s<= 0x0 goto pc+1 ; R0_w=0 But if there is some intervening extra output (e.g., precision backtracking log) involved, we are supposed to see the state after the precision backtrack log: 4: (75) if r0 s>= 0x0 goto pc+1 mark_precise: frame0: last_idx 4 first_idx 0 subseq_idx -1 mark_precise: frame0: regs=r0 stack= before 2: (d5) if r0 s<= 0x0 goto pc+1 mark_precise: frame0: regs=r0 stack= before 1: (b7) r0 = 0 6: R0_w=0 First off, note that in `6: R0_w=0` instruction index corresponds to the next instruction, not to the conditional jump instruction itself, which is wrong and we'll get to that. But besides that, the above is a happy case that does work today. Yet, if it so happens that precision backtracking had to traverse some of the parent states, this `6: R0_w=0` state output would be missing. This is due to a quirk of print_verifier_state() routine, which performs mark_verifier_state_clean(env) at the end. This marks all registers as "non-scratched", which means that subsequent logic to print *relevant* registers (that is, "scratched ones") fails and doesn't see anything relevant to print and skips the output altogether. print_verifier_state() is used both to print instruction context, but also to print an **entire** verifier state indiscriminately, e.g., during precision backtracking (and in a few other situations, like during entering or exiting subprogram). Which means if we have to print entire parent state before getting to printing instruction context state, instruction context is marked as clean and is omitted. Long story short, this is definitely not intentional. So we fix this behavior in this patch by teaching print_verifier_state() to clear scratch state only if it was used to print instruction state, not the parent/callback state. This is determined by print_all option, so if it's not set, we don't clear scratch state. This fixes missing instruction state for these cases. As for the mismatched instruction index, we fix that by making sure we call print_insn_state() early inside check_cond_jmp_op() before we adjusted insn_idx based on jump branch taken logic. And with that we get desired correct information: 9: (16) if w4 == 0x1 goto pc+9 mark_precise: frame0: last_idx 9 first_idx 9 subseq_idx -1 mark_precise: frame0: parent state regs=r4 stack=: R2_w=1944 R4_rw=P1 R10=fp0 mark_precise: frame0: last_idx 8 first_idx 0 subseq_idx 9 mark_precise: frame0: regs=r4 stack= before 8: (66) if w4 s> 0x3 goto pc+5 mark_precise: frame0: regs=r4 stack= before 7: (b7) r4 = 1 9: R4=1 Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Acked-by: John Fastabend Acked-by: Eduard Zingerman Link: https://lore.kernel.org/bpf/20231011223728.3188086-6-andrii@kernel.org --- kernel/bpf/verifier.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'kernel/bpf') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 82ae14f32a01..6d543a129406 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1539,7 +1539,8 @@ static void print_verifier_state(struct bpf_verifier_env *env, if (state->in_async_callback_fn) verbose(env, " async_cb"); verbose(env, "\n"); - mark_verifier_state_clean(env); + if (!print_all) + mark_verifier_state_clean(env); } static inline u32 vlog_alignment(u32 pos) @@ -14408,6 +14409,8 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, !sanitize_speculative_path(env, insn, *insn_idx + 1, *insn_idx)) return -EFAULT; + if (env->log.level & BPF_LOG_LEVEL) + print_insn_state(env, this_branch->frame[this_branch->curframe]); *insn_idx += insn->off; return 0; } else if (pred == 0) { @@ -14420,6 +14423,8 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, *insn_idx + insn->off + 1, *insn_idx)) return -EFAULT; + if (env->log.level & BPF_LOG_LEVEL) + print_insn_state(env, this_branch->frame[this_branch->curframe]); return 0; } -- cgit v1.2.3