diff --git a/include/linux/bpf_sched.h b/include/linux/bpf_sched.h new file mode 100644 index 0000000000000000000000000000000000000000..874393e6a6aa3f36780e6f3e6f407acfd6ce860c --- /dev/null +++ b/include/linux/bpf_sched.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_BPF_SCHED_H +#define _LINUX_BPF_SCHED_H + +#include + +#ifdef CONFIG_BPF_SCHED + +#define BPF_SCHED_HOOK(RET, DEFAULT, NAME, ...) \ + RET bpf_sched_##NAME(__VA_ARGS__); +#include +#undef BPF_SCHED_HOOK + +int bpf_sched_verify_prog(struct bpf_verifier_log *vlog, + const struct bpf_prog *prog); + +#else /* !CONFIG_BPF_SCHED */ + +static inline int bpf_sched_verify_prog(struct bpf_verifier_log *vlog, + const struct bpf_prog *prog) +{ + return -EOPNOTSUPP; +} + +#endif /* CONFIG_BPF_SCHED */ +#endif /* _LINUX_BPF_SCHED_H */ diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index a8137bb6dd3c223e42426c3b6d6442af0d63c762..5732b485c53991f6c92322cd0a788e83d08b2349 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -77,6 +77,10 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_LSM, lsm, void *, void *) #endif /* CONFIG_BPF_LSM */ #endif +#ifdef CONFIG_BPF_SCHED +BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED, bpf_sched, + void *, void *) +#endif /* CONFIG_BPF_SCHED */ BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY, array_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_ARRAY, percpu_array_map_ops) diff --git a/include/linux/sched_hook_defs.h b/include/linux/sched_hook_defs.h new file mode 100644 index 0000000000000000000000000000000000000000..14344004e3353ef36994d9b2a2e27961d8a7f41a --- /dev/null +++ b/include/linux/sched_hook_defs.h @@ -0,0 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +BPF_SCHED_HOOK(int, 0, dummy, void) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 8fae845d80e260f59a1729c8b1d4364a0fdc80fc..4f8f3f2113a76edd9b0cd16147f751acf4a4ef28 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -199,6 +199,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_EXT, BPF_PROG_TYPE_LSM, BPF_PROG_TYPE_SK_LOOKUP, + BPF_PROG_TYPE_SCHED, }; enum bpf_attach_type { @@ -240,6 +241,7 @@ enum bpf_attach_type { BPF_XDP_CPUMAP, BPF_SK_LOOKUP, BPF_XDP, + BPF_SCHED, __MAX_BPF_ATTACH_TYPE }; diff --git a/init/Kconfig b/init/Kconfig index 0ac3206686dbb4be00f8dbca108d154b45180541..0935a7d84a26d46f87186b295f5b56ede49af499 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1758,6 +1758,16 @@ config BPF_LSM If you are unsure how to answer this question, answer N. +config BPF_SCHED + bool "SCHED Instrumentation with BPF" + depends on BPF_EVENTS + depends on BPF_SYSCALL + help + Enables instrumentation of the sched hooks with eBPF programs for + implementing dynamic scheduling policies. + + If you are unsure how to answer this question, answer N. + config BPF_SYSCALL bool "Enable bpf() system call" select BPF diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index fba28f17e61aa7b353cb8d42b3fef9eae740c0d3..9a0a9895ec62ad071a319eeb0e72aa16433e4dd8 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -4479,6 +4479,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, return true; t = btf_type_by_id(btf, t->type); break; + case BPF_SCHED: case BPF_MODIFY_RETURN: /* For now the BPF_MODIFY_RETURN can only be attached to * functions that return an int. diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 419dbc3d060ee1fea6835a59291bf36b9c570d7e..ff65862ae5ce3100bb8e2461e8c9d5d1807fdfbd 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1997,6 +1997,7 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type, case BPF_PROG_TYPE_LSM: case BPF_PROG_TYPE_STRUCT_OPS: case BPF_PROG_TYPE_EXT: + case BPF_PROG_TYPE_SCHED: break; default: return -EINVAL; @@ -2108,6 +2109,7 @@ static bool is_perfmon_prog_type(enum bpf_prog_type prog_type) case BPF_PROG_TYPE_LSM: case BPF_PROG_TYPE_STRUCT_OPS: /* has access to struct sock */ case BPF_PROG_TYPE_EXT: /* extends any prog */ + case BPF_PROG_TYPE_SCHED: return true; default: return false; @@ -2608,6 +2610,12 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog, goto out_put_prog; } break; + case BPF_PROG_TYPE_SCHED: + if (prog->expected_attach_type != BPF_SCHED) { + err = -EINVAL; + goto out_put_prog; + } + break; default: err = -EINVAL; goto out_put_prog; @@ -2838,6 +2846,7 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr) case BPF_PROG_TYPE_TRACING: case BPF_PROG_TYPE_EXT: case BPF_PROG_TYPE_LSM: + case BPF_PROG_TYPE_SCHED: if (attr->raw_tracepoint.name) { /* The attach point for this category of programs * should be specified via btf_id during program load. diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index 986dabc3d11f0688433bd27d02d67991d9574811..cc6ba35a1d14dc584d6114b5d309a8672c3971b4 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -357,6 +357,7 @@ static enum bpf_tramp_prog_type bpf_attach_type_to_tramp(struct bpf_prog *prog) switch (prog->expected_attach_type) { case BPF_TRACE_FENTRY: return BPF_TRAMP_FENTRY; + case BPF_SCHED: case BPF_MODIFY_RETURN: return BPF_TRAMP_MODIFY_RETURN; case BPF_TRACE_FEXIT: diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 6423f1714a2f456b17c017217e63218611f653cb..d26104b258baba4020f1587504c81ec4b403894e 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -22,6 +22,7 @@ #include #include #include +#include #include "disasm.h" @@ -12178,6 +12179,7 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, case BPF_LSM_MAC: case BPF_TRACE_FENTRY: case BPF_TRACE_FEXIT: + case BPF_SCHED: if (!btf_type_is_func(t)) { bpf_log(log, "attach_btf_id %u is not a function\n", btf_id); @@ -12283,7 +12285,8 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) if (prog->type != BPF_PROG_TYPE_TRACING && prog->type != BPF_PROG_TYPE_LSM && - prog->type != BPF_PROG_TYPE_EXT) + prog->type != BPF_PROG_TYPE_EXT && + prog->type != BPF_PROG_TYPE_SCHED) return 0; ret = bpf_check_attach_target(&env->log, prog, tgt_prog, btf_id, &tgt_info); @@ -12323,6 +12326,12 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) return ret; } + if (prog->type == BPF_PROG_TYPE_SCHED) { + ret = bpf_sched_verify_prog(&env->log, prog); + if (ret < 0) + return ret; + } + key = bpf_trampoline_compute_key(tgt_prog, btf_id); tr = bpf_trampoline_get(key, &tgt_info); if (!tr) diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile index 5fc9c9b70862f72486b4b6e57711d530ceaeca18..8ae9e39eb83ab9cf9bd30f5005932a3ce924e370 100644 --- a/kernel/sched/Makefile +++ b/kernel/sched/Makefile @@ -36,3 +36,4 @@ obj-$(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) += cpufreq_schedutil.o obj-$(CONFIG_MEMBARRIER) += membarrier.o obj-$(CONFIG_CPU_ISOLATION) += isolation.o obj-$(CONFIG_PSI) += psi.o +obj-$(CONFIG_BPF_SCHED) += bpf_sched.o \ No newline at end of file diff --git a/kernel/sched/bpf_sched.c b/kernel/sched/bpf_sched.c new file mode 100644 index 0000000000000000000000000000000000000000..2f05c186cfd0d7e81f90c266d4dc121f0b032820 --- /dev/null +++ b/kernel/sched/bpf_sched.c @@ -0,0 +1,62 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include +#include "sched.h" + +/* + * For every hook declare a nop function where a BPF program can be attached. + */ +#define BPF_SCHED_HOOK(RET, DEFAULT, NAME, ...) \ +noinline RET bpf_sched_##NAME(__VA_ARGS__) \ +{ \ + return DEFAULT; \ +} + +#include +#undef BPF_SCHED_HOOK + +#define BPF_SCHED_HOOK(RET, DEFAULT, NAME, ...) BTF_ID(func, bpf_sched_##NAME) +BTF_SET_START(bpf_sched_hooks) +#include +#undef BPF_SCHED_HOOK +BTF_SET_END(bpf_sched_hooks) + +int bpf_sched_verify_prog(struct bpf_verifier_log *vlog, + const struct bpf_prog *prog) +{ + if (!prog->gpl_compatible) { + bpf_log(vlog, + "sched programs must have a GPL compatible license\n"); + return -EINVAL; + } + + if (!btf_id_set_contains(&bpf_sched_hooks, prog->aux->attach_btf_id)) { + bpf_log(vlog, "attach_btf_id %u points to wrong type name %s\n", + prog->aux->attach_btf_id, prog->aux->attach_func_name); + return -EINVAL; + } + + return 0; +} + +static const struct bpf_func_proto * +bpf_sched_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) +{ + switch (func_id) { + case BPF_FUNC_trace_printk: + return bpf_get_trace_printk_proto(); + default: + return NULL; + } +} + +const struct bpf_prog_ops bpf_sched_prog_ops = { +}; + +const struct bpf_verifier_ops bpf_sched_verifier_ops = { + .get_func_proto = bpf_sched_func_proto, + .is_valid_access = btf_ctx_access, +}; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index a44cb51558254c7bc1dcd9f4c55b17f88c177e40..7d7c04f698eceab8d7d30d50bbbc7155a370d500 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -199,6 +199,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_EXT, BPF_PROG_TYPE_LSM, BPF_PROG_TYPE_SK_LOOKUP, + BPF_PROG_TYPE_SCHED, }; enum bpf_attach_type { @@ -240,6 +241,7 @@ enum bpf_attach_type { BPF_XDP_CPUMAP, BPF_SK_LOOKUP, BPF_XDP, + BPF_SCHED, __MAX_BPF_ATTACH_TYPE };