From f371b304f12e31fe30207c41ca7754564e0ea4dc Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Mon, 11 Dec 2017 11:39:02 -0800 Subject: bpf/tracing: allow user space to query prog array on the same tp Commit e87c6bc3852b ("bpf: permit multiple bpf attachments for a single perf event") added support to attach multiple bpf programs to a single perf event. Although this provides flexibility, users may want to know what other bpf programs attached to the same tp interface. Besides getting visibility for the underlying bpf system, such information may also help consolidate multiple bpf programs, understand potential performance issues due to a large array, and debug (e.g., one bpf program which overwrites return code may impact subsequent program results). Commit 2541517c32be ("tracing, perf: Implement BPF programs attached to kprobes") utilized the existing perf ioctl interface and added the command PERF_EVENT_IOC_SET_BPF to attach a bpf program to a tracepoint. This patch adds a new ioctl command, given a perf event fd, to query the bpf program array attached to the same perf tracepoint event. The new uapi ioctl command: PERF_EVENT_IOC_QUERY_BPF The new uapi/linux/perf_event.h structure: struct perf_event_query_bpf { __u32 ids_len; __u32 prog_cnt; __u32 ids[0]; }; User space provides buffer "ids" for kernel to copy to. When returning from the kernel, the number of available programs in the array is set in "prog_cnt". The usage: struct perf_event_query_bpf *query = malloc(sizeof(*query) + sizeof(u32) * ids_len); query.ids_len = ids_len; err = ioctl(pmu_efd, PERF_EVENT_IOC_QUERY_BPF, query); if (err == 0) { /* query.prog_cnt is the number of available progs, * number of progs in ids: (ids_len == 0) ? 0 : query.prog_cnt */ } else if (errno == ENOSPC) { /* query.ids_len number of progs copied, * query.prog_cnt is the number of available progs */ } else { /* other errors */ } Signed-off-by: Yonghong Song Acked-by: Peter Zijlstra (Intel) Acked-by: Alexei Starovoitov Signed-off-by: Alexei Starovoitov --- include/uapi/linux/perf_event.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index b9a4953018ed..769533696483 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -418,6 +418,27 @@ struct perf_event_attr { __u16 __reserved_2; /* align to __u64 */ }; +/* + * Structure used by below PERF_EVENT_IOC_QUERY_BPF command + * to query bpf programs attached to the same perf tracepoint + * as the given perf event. + */ +struct perf_event_query_bpf { + /* + * The below ids array length + */ + __u32 ids_len; + /* + * Set by the kernel to indicate the number of + * available programs + */ + __u32 prog_cnt; + /* + * User provided buffer to store program ids + */ + __u32 ids[0]; +}; + #define perf_flags(attr) (*(&(attr)->read_format + 1)) /* @@ -433,6 +454,7 @@ struct perf_event_attr { #define PERF_EVENT_IOC_ID _IOR('$', 7, __u64 *) #define PERF_EVENT_IOC_SET_BPF _IOW('$', 8, __u32) #define PERF_EVENT_IOC_PAUSE_OUTPUT _IOW('$', 9, __u32) +#define PERF_EVENT_IOC_QUERY_BPF _IOWR('$', 10, struct perf_event_query_bpf *) enum perf_event_ioc_flags { PERF_IOC_FLAG_GROUP = 1U << 0, -- cgit v1.2.3 From 9802d86585db91655c7d1929a4f6bbe0952ea88e Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Mon, 11 Dec 2017 11:36:48 -0500 Subject: bpf: add a bpf_override_function helper Error injection is sloppy and very ad-hoc. BPF could fill this niche perfectly with it's kprobe functionality. We could make sure errors are only triggered in specific call chains that we care about with very specific situations. Accomplish this with the bpf_override_funciton helper. This will modify the probe'd callers return value to the specified value and set the PC to an override function that simply returns, bypassing the originally probed function. This gives us a nice clean way to implement systematic error injection for all of our code paths. Acked-by: Alexei Starovoitov Acked-by: Ingo Molnar Signed-off-by: Josef Bacik Signed-off-by: Alexei Starovoitov --- arch/Kconfig | 3 +++ arch/x86/Kconfig | 1 + arch/x86/include/asm/kprobes.h | 4 +++ arch/x86/include/asm/ptrace.h | 5 ++++ arch/x86/kernel/kprobes/ftrace.c | 14 ++++++++++ include/linux/filter.h | 3 ++- include/linux/trace_events.h | 1 + include/uapi/linux/bpf.h | 7 ++++- kernel/bpf/core.c | 3 +++ kernel/bpf/verifier.c | 2 ++ kernel/events/core.c | 7 +++++ kernel/trace/Kconfig | 11 ++++++++ kernel/trace/bpf_trace.c | 35 +++++++++++++++++++++++++ kernel/trace/trace_kprobe.c | 55 +++++++++++++++++++++++++++++++++++----- kernel/trace/trace_probe.h | 12 +++++++++ 15 files changed, 154 insertions(+), 9 deletions(-) (limited to 'include/uapi/linux') diff --git a/arch/Kconfig b/arch/Kconfig index 400b9e1b2f27..d3f4aaf9cb7a 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -196,6 +196,9 @@ config HAVE_OPTPROBES config HAVE_KPROBES_ON_FTRACE bool +config HAVE_KPROBE_OVERRIDE + bool + config HAVE_NMI bool diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 8eed3f94bfc7..04d66e6fa447 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -154,6 +154,7 @@ config X86 select HAVE_KERNEL_XZ select HAVE_KPROBES select HAVE_KPROBES_ON_FTRACE + select HAVE_KPROBE_OVERRIDE select HAVE_KRETPROBES select HAVE_KVM select HAVE_LIVEPATCH if X86_64 diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h index 9f2e3102e0bb..36abb23a7a35 100644 --- a/arch/x86/include/asm/kprobes.h +++ b/arch/x86/include/asm/kprobes.h @@ -67,6 +67,10 @@ extern const int kretprobe_blacklist_size; void arch_remove_kprobe(struct kprobe *p); asmlinkage void kretprobe_trampoline(void); +#ifdef CONFIG_KPROBES_ON_FTRACE +extern void arch_ftrace_kprobe_override_function(struct pt_regs *regs); +#endif + /* Architecture specific copy of original instruction*/ struct arch_specific_insn { /* copy of the original instruction */ diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index 14131dd06b29..6de1fd3d0097 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -109,6 +109,11 @@ static inline unsigned long regs_return_value(struct pt_regs *regs) return regs->ax; } +static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc) +{ + regs->ax = rc; +} + /* * user_mode(regs) determines whether a register set came from user * mode. On x86_32, this is true if V8086 mode was enabled OR if the diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c index 8dc0161cec8f..1ea748d682fd 100644 --- a/arch/x86/kernel/kprobes/ftrace.c +++ b/arch/x86/kernel/kprobes/ftrace.c @@ -97,3 +97,17 @@ int arch_prepare_kprobe_ftrace(struct kprobe *p) p->ainsn.boostable = false; return 0; } + +asmlinkage void override_func(void); +asm( + ".type override_func, @function\n" + "override_func:\n" + " ret\n" + ".size override_func, .-override_func\n" +); + +void arch_ftrace_kprobe_override_function(struct pt_regs *regs) +{ + regs->ip = (unsigned long)&override_func; +} +NOKPROBE_SYMBOL(arch_ftrace_kprobe_override_function); diff --git a/include/linux/filter.h b/include/linux/filter.h index 0062302e1285..5feb441d3dd9 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -458,7 +458,8 @@ struct bpf_prog { locked:1, /* Program image locked? */ gpl_compatible:1, /* Is filter GPL compatible? */ cb_access:1, /* Is control block accessed? */ - dst_needed:1; /* Do we need dst entry? */ + dst_needed:1, /* Do we need dst entry? */ + kprobe_override:1; /* Do we override a kprobe? */ enum bpf_prog_type type; /* Type of BPF program */ u32 len; /* Number of filter blocks */ u32 jited_len; /* Size of jited insns in bytes */ diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index af44e7c2d577..5fea451f6e28 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -528,6 +528,7 @@ do { \ struct perf_event; DECLARE_PER_CPU(struct pt_regs, perf_trace_regs); +DECLARE_PER_CPU(int, bpf_kprobe_override); extern int perf_trace_init(struct perf_event *event); extern void perf_trace_destroy(struct perf_event *event); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 80d62e88590c..595bda120cfb 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -677,6 +677,10 @@ union bpf_attr { * @buf: buf to fill * @buf_size: size of the buf * Return : 0 on success or negative error code + * + * int bpf_override_return(pt_regs, rc) + * @pt_regs: pointer to struct pt_regs + * @rc: the return value to set */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -736,7 +740,8 @@ union bpf_attr { FN(xdp_adjust_meta), \ FN(perf_event_read_value), \ FN(perf_prog_read_value), \ - FN(getsockopt), + FN(getsockopt), \ + FN(override_return), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index b16c6f8f42b6..d32bebf4f2de 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1320,6 +1320,9 @@ EVAL4(PROG_NAME_LIST, 416, 448, 480, 512) bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp) { + if (fp->kprobe_override) + return false; + if (!array->owner_prog_type) { /* There's no owner yet where we could check for * compatibility. diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 7afa92e9b409..e807bda7fe29 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -4413,6 +4413,8 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) prog->dst_needed = 1; if (insn->imm == BPF_FUNC_get_prandom_u32) bpf_user_rnd_init_once(); + if (insn->imm == BPF_FUNC_override_return) + prog->kprobe_override = 1; if (insn->imm == BPF_FUNC_tail_call) { /* If we tail call into other programs, we * cannot make any assumptions since they can diff --git a/kernel/events/core.c b/kernel/events/core.c index f10609e539d4..5857c500721b 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -8080,6 +8080,13 @@ static int perf_event_set_bpf_prog(struct perf_event *event, u32 prog_fd) return -EINVAL; } + /* Kprobe override only works for kprobes, not uprobes. */ + if (prog->kprobe_override && + !(event->tp_event->flags & TRACE_EVENT_FL_KPROBE)) { + bpf_prog_put(prog); + return -EINVAL; + } + if (is_tracepoint || is_syscall_tp) { int off = trace_event_get_offsets(event->tp_event); diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index af7dad126c13..3e6fd580fe7f 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -529,6 +529,17 @@ config FUNCTION_PROFILER If in doubt, say N. +config BPF_KPROBE_OVERRIDE + bool "Enable BPF programs to override a kprobed function" + depends on BPF_EVENTS + depends on KPROBES_ON_FTRACE + depends on HAVE_KPROBE_OVERRIDE + depends on DYNAMIC_FTRACE_WITH_REGS + default n + help + Allows BPF to override the execution of a probed function and + set a different return value. This is used for error injection. + config FTRACE_MCOUNT_RECORD def_bool y depends on DYNAMIC_FTRACE diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index b143f2a05aff..e009b7ecf473 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -13,6 +13,10 @@ #include #include #include +#include +#include + +#include "trace_probe.h" #include "trace.h" u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); @@ -76,6 +80,24 @@ unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx) } EXPORT_SYMBOL_GPL(trace_call_bpf); +#ifdef CONFIG_BPF_KPROBE_OVERRIDE +BPF_CALL_2(bpf_override_return, struct pt_regs *, regs, unsigned long, rc) +{ + __this_cpu_write(bpf_kprobe_override, 1); + regs_set_return_value(regs, rc); + arch_ftrace_kprobe_override_function(regs); + return 0; +} + +static const struct bpf_func_proto bpf_override_return_proto = { + .func = bpf_override_return, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, +}; +#endif + BPF_CALL_3(bpf_probe_read, void *, dst, u32, size, const void *, unsafe_ptr) { int ret; @@ -551,6 +573,10 @@ static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func return &bpf_get_stackid_proto; case BPF_FUNC_perf_event_read_value: return &bpf_perf_event_read_value_proto; +#ifdef CONFIG_BPF_KPROBE_OVERRIDE + case BPF_FUNC_override_return: + return &bpf_override_return_proto; +#endif default: return tracing_func_proto(func_id); } @@ -768,6 +794,15 @@ int perf_event_attach_bpf_prog(struct perf_event *event, struct bpf_prog_array *new_array; int ret = -EEXIST; + /* + * Kprobe override only works for ftrace based kprobes, and only if they + * are on the opt-in list. + */ + if (prog->kprobe_override && + (!trace_kprobe_ftrace(event->tp_event) || + !trace_kprobe_error_injectable(event->tp_event))) + return -EINVAL; + mutex_lock(&bpf_event_mutex); if (event->prog) diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 492700c5fb4d..5db849809a56 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -42,6 +42,7 @@ struct trace_kprobe { (offsetof(struct trace_kprobe, tp.args) + \ (sizeof(struct probe_arg) * (n))) +DEFINE_PER_CPU(int, bpf_kprobe_override); static nokprobe_inline bool trace_kprobe_is_return(struct trace_kprobe *tk) { @@ -87,6 +88,27 @@ static nokprobe_inline unsigned long trace_kprobe_nhit(struct trace_kprobe *tk) return nhit; } +int trace_kprobe_ftrace(struct trace_event_call *call) +{ + struct trace_kprobe *tk = (struct trace_kprobe *)call->data; + return kprobe_ftrace(&tk->rp.kp); +} + +int trace_kprobe_error_injectable(struct trace_event_call *call) +{ + struct trace_kprobe *tk = (struct trace_kprobe *)call->data; + unsigned long addr; + + if (tk->symbol) { + addr = (unsigned long) + kallsyms_lookup_name(trace_kprobe_symbol(tk)); + addr += tk->rp.kp.offset; + } else { + addr = (unsigned long)tk->rp.kp.addr; + } + return within_kprobe_error_injection_list(addr); +} + static int register_kprobe_event(struct trace_kprobe *tk); static int unregister_kprobe_event(struct trace_kprobe *tk); @@ -1170,7 +1192,7 @@ static int kretprobe_event_define_fields(struct trace_event_call *event_call) #ifdef CONFIG_PERF_EVENTS /* Kprobe profile handler */ -static void +static int kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs) { struct trace_event_call *call = &tk->tp.call; @@ -1179,12 +1201,29 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs) int size, __size, dsize; int rctx; - if (bpf_prog_array_valid(call) && !trace_call_bpf(call, regs)) - return; + if (bpf_prog_array_valid(call)) { + int ret; + + ret = trace_call_bpf(call, regs); + + /* + * We need to check and see if we modified the pc of the + * pt_regs, and if so clear the kprobe and return 1 so that we + * don't do the instruction skipping. Also reset our state so + * we are clean the next pass through. + */ + if (__this_cpu_read(bpf_kprobe_override)) { + __this_cpu_write(bpf_kprobe_override, 0); + reset_current_kprobe(); + return 1; + } + if (!ret) + return 0; + } head = this_cpu_ptr(call->perf_events); if (hlist_empty(head)) - return; + return 0; dsize = __get_data_size(&tk->tp, regs); __size = sizeof(*entry) + tk->tp.size + dsize; @@ -1193,13 +1232,14 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs) entry = perf_trace_buf_alloc(size, NULL, &rctx); if (!entry) - return; + return 0; entry->ip = (unsigned long)tk->rp.kp.addr; memset(&entry[1], 0, dsize); store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize); perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs, head, NULL); + return 0; } NOKPROBE_SYMBOL(kprobe_perf_func); @@ -1275,6 +1315,7 @@ static int kprobe_register(struct trace_event_call *event, static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs) { struct trace_kprobe *tk = container_of(kp, struct trace_kprobe, rp.kp); + int ret = 0; raw_cpu_inc(*tk->nhit); @@ -1282,9 +1323,9 @@ static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs) kprobe_trace_func(tk, regs); #ifdef CONFIG_PERF_EVENTS if (tk->tp.flags & TP_FLAG_PROFILE) - kprobe_perf_func(tk, regs); + ret = kprobe_perf_func(tk, regs); #endif - return 0; /* We don't tweek kernel, so just return 0 */ + return ret; } NOKPROBE_SYMBOL(kprobe_dispatcher); diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index fb66e3eaa192..5e54d748c84c 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -252,6 +252,8 @@ struct symbol_cache; unsigned long update_symbol_cache(struct symbol_cache *sc); void free_symbol_cache(struct symbol_cache *sc); struct symbol_cache *alloc_symbol_cache(const char *sym, long offset); +int trace_kprobe_ftrace(struct trace_event_call *call); +int trace_kprobe_error_injectable(struct trace_event_call *call); #else /* uprobes do not support symbol fetch methods */ #define fetch_symbol_u8 NULL @@ -277,6 +279,16 @@ alloc_symbol_cache(const char *sym, long offset) { return NULL; } + +static inline int trace_kprobe_ftrace(struct trace_event_call *call) +{ + return 0; +} + +static inline int trace_kprobe_error_injectable(struct trace_event_call *call) +{ + return 0; +} #endif /* CONFIG_KPROBE_EVENTS */ struct probe_arg { -- cgit v1.2.3 From cc8b0b92a1699bc32f7fec71daa2bfc90de43a4d Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 14 Dec 2017 17:55:05 -0800 Subject: bpf: introduce function calls (function boundaries) Allow arbitrary function calls from bpf function to another bpf function. Since the beginning of bpf all bpf programs were represented as a single function and program authors were forced to use always_inline for all functions in their C code. That was causing llvm to unnecessary inflate the code size and forcing developers to move code to header files with little code reuse. With a bit of additional complexity teach verifier to recognize arbitrary function calls from one bpf function to another as long as all of functions are presented to the verifier as a single bpf program. New program layout: r6 = r1 // some code .. r1 = .. // arg1 r2 = .. // arg2 call pc+1 // function call pc-relative exit .. = r1 // access arg1 .. = r2 // access arg2 .. call pc+20 // second level of function call ... It allows for better optimized code and finally allows to introduce the core bpf libraries that can be reused in different projects, since programs are no longer limited by single elf file. With function calls bpf can be compiled into multiple .o files. This patch is the first step. It detects programs that contain multiple functions and checks that calls between them are valid. It splits the sequence of bpf instructions (one program) into a set of bpf functions that call each other. Calls to only known functions are allowed. In the future the verifier may allow calls to unresolved functions and will do dynamic linking. This logic supports statically linked bpf functions only. Such function boundary detection could have been done as part of control flow graph building in check_cfg(), but it's cleaner to separate function boundary detection vs control flow checks within a subprogram (function) into logically indepedent steps. Follow up patches may split check_cfg() further, but not check_subprogs(). Only allow bpf-to-bpf calls for root only and for non-hw-offloaded programs. These restrictions can be relaxed in the future. Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: Daniel Borkmann --- include/linux/bpf_verifier.h | 5 +- include/uapi/linux/bpf.h | 6 ++ kernel/bpf/disasm.c | 8 ++- kernel/bpf/verifier.c | 141 ++++++++++++++++++++++++++++++++++++++++++- 4 files changed, 155 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index c561b986bab0..91a583bb3fa7 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -141,6 +141,8 @@ struct bpf_ext_analyzer_ops { int insn_idx, int prev_insn_idx); }; +#define BPF_MAX_SUBPROGS 256 + /* single container for all structs * one verifier_env per bpf_check() call */ @@ -159,8 +161,9 @@ struct bpf_verifier_env { bool allow_ptr_leaks; bool seen_direct_write; struct bpf_insn_aux_data *insn_aux_data; /* array of per-insn state */ - struct bpf_verifer_log log; + u32 subprog_starts[BPF_MAX_SUBPROGS]; + u32 subprog_cnt; }; static inline struct bpf_reg_state *cur_regs(struct bpf_verifier_env *env) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 595bda120cfb..d01f1cb3cfc0 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -197,8 +197,14 @@ enum bpf_attach_type { */ #define BPF_F_STRICT_ALIGNMENT (1U << 0) +/* when bpf_ldimm64->src_reg == BPF_PSEUDO_MAP_FD, bpf_ldimm64->imm == fd */ #define BPF_PSEUDO_MAP_FD 1 +/* when bpf_call->src_reg == BPF_PSEUDO_CALL, bpf_call->imm == pc-relative + * offset to another bpf function + */ +#define BPF_PSEUDO_CALL 1 + /* flags for BPF_MAP_UPDATE_ELEM command */ #define BPF_ANY 0 /* create new element or update existing */ #define BPF_NOEXIST 1 /* create new element if it didn't exist */ diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c index e682850c9715..883f88fa5bfc 100644 --- a/kernel/bpf/disasm.c +++ b/kernel/bpf/disasm.c @@ -189,8 +189,12 @@ void print_bpf_insn(bpf_insn_print_cb verbose, struct bpf_verifier_env *env, u8 opcode = BPF_OP(insn->code); if (opcode == BPF_CALL) { - verbose(env, "(%02x) call %s#%d\n", insn->code, - func_id_name(insn->imm), insn->imm); + if (insn->src_reg == BPF_PSEUDO_CALL) + verbose(env, "(%02x) call pc%+d\n", insn->code, + insn->imm); + else + verbose(env, "(%02x) call %s#%d\n", insn->code, + func_id_name(insn->imm), insn->imm); } else if (insn->code == (BPF_JMP | BPF_JA)) { verbose(env, "(%02x) goto pc%+d\n", insn->code, insn->off); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index e807bda7fe29..1d0f7ff0b9a9 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -20,6 +20,8 @@ #include #include #include +#include +#include #include "disasm.h" @@ -636,6 +638,113 @@ enum reg_arg_type { DST_OP_NO_MARK /* same as above, check only, don't mark */ }; +static int cmp_subprogs(const void *a, const void *b) +{ + return *(int *)a - *(int *)b; +} + +static int find_subprog(struct bpf_verifier_env *env, int off) +{ + u32 *p; + + p = bsearch(&off, env->subprog_starts, env->subprog_cnt, + sizeof(env->subprog_starts[0]), cmp_subprogs); + if (!p) + return -ENOENT; + return p - env->subprog_starts; + +} + +static int add_subprog(struct bpf_verifier_env *env, int off) +{ + int insn_cnt = env->prog->len; + int ret; + + if (off >= insn_cnt || off < 0) { + verbose(env, "call to invalid destination\n"); + return -EINVAL; + } + ret = find_subprog(env, off); + if (ret >= 0) + return 0; + if (env->subprog_cnt >= BPF_MAX_SUBPROGS) { + verbose(env, "too many subprograms\n"); + return -E2BIG; + } + env->subprog_starts[env->subprog_cnt++] = off; + sort(env->subprog_starts, env->subprog_cnt, + sizeof(env->subprog_starts[0]), cmp_subprogs, NULL); + return 0; +} + +static int check_subprogs(struct bpf_verifier_env *env) +{ + int i, ret, subprog_start, subprog_end, off, cur_subprog = 0; + struct bpf_insn *insn = env->prog->insnsi; + int insn_cnt = env->prog->len; + + /* determine subprog starts. The end is one before the next starts */ + for (i = 0; i < insn_cnt; i++) { + if (insn[i].code != (BPF_JMP | BPF_CALL)) + continue; + if (insn[i].src_reg != BPF_PSEUDO_CALL) + continue; + if (!env->allow_ptr_leaks) { + verbose(env, "function calls to other bpf functions are allowed for root only\n"); + return -EPERM; + } + if (bpf_prog_is_dev_bound(env->prog->aux)) { + verbose(env, "funcation calls in offloaded programs are not supported yet\n"); + return -EINVAL; + } + ret = add_subprog(env, i + insn[i].imm + 1); + if (ret < 0) + return ret; + } + + if (env->log.level > 1) + for (i = 0; i < env->subprog_cnt; i++) + verbose(env, "func#%d @%d\n", i, env->subprog_starts[i]); + + /* now check that all jumps are within the same subprog */ + subprog_start = 0; + if (env->subprog_cnt == cur_subprog) + subprog_end = insn_cnt; + else + subprog_end = env->subprog_starts[cur_subprog++]; + for (i = 0; i < insn_cnt; i++) { + u8 code = insn[i].code; + + if (BPF_CLASS(code) != BPF_JMP) + goto next; + if (BPF_OP(code) == BPF_EXIT || BPF_OP(code) == BPF_CALL) + goto next; + off = i + insn[i].off + 1; + if (off < subprog_start || off >= subprog_end) { + verbose(env, "jump out of range from insn %d to %d\n", i, off); + return -EINVAL; + } +next: + if (i == subprog_end - 1) { + /* to avoid fall-through from one subprog into another + * the last insn of the subprog should be either exit + * or unconditional jump back + */ + if (code != (BPF_JMP | BPF_EXIT) && + code != (BPF_JMP | BPF_JA)) { + verbose(env, "last insn is not an exit or jmp\n"); + return -EINVAL; + } + subprog_start = subprog_end; + if (env->subprog_cnt == cur_subprog) + subprog_end = insn_cnt; + else + subprog_end = env->subprog_starts[cur_subprog++]; + } + } + return 0; +} + static void mark_reg_read(const struct bpf_verifier_state *state, u32 regno) { struct bpf_verifier_state *parent = state->parent; @@ -3284,6 +3393,10 @@ static int check_cfg(struct bpf_verifier_env *env) int ret = 0; int i, t; + ret = check_subprogs(env); + if (ret < 0) + return ret; + insn_state = kcalloc(insn_cnt, sizeof(int), GFP_KERNEL); if (!insn_state) return -ENOMEM; @@ -3316,6 +3429,14 @@ peek_stack: goto err_free; if (t + 1 < insn_cnt) env->explored_states[t + 1] = STATE_LIST_MARK; + if (insns[t].src_reg == BPF_PSEUDO_CALL) { + env->explored_states[t] = STATE_LIST_MARK; + ret = push_insn(t, t + insns[t].imm + 1, BRANCH, env); + if (ret == 1) + goto peek_stack; + else if (ret < 0) + goto err_free; + } } else if (opcode == BPF_JA) { if (BPF_SRC(insns[t].code) != BPF_K) { ret = -EINVAL; @@ -4245,6 +4366,19 @@ static int adjust_insn_aux_data(struct bpf_verifier_env *env, u32 prog_len, return 0; } +static void adjust_subprog_starts(struct bpf_verifier_env *env, u32 off, u32 len) +{ + int i; + + if (len == 1) + return; + for (i = 0; i < env->subprog_cnt; i++) { + if (env->subprog_starts[i] < off) + continue; + env->subprog_starts[i] += len - 1; + } +} + static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 off, const struct bpf_insn *patch, u32 len) { @@ -4255,6 +4389,7 @@ static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 of return NULL; if (adjust_insn_aux_data(env, new_prog->len, off, len)) return NULL; + adjust_subprog_starts(env, off, len); return new_prog; } @@ -4408,6 +4543,8 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) for (i = 0; i < insn_cnt; i++, insn++) { if (insn->code != (BPF_JMP | BPF_CALL)) continue; + if (insn->src_reg == BPF_PSEUDO_CALL) + continue; if (insn->imm == BPF_FUNC_get_route_realm) prog->dst_needed = 1; @@ -4589,12 +4726,12 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) if (!env->explored_states) goto skip_full_check; + env->allow_ptr_leaks = capable(CAP_SYS_ADMIN); + ret = check_cfg(env); if (ret < 0) goto skip_full_check; - env->allow_ptr_leaks = capable(CAP_SYS_ADMIN); - ret = do_check(env); if (env->cur_state) { free_verifier_state(env->cur_state, true); -- cgit v1.2.3