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 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/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) -- cgit v1.2.3 From f4d7e40a5b7157e1329c3c5b10f60d8289fc2941 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 14 Dec 2017 17:55:06 -0800 Subject: bpf: introduce function calls (verification) Allow arbitrary function calls from bpf function to another bpf function. To recognize such set of bpf functions the verifier does: 1. runs control flow analysis to detect function boundaries 2. proceeds with verification of all functions starting from main(root) function It recognizes that the stack of the caller can be accessed by the callee (if the caller passed a pointer to its stack to the callee) and the callee can store map_value and other pointers into the stack of the caller. 3. keeps track of the stack_depth of each function to make sure that total stack depth is still less than 512 bytes 4. disallows pointers to the callee stack to be stored into the caller stack, since they will be invalid as soon as the callee returns 5. to reuse all of the existing state_pruning logic each function call is considered to be independent call from the verifier point of view. The verifier pretends to inline all function calls it sees are being called. It stores the callsite instruction index as part of the state to make sure that two calls to the same callee from two different places in the caller will be different from state pruning point of view 6. more safety checks are added to liveness analysis Implementation details: . struct bpf_verifier_state is now consists of all stack frames that led to this function . struct bpf_func_state represent one stack frame. It consists of registers in the given frame and its stack . propagate_liveness() logic had a premature optimization where mark_reg_read() and mark_stack_slot_read() were manually inlined with loop iterating over parents for each register or stack slot. Undo this optimization to reuse more complex mark_*_read() logic . skip_callee() logic is not necessary from safety point of view, but without it mark_*_read() markings become too conservative, since after returning from the funciton call a read of r6-r9 will incorrectly propagate the read marks into callee causing inefficient pruning later . mark_*_read() logic is now aware of control flow which makes it more complex. In the future the plan is to rewrite liveness to be hierarchical. So that liveness can be done within basic block only and control flow will be responsible for propagation of liveness information along cfg and between calls. . tail_calls and ld_abs insns are not allowed in the programs with bpf-to-bpf calls . returning stack pointers to the caller or storing them into stack frame of the caller is not allowed Testing: . no difference in cilium processed_insn numbers . large number of tests follows in next patches Signed-off-by: Alexei Starovoitov Acked-by: John Fastabend Acked-by: Daniel Borkmann Signed-off-by: Daniel Borkmann --- include/linux/bpf_verifier.h | 36 ++++++++++++++++++++++++++++++++++-- 1 file changed, 34 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 91a583bb3fa7..1f23408024ee 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -76,6 +76,14 @@ struct bpf_reg_state { s64 smax_value; /* maximum possible (s64)value */ u64 umin_value; /* minimum possible (u64)value */ u64 umax_value; /* maximum possible (u64)value */ + /* Inside the callee two registers can be both PTR_TO_STACK like + * R1=fp-8 and R2=fp-8, but one of them points to this function stack + * while another to the caller's stack. To differentiate them 'frameno' + * is used which is an index in bpf_verifier_state->frame[] array + * pointing to bpf_func_state. + * This field must be second to last, for states_equal() reasons. + */ + u32 frameno; /* This field must be last, for states_equal() reasons. */ enum bpf_reg_liveness live; }; @@ -96,13 +104,34 @@ struct bpf_stack_state { /* state of the program: * type of all registers and stack info */ -struct bpf_verifier_state { +struct bpf_func_state { struct bpf_reg_state regs[MAX_BPF_REG]; struct bpf_verifier_state *parent; + /* index of call instruction that called into this func */ + int callsite; + /* stack frame number of this function state from pov of + * enclosing bpf_verifier_state. + * 0 = main function, 1 = first callee. + */ + u32 frameno; + /* subprog number == index within subprog_stack_depth + * zero == main subprog + */ + u32 subprogno; + + /* should be second to last. See copy_func_state() */ int allocated_stack; struct bpf_stack_state *stack; }; +#define MAX_CALL_FRAMES 8 +struct bpf_verifier_state { + /* call stack tracking */ + struct bpf_func_state *frame[MAX_CALL_FRAMES]; + struct bpf_verifier_state *parent; + u32 curframe; +}; + /* linked list of verifier states used to prune search */ struct bpf_verifier_state_list { struct bpf_verifier_state state; @@ -163,12 +192,15 @@ struct bpf_verifier_env { struct bpf_insn_aux_data *insn_aux_data; /* array of per-insn state */ struct bpf_verifer_log log; u32 subprog_starts[BPF_MAX_SUBPROGS]; + u16 subprog_stack_depth[BPF_MAX_SUBPROGS + 1]; u32 subprog_cnt; }; static inline struct bpf_reg_state *cur_regs(struct bpf_verifier_env *env) { - return env->cur_state->regs; + struct bpf_verifier_state *cur = env->cur_state; + + return cur->frame[cur->curframe]->regs; } #if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL) -- cgit v1.2.3 From cc2b14d51053eb055c06f45e1a5cdbfcf2b79e94 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 14 Dec 2017 17:55:08 -0800 Subject: bpf: teach verifier to recognize zero initialized stack programs with function calls are often passing various pointers via stack. When all calls are inlined llvm flattens stack accesses and optimizes away extra branches. When functions are not inlined it becomes the job of the verifier to recognize zero initialized stack to avoid exploring paths that program will not take. The following program would fail otherwise: ptr = &buffer_on_stack; *ptr = 0; ... func_call(.., ptr, ...) { if (..) *ptr = bpf_map_lookup(); } ... if (*ptr != 0) { // Access (*ptr)->field is valid. // Without stack_zero tracking such (*ptr)->field access // will be rejected } since stack slots are no longer uniform invalid | spill | misc add liveness marking to all slots, but do it in 8 byte chunks. So if nothing was read or written in [fp-16, fp-9] range it will be marked as LIVE_NONE. If any byte in that range was read, it will be marked LIVE_READ and stacksafe() check will perform byte-by-byte verification. If all bytes in the range were written the slot will be marked as LIVE_WRITTEN. This significantly speeds up state equality comparison and reduces total number of states processed. before after bpf_lb-DLB_L3.o 2051 2003 bpf_lb-DLB_L4.o 3287 3164 bpf_lb-DUNKNOWN.o 1080 1080 bpf_lxc-DDROP_ALL.o 24980 12361 bpf_lxc-DUNKNOWN.o 34308 16605 bpf_netdev.o 15404 10962 bpf_overlay.o 7191 6679 Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: Daniel Borkmann --- include/linux/bpf_verifier.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 1f23408024ee..585d4e17ea88 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -91,7 +91,8 @@ struct bpf_reg_state { enum bpf_stack_slot_type { STACK_INVALID, /* nothing was stored in this stack slot */ STACK_SPILL, /* register spilled into stack */ - STACK_MISC /* BPF program wrote some data into this slot */ + STACK_MISC, /* BPF program wrote some data into this slot */ + STACK_ZERO, /* BPF program wrote constant zero */ }; #define BPF_REG_SIZE 8 /* size of eBPF register in bytes */ -- cgit v1.2.3 From 1ea47e01ad6ea0fe99697c54c2413d81dd21fe32 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 14 Dec 2017 17:55:13 -0800 Subject: bpf: add support for bpf_call to interpreter though bpf_call is still the same call instruction and calling convention 'bpf to bpf' and 'bpf to helper' is the same the interpreter has to oparate on 'struct bpf_insn *'. To distinguish these two cases add a kernel internal opcode and mark call insns with it. This opcode is seen by interpreter only. JITs will never see it. Also add tiny bit of debug code to aid interpreter debugging. Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 1 + include/linux/filter.h | 6 ++++++ 2 files changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 54dc7cae2949..8935f6f63d5f 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -402,6 +402,7 @@ static inline void bpf_long_memcpy(void *dst, const void *src, u32 size) /* verify correctness of eBPF program */ int bpf_check(struct bpf_prog **fp, union bpf_attr *attr); +void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth); /* Map specifics */ struct net_device *__dev_map_lookup_elem(struct bpf_map *map, u32 key); diff --git a/include/linux/filter.h b/include/linux/filter.h index 5feb441d3dd9..f26e6da1007b 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -58,6 +58,9 @@ struct bpf_prog_aux; /* unused opcode to mark special call to bpf_tail_call() helper */ #define BPF_TAIL_CALL 0xf0 +/* unused opcode to mark call to interpreter with arguments */ +#define BPF_CALL_ARGS 0xe0 + /* As per nm, we expose JITed images as text (code) section for * kallsyms. That way, tools like perf can find it to match * addresses. @@ -710,6 +713,9 @@ bool sk_filter_charge(struct sock *sk, struct sk_filter *fp); void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp); u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); +#define __bpf_call_base_args \ + ((u64 (*)(u64, u64, u64, u64, u64, const struct bpf_insn *)) \ + __bpf_call_base) struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog); void bpf_jit_compile(struct bpf_prog *prog); -- cgit v1.2.3 From 60b58afc96c9df71871df2dbad42037757ceef26 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 14 Dec 2017 17:55:14 -0800 Subject: bpf: fix net.core.bpf_jit_enable race global bpf_jit_enable variable is tested multiple times in JITs, blinding and verifier core. The malicious root can try to toggle it while loading the programs. This race condition was accounted for and there should be no issues, but it's safer to avoid this race condition. Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: Daniel Borkmann --- include/linux/filter.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index f26e6da1007b..3d6edc34932c 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -458,6 +458,7 @@ struct bpf_binary_header { struct bpf_prog { u16 pages; /* Number of allocated pages */ u16 jited:1, /* Is our filter JIT'ed? */ + jit_requested:1,/* archs need to JIT the prog */ locked:1, /* Program image locked? */ gpl_compatible:1, /* Is filter GPL compatible? */ cb_access:1, /* Is control block accessed? */ @@ -804,7 +805,7 @@ static inline bool bpf_prog_ebpf_jited(const struct bpf_prog *fp) return fp->jited && bpf_jit_is_ebpf(); } -static inline bool bpf_jit_blinding_enabled(void) +static inline bool bpf_jit_blinding_enabled(struct bpf_prog *prog) { /* These are the prerequisites, should someone ever have the * idea to call blinding outside of them, we make sure to @@ -812,7 +813,7 @@ static inline bool bpf_jit_blinding_enabled(void) */ if (!bpf_jit_is_ebpf()) return false; - if (!bpf_jit_enable) + if (!prog->jit_requested) return false; if (!bpf_jit_harden) return false; -- cgit v1.2.3 From 1c2a088a6626d4f51d2f2c97b0cbedbfbf3637f6 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 14 Dec 2017 17:55:15 -0800 Subject: bpf: x64: add JIT support for multi-function programs Typical JIT does several passes over bpf instructions to compute total size and relative offsets of jumps and calls. With multitple bpf functions calling each other all relative calls will have invalid offsets intially therefore we need to additional last pass over the program to emit calls with correct offsets. For example in case of three bpf functions: main: call foo call bpf_map_lookup exit foo: call bar exit bar: exit We will call bpf_int_jit_compile() indepedently for main(), foo() and bar() x64 JIT typically does 4-5 passes to converge. After these initial passes the image for these 3 functions will be good except call targets, since start addresses of foo() and bar() are unknown when we were JITing main() (note that call bpf_map_lookup will be resolved properly during initial passes). Once start addresses of 3 functions are known we patch call_insn->imm to point to right functions and call bpf_int_jit_compile() again which needs only one pass. Additional safety checks are done to make sure this last pass doesn't produce image that is larger or smaller than previous pass. When constant blinding is on it's applied to all functions at the first pass, since doing it once again at the last pass can change size of the JITed code. Tested on x64 and arm64 hw with JIT on/off, blinding on/off. x64 jits bpf-to-bpf calls correctly while arm64 falls back to interpreter. All other JITs that support normal BPF_CALL will behave the same way since bpf-to-bpf call is equivalent to bpf-to-kernel call from JITs point of view. Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 3 +++ include/linux/bpf_verifier.h | 1 + include/linux/filter.h | 2 ++ 3 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 8935f6f63d5f..da54ef644fcd 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -200,6 +200,9 @@ struct bpf_prog_aux { u32 max_ctx_offset; u32 stack_depth; u32 id; + u32 func_cnt; + struct bpf_prog **func; + void *jit_data; /* JIT specific data. arch dependent */ struct latch_tree_node ksym_tnode; struct list_head ksym_lnode; const struct bpf_prog_ops *ops; diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 585d4e17ea88..aaac589e490c 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -143,6 +143,7 @@ struct bpf_insn_aux_data { union { enum bpf_reg_type ptr_type; /* pointer type for load/store insns */ struct bpf_map *map_ptr; /* pointer for call insn into lookup_elem */ + s32 call_imm; /* saved imm field of call insn */ }; int ctx_field_size; /* the ctx field size for load insn, maybe 0 */ bool seen; /* this insn was processed by the verifier */ diff --git a/include/linux/filter.h b/include/linux/filter.h index 3d6edc34932c..e872b4ebaa57 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -463,6 +463,8 @@ struct bpf_prog { gpl_compatible:1, /* Is filter GPL compatible? */ cb_access:1, /* Is control block accessed? */ dst_needed:1, /* Do we need dst entry? */ + blinded:1, /* Was blinded */ + is_func:1, /* program is a bpf function */ kprobe_override:1; /* Do we override a kprobe? */ enum bpf_prog_type type; /* Type of BPF program */ u32 len; /* Number of filter blocks */ -- cgit v1.2.3