From 011832b97b311bb9e3c27945bc0d1089a14209c9 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 5 Mar 2024 19:19:26 -0800 Subject: bpf: Introduce may_goto instruction Introduce may_goto instruction that from the verifier pov is similar to open coded iterators bpf_for()/bpf_repeat() and bpf_loop() helper, but it doesn't iterate any objects. In assembly 'may_goto' is a nop most of the time until bpf runtime has to terminate the program for whatever reason. In the current implementation may_goto has a hidden counter, but other mechanisms can be used. For programs written in C the later patch introduces 'cond_break' macro that combines 'may_goto' with 'break' statement and has similar semantics: cond_break is a nop until bpf runtime has to break out of this loop. It can be used in any normal "for" or "while" loop, like for (i = zero; i < cnt; cond_break, i++) { The verifier recognizes that may_goto is used in the program, reserves additional 8 bytes of stack, initializes them in subprog prologue, and replaces may_goto instruction with: aux_reg = *(u64 *)(fp - 40) if aux_reg == 0 goto pc+off aux_reg -= 1 *(u64 *)(fp - 40) = aux_reg may_goto instruction can be used by LLVM to implement __builtin_memcpy, __builtin_strcmp. may_goto is not a full substitute for bpf_for() macro. bpf_for() doesn't have induction variable that verifiers sees, so 'i' in bpf_for(i, 0, 100) is seen as imprecise and bounded. But when the code is written as: for (i = 0; i < 100; cond_break, i++) the verifier see 'i' as precise constant zero, hence cond_break (aka may_goto) doesn't help to converge the loop. A static or global variable can be used as a workaround: static int zero = 0; for (i = zero; i < 100; cond_break, i++) // works! may_goto works well with arena pointers that don't need to be bounds checked on access. Load/store from arena returns imprecise unbounded scalar and loops with may_goto pass the verifier. Reserve new opcode BPF_JMP | BPF_JCOND for may_goto insn. JCOND stands for conditional pseudo jump. Since goto_or_nop insn was proposed, it may use the same opcode. may_goto vs goto_or_nop can be distinguished by src_reg: code = BPF_JMP | BPF_JCOND src_reg = 0 - may_goto src_reg = 1 - goto_or_nop Signed-off-by: Alexei Starovoitov Signed-off-by: Andrii Nakryiko Acked-by: Andrii Nakryiko Acked-by: Eduard Zingerman Acked-by: John Fastabend Tested-by: John Fastabend Link: https://lore.kernel.org/bpf/20240306031929.42666-2-alexei.starovoitov@gmail.com --- kernel/bpf/disasm.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'kernel/bpf/disasm.c') diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c index 49940c26a227..82b2dbdd048f 100644 --- a/kernel/bpf/disasm.c +++ b/kernel/bpf/disasm.c @@ -322,6 +322,10 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs, } else if (insn->code == (BPF_JMP | BPF_JA)) { verbose(cbs->private_data, "(%02x) goto pc%+d\n", insn->code, insn->off); + } else if (insn->code == (BPF_JMP | BPF_JCOND) && + insn->src_reg == BPF_MAY_GOTO) { + verbose(cbs->private_data, "(%02x) may_goto pc%+d\n", + insn->code, insn->off); } else if (insn->code == (BPF_JMP32 | BPF_JA)) { verbose(cbs->private_data, "(%02x) gotol pc%+d\n", insn->code, insn->imm); -- cgit v1.2.3 From 667a86ad9b71d934c444eec193cf3508016f35c5 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 7 Mar 2024 17:08:00 -0800 Subject: bpf: Disasm support for addr_space_cast instruction. LLVM generates rX = addr_space_cast(rY, dst_addr_space, src_addr_space) instruction when pointers in non-zero address space are used by the bpf program. Recognize this insn in uapi and in bpf disassembler. Signed-off-by: Alexei Starovoitov Signed-off-by: Andrii Nakryiko Acked-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/bpf/20240308010812.89848-3-alexei.starovoitov@gmail.com --- include/uapi/linux/bpf.h | 4 ++++ kernel/bpf/disasm.c | 10 ++++++++++ tools/include/uapi/linux/bpf.h | 4 ++++ 3 files changed, 18 insertions(+) (limited to 'kernel/bpf/disasm.c') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index e30d943db8a4..3c42b9f1bada 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1339,6 +1339,10 @@ enum { */ #define BPF_PSEUDO_KFUNC_CALL 2 +enum bpf_addr_space_cast { + BPF_ADDR_SPACE_CAST = 1, +}; + /* flags for BPF_MAP_UPDATE_ELEM command */ enum { BPF_ANY = 0, /* create new element or update existing */ diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c index 82b2dbdd048f..bd2e2dd04740 100644 --- a/kernel/bpf/disasm.c +++ b/kernel/bpf/disasm.c @@ -166,6 +166,12 @@ static bool is_movsx(const struct bpf_insn *insn) (insn->off == 8 || insn->off == 16 || insn->off == 32); } +static bool is_addr_space_cast(const struct bpf_insn *insn) +{ + return insn->code == (BPF_ALU64 | BPF_MOV | BPF_X) && + insn->off == BPF_ADDR_SPACE_CAST; +} + void print_bpf_insn(const struct bpf_insn_cbs *cbs, const struct bpf_insn *insn, bool allow_ptr_leaks) @@ -184,6 +190,10 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs, insn->code, class == BPF_ALU ? 'w' : 'r', insn->dst_reg, class == BPF_ALU ? 'w' : 'r', insn->dst_reg); + } else if (is_addr_space_cast(insn)) { + verbose(cbs->private_data, "(%02x) r%d = addr_space_cast(r%d, %d, %d)\n", + insn->code, insn->dst_reg, + insn->src_reg, ((u32)insn->imm) >> 16, (u16)insn->imm); } else if (BPF_SRC(insn->code) == BPF_X) { verbose(cbs->private_data, "(%02x) %c%d %s %s%c%d\n", insn->code, class == BPF_ALU ? 'w' : 'r', diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index e30d943db8a4..3c42b9f1bada 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1339,6 +1339,10 @@ enum { */ #define BPF_PSEUDO_KFUNC_CALL 2 +enum bpf_addr_space_cast { + BPF_ADDR_SPACE_CAST = 1, +}; + /* flags for BPF_MAP_UPDATE_ELEM command */ enum { BPF_ANY = 0, /* create new element or update existing */ -- cgit v1.2.3