// SPDX-License-Identifier: GPL-2.0-or-later /* * Linux Socket Filter - Kernel level socket filtering * * Based on the design of the Berkeley Packet Filter. The new * internal format has been designed by PLUMgrid: * * Copyright (c) 2011 - 2014 PLUMgrid, http://plumgrid.com * * Authors: * * Jay Schulist <[email protected]> * Alexei Starovoitov <[email protected]> * Daniel Borkmann <[email protected]> * * Andi Kleen - Fix a few bad bugs and races. * Kris Katterjohn - Added many additional checks in bpf_check_classic() */ #include <uapi/linux/btf.h> #include <linux/filter.h> #include <linux/skbuff.h> #include <linux/vmalloc.h> #include <linux/random.h> #include <linux/bpf.h> #include <linux/btf.h> #include <linux/objtool.h> #include <linux/overflow.h> #include <linux/rbtree_latch.h> #include <linux/kallsyms.h> #include <linux/rcupdate.h> #include <linux/perf_event.h> #include <linux/extable.h> #include <linux/log2.h> #include <linux/bpf_verifier.h> #include <linux/nodemask.h> #include <linux/nospec.h> #include <linux/bpf_mem_alloc.h> #include <linux/memcontrol.h> #include <linux/execmem.h> #include <asm/barrier.h> #include <asm/unaligned.h> /* Registers */ #define BPF_R0 … #define BPF_R1 … #define BPF_R2 … #define BPF_R3 … #define BPF_R4 … #define BPF_R5 … #define BPF_R6 … #define BPF_R7 … #define BPF_R8 … #define BPF_R9 … #define BPF_R10 … /* Named registers */ #define DST … #define SRC … #define FP … #define AX … #define ARG1 … #define CTX … #define OFF … #define IMM … struct bpf_mem_alloc bpf_global_ma; bool bpf_global_ma_set; /* No hurry in this branch * * Exported for the bpf jit load helper. */ void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, unsigned int size) { … } /* tell bpf programs that include vmlinux.h kernel's PAGE_SIZE */ enum page_size_enum { … }; struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flags) { … } struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags) { … } EXPORT_SYMBOL_GPL(…); int bpf_prog_alloc_jited_linfo(struct bpf_prog *prog) { … } void bpf_prog_jit_attempt_done(struct bpf_prog *prog) { … } /* The jit engine is responsible to provide an array * for insn_off to the jited_off mapping (insn_to_jit_off). * * The idx to this array is the insn_off. Hence, the insn_off * here is relative to the prog itself instead of the main prog. * This array has one entry for each xlated bpf insn. * * jited_off is the byte off to the end of the jited insn. * * Hence, with * insn_start: * The first bpf insn off of the prog. The insn off * here is relative to the main prog. * e.g. if prog is a subprog, insn_start > 0 * linfo_idx: * The prog's idx to prog->aux->linfo and jited_linfo * * jited_linfo[linfo_idx] = prog->bpf_func * * For i > linfo_idx, * * jited_linfo[i] = prog->bpf_func + * insn_to_jit_off[linfo[i].insn_off - insn_start - 1] */ void bpf_prog_fill_jited_linfo(struct bpf_prog *prog, const u32 *insn_to_jit_off) { … } struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size, gfp_t gfp_extra_flags) { … } void __bpf_prog_free(struct bpf_prog *fp) { … } int bpf_prog_calc_tag(struct bpf_prog *fp) { … } static int bpf_adj_delta_to_imm(struct bpf_insn *insn, u32 pos, s32 end_old, s32 end_new, s32 curr, const bool probe_pass) { … } static int bpf_adj_delta_to_off(struct bpf_insn *insn, u32 pos, s32 end_old, s32 end_new, s32 curr, const bool probe_pass) { … } static int bpf_adj_branches(struct bpf_prog *prog, u32 pos, s32 end_old, s32 end_new, const bool probe_pass) { … } static void bpf_adj_linfo(struct bpf_prog *prog, u32 off, u32 delta) { … } struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, const struct bpf_insn *patch, u32 len) { … } int bpf_remove_insns(struct bpf_prog *prog, u32 off, u32 cnt) { … } static void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp) { … } void bpf_prog_kallsyms_del_all(struct bpf_prog *fp) { … } #ifdef CONFIG_BPF_JIT /* All BPF JIT sysctl knobs here. */ int bpf_jit_enable __read_mostly = … IS_BUILTIN(…); int bpf_jit_kallsyms __read_mostly = … IS_BUILTIN(…); int bpf_jit_harden __read_mostly; long bpf_jit_limit __read_mostly; long bpf_jit_limit_max __read_mostly; static void bpf_prog_ksym_set_addr(struct bpf_prog *prog) { … } static void bpf_prog_ksym_set_name(struct bpf_prog *prog) { … } static unsigned long bpf_get_ksym_start(struct latch_tree_node *n) { … } static __always_inline bool bpf_tree_less(struct latch_tree_node *a, struct latch_tree_node *b) { … } static __always_inline int bpf_tree_comp(void *key, struct latch_tree_node *n) { … } static const struct latch_tree_ops bpf_tree_ops = …; static DEFINE_SPINLOCK(bpf_lock); static LIST_HEAD(bpf_kallsyms); static struct latch_tree_root bpf_tree __cacheline_aligned; void bpf_ksym_add(struct bpf_ksym *ksym) { … } static void __bpf_ksym_del(struct bpf_ksym *ksym) { … } void bpf_ksym_del(struct bpf_ksym *ksym) { … } static bool bpf_prog_kallsyms_candidate(const struct bpf_prog *fp) { … } void bpf_prog_kallsyms_add(struct bpf_prog *fp) { … } void bpf_prog_kallsyms_del(struct bpf_prog *fp) { … } static struct bpf_ksym *bpf_ksym_find(unsigned long addr) { … } int __bpf_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char *sym) { … } bool is_bpf_text_address(unsigned long addr) { … } struct bpf_prog *bpf_prog_ksym_find(unsigned long addr) { … } const struct exception_table_entry *search_bpf_extables(unsigned long addr) { … } int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *sym) { … } int bpf_jit_add_poke_descriptor(struct bpf_prog *prog, struct bpf_jit_poke_descriptor *poke) { … } /* * BPF program pack allocator. * * Most BPF programs are pretty small. Allocating a hole page for each * program is sometime a waste. Many small bpf program also adds pressure * to instruction TLB. To solve this issue, we introduce a BPF program pack * allocator. The prog_pack allocator uses HPAGE_PMD_SIZE page (2MB on x86) * to host BPF programs. */ #define BPF_PROG_CHUNK_SHIFT … #define BPF_PROG_CHUNK_SIZE … #define BPF_PROG_CHUNK_MASK … struct bpf_prog_pack { … }; void bpf_jit_fill_hole_with_zero(void *area, unsigned int size) { … } #define BPF_PROG_SIZE_TO_NBITS(size) … static DEFINE_MUTEX(pack_mutex); static LIST_HEAD(pack_list); /* PMD_SIZE is not available in some special config, e.g. ARCH=arm with * CONFIG_MMU=n. Use PAGE_SIZE in these cases. */ #ifdef PMD_SIZE /* PMD_SIZE is really big for some archs. It doesn't make sense to * reserve too much memory in one allocation. Hardcode BPF_PROG_PACK_SIZE to * 2MiB * num_possible_nodes(). On most architectures PMD_SIZE will be * greater than or equal to 2MB. */ #define BPF_PROG_PACK_SIZE … #else #define BPF_PROG_PACK_SIZE … #endif #define BPF_PROG_CHUNK_COUNT … static struct bpf_prog_pack *alloc_new_pack(bpf_jit_fill_hole_t bpf_fill_ill_insns) { … } void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns) { … } void bpf_prog_pack_free(void *ptr, u32 size) { … } static atomic_long_t bpf_jit_current; /* Can be overridden by an arch's JIT compiler if it has a custom, * dedicated BPF backend memory area, or if neither of the two * below apply. */ u64 __weak bpf_jit_alloc_exec_limit(void) { … } static int __init bpf_jit_charge_init(void) { … } pure_initcall(bpf_jit_charge_init); int bpf_jit_charge_modmem(u32 size) { … } void bpf_jit_uncharge_modmem(u32 size) { … } void *__weak bpf_jit_alloc_exec(unsigned long size) { … } void __weak bpf_jit_free_exec(void *addr) { … } struct bpf_binary_header * bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr, unsigned int alignment, bpf_jit_fill_hole_t bpf_fill_ill_insns) { … } void bpf_jit_binary_free(struct bpf_binary_header *hdr) { … } /* Allocate jit binary from bpf_prog_pack allocator. * Since the allocated memory is RO+X, the JIT engine cannot write directly * to the memory. To solve this problem, a RW buffer is also allocated at * as the same time. The JIT engine should calculate offsets based on the * RO memory address, but write JITed program to the RW buffer. Once the * JIT engine finishes, it calls bpf_jit_binary_pack_finalize, which copies * the JITed program to the RO memory. */ struct bpf_binary_header * bpf_jit_binary_pack_alloc(unsigned int proglen, u8 **image_ptr, unsigned int alignment, struct bpf_binary_header **rw_header, u8 **rw_image, bpf_jit_fill_hole_t bpf_fill_ill_insns) { … } /* Copy JITed text from rw_header to its final location, the ro_header. */ int bpf_jit_binary_pack_finalize(struct bpf_binary_header *ro_header, struct bpf_binary_header *rw_header) { … } /* bpf_jit_binary_pack_free is called in two different scenarios: * 1) when the program is freed after; * 2) when the JIT engine fails (before bpf_jit_binary_pack_finalize). * For case 2), we need to free both the RO memory and the RW buffer. * * bpf_jit_binary_pack_free requires proper ro_header->size. However, * bpf_jit_binary_pack_alloc does not set it. Therefore, ro_header->size * must be set with either bpf_jit_binary_pack_finalize (normal path) or * bpf_arch_text_copy (when jit fails). */ void bpf_jit_binary_pack_free(struct bpf_binary_header *ro_header, struct bpf_binary_header *rw_header) { … } struct bpf_binary_header * bpf_jit_binary_pack_hdr(const struct bpf_prog *fp) { … } static inline struct bpf_binary_header * bpf_jit_binary_hdr(const struct bpf_prog *fp) { … } /* This symbol is only overridden by archs that have different * requirements than the usual eBPF JITs, f.e. when they only * implement cBPF JIT, do not set images read-only, etc. */ void __weak bpf_jit_free(struct bpf_prog *fp) { … } int bpf_jit_get_func_addr(const struct bpf_prog *prog, const struct bpf_insn *insn, bool extra_pass, u64 *func_addr, bool *func_addr_fixed) { … } static int bpf_jit_blind_insn(const struct bpf_insn *from, const struct bpf_insn *aux, struct bpf_insn *to_buff, bool emit_zext) { … } static struct bpf_prog *bpf_prog_clone_create(struct bpf_prog *fp_other, gfp_t gfp_extra_flags) { … } static void bpf_prog_clone_free(struct bpf_prog *fp) { … } void bpf_jit_prog_release_other(struct bpf_prog *fp, struct bpf_prog *fp_other) { … } struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *prog) { … } #endif /* CONFIG_BPF_JIT */ /* Base function for offset calculation. Needs to go into .text section, * therefore keeping it non-static as well; will also be used by JITs * anyway later on, so do not let the compiler omit it. This also needs * to go into kallsyms for correlation from e.g. bpftool, so naming * must not change. */ noinline u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) { … } EXPORT_SYMBOL_GPL(…); /* All UAPI available opcodes. */ #define BPF_INSN_MAP(INSN_2, INSN_3) … bool bpf_opcode_in_insntable(u8 code) { … } #ifndef CONFIG_BPF_JIT_ALWAYS_ON /** * ___bpf_prog_run - run eBPF program on a given context * @regs: is the array of MAX_BPF_EXT_REG eBPF pseudo-registers * @insn: is the array of eBPF instructions * * Decode and execute eBPF instructions. * * Return: whatever value is in %BPF_R0 at program exit */ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn) { #define BPF_INSN_2_LBL … #define BPF_INSN_3_LBL … static const void * const jumptable[256] __annotate_jump_table = { [0 ... 255] = &&default_label, /* Now overwrite non-defaults ... */ BPF_INSN_MAP(BPF_INSN_2_LBL, BPF_INSN_3_LBL), /* Non-UAPI available opcodes. */ [BPF_JMP | BPF_CALL_ARGS] = &&JMP_CALL_ARGS, [BPF_JMP | BPF_TAIL_CALL] = &&JMP_TAIL_CALL, [BPF_ST | BPF_NOSPEC] = &&ST_NOSPEC, [BPF_LDX | BPF_PROBE_MEM | BPF_B] = &&LDX_PROBE_MEM_B, [BPF_LDX | BPF_PROBE_MEM | BPF_H] = &&LDX_PROBE_MEM_H, [BPF_LDX | BPF_PROBE_MEM | BPF_W] = &&LDX_PROBE_MEM_W, [BPF_LDX | BPF_PROBE_MEM | BPF_DW] = &&LDX_PROBE_MEM_DW, [BPF_LDX | BPF_PROBE_MEMSX | BPF_B] = &&LDX_PROBE_MEMSX_B, [BPF_LDX | BPF_PROBE_MEMSX | BPF_H] = &&LDX_PROBE_MEMSX_H, [BPF_LDX | BPF_PROBE_MEMSX | BPF_W] = &&LDX_PROBE_MEMSX_W, }; #undef BPF_INSN_3_LBL #undef BPF_INSN_2_LBL u32 tail_call_cnt = 0; #define CONT … #define CONT_JMP … select_insn: goto *jumptable[insn->code]; /* Explicitly mask the register-based shift amounts with 63 or 31 * to avoid undefined behavior. Normally this won't affect the * generated code, for example, in case of native 64 bit archs such * as x86-64 or arm64, the compiler is optimizing the AND away for * the interpreter. In case of JITs, each of the JIT backends compiles * the BPF shift operations to machine instructions which produce * implementation-defined results in such a case; the resulting * contents of the register may be arbitrary, but program behaviour * as a whole remains defined. In other words, in case of JIT backends, * the AND must /not/ be added to the emitted LSH/RSH/ARSH translation. */ /* ALU (shifts) */ #define SHT … /* ALU (rest) */ #define ALU … ALU(ADD, +) ALU(SUB, -) ALU(AND, &) ALU(OR, |) ALU(XOR, ^) ALU(MUL, *) SHT(LSH, <<) SHT(RSH, >>) #undef SHT #undef ALU ALU_NEG: DST = (u32) -DST; CONT; ALU64_NEG: DST = -DST; CONT; ALU_MOV_X: switch (OFF) { case 0: DST = (u32) SRC; break; case 8: DST = (u32)(s8) SRC; break; case 16: DST = (u32)(s16) SRC; break; } CONT; ALU_MOV_K: DST = (u32) IMM; CONT; ALU64_MOV_X: switch (OFF) { case 0: DST = SRC; break; case 8: DST = (s8) SRC; break; case 16: DST = (s16) SRC; break; case 32: DST = (s32) SRC; break; } CONT; ALU64_MOV_K: DST = IMM; CONT; LD_IMM_DW: DST = (u64) (u32) insn[0].imm | ((u64) (u32) insn[1].imm) << 32; insn++; CONT; ALU_ARSH_X: DST = (u64) (u32) (((s32) DST) >> (SRC & 31)); CONT; ALU_ARSH_K: DST = (u64) (u32) (((s32) DST) >> IMM); CONT; ALU64_ARSH_X: (*(s64 *) &DST) >>= (SRC & 63); CONT; ALU64_ARSH_K: (*(s64 *) &DST) >>= IMM; CONT; ALU64_MOD_X: switch (OFF) { case 0: div64_u64_rem(DST, SRC, &AX); DST = AX; break; case 1: AX = div64_s64(DST, SRC); DST = DST - AX * SRC; break; } CONT; ALU_MOD_X: switch (OFF) { case 0: AX = (u32) DST; DST = do_div(AX, (u32) SRC); break; case 1: AX = abs((s32)DST); AX = do_div(AX, abs((s32)SRC)); if ((s32)DST < 0) DST = (u32)-AX; else DST = (u32)AX; break; } CONT; ALU64_MOD_K: switch (OFF) { case 0: div64_u64_rem(DST, IMM, &AX); DST = AX; break; case 1: AX = div64_s64(DST, IMM); DST = DST - AX * IMM; break; } CONT; ALU_MOD_K: switch (OFF) { case 0: AX = (u32) DST; DST = do_div(AX, (u32) IMM); break; case 1: AX = abs((s32)DST); AX = do_div(AX, abs((s32)IMM)); if ((s32)DST < 0) DST = (u32)-AX; else DST = (u32)AX; break; } CONT; ALU64_DIV_X: switch (OFF) { case 0: DST = div64_u64(DST, SRC); break; case 1: DST = div64_s64(DST, SRC); break; } CONT; ALU_DIV_X: switch (OFF) { case 0: AX = (u32) DST; do_div(AX, (u32) SRC); DST = (u32) AX; break; case 1: AX = abs((s32)DST); do_div(AX, abs((s32)SRC)); if (((s32)DST < 0) == ((s32)SRC < 0)) DST = (u32)AX; else DST = (u32)-AX; break; } CONT; ALU64_DIV_K: switch (OFF) { case 0: DST = div64_u64(DST, IMM); break; case 1: DST = div64_s64(DST, IMM); break; } CONT; ALU_DIV_K: switch (OFF) { case 0: AX = (u32) DST; do_div(AX, (u32) IMM); DST = (u32) AX; break; case 1: AX = abs((s32)DST); do_div(AX, abs((s32)IMM)); if (((s32)DST < 0) == ((s32)IMM < 0)) DST = (u32)AX; else DST = (u32)-AX; break; } CONT; ALU_END_TO_BE: switch (IMM) { case 16: DST = (__force u16) cpu_to_be16(DST); break; case 32: DST = (__force u32) cpu_to_be32(DST); break; case 64: DST = (__force u64) cpu_to_be64(DST); break; } CONT; ALU_END_TO_LE: switch (IMM) { case 16: DST = (__force u16) cpu_to_le16(DST); break; case 32: DST = (__force u32) cpu_to_le32(DST); break; case 64: DST = (__force u64) cpu_to_le64(DST); break; } CONT; ALU64_END_TO_LE: switch (IMM) { case 16: DST = (__force u16) __swab16(DST); break; case 32: DST = (__force u32) __swab32(DST); break; case 64: DST = (__force u64) __swab64(DST); break; } CONT; /* CALL */ JMP_CALL: /* Function call scratches BPF_R1-BPF_R5 registers, * preserves BPF_R6-BPF_R9, and stores return value * into BPF_R0. */ BPF_R0 = (__bpf_call_base + insn->imm)(BPF_R1, BPF_R2, BPF_R3, BPF_R4, BPF_R5); CONT; JMP_CALL_ARGS: BPF_R0 = (__bpf_call_base_args + insn->imm)(BPF_R1, BPF_R2, BPF_R3, BPF_R4, BPF_R5, insn + insn->off + 1); CONT; JMP_TAIL_CALL: { struct bpf_map *map = (struct bpf_map *) (unsigned long) BPF_R2; struct bpf_array *array = container_of(map, struct bpf_array, map); struct bpf_prog *prog; u32 index = BPF_R3; if (unlikely(index >= array->map.max_entries)) goto out; if (unlikely(tail_call_cnt >= MAX_TAIL_CALL_CNT)) goto out; tail_call_cnt++; prog = READ_ONCE(array->ptrs[index]); if (!prog) goto out; /* ARG1 at this point is guaranteed to point to CTX from * the verifier side due to the fact that the tail call is * handled like a helper, that is, bpf_tail_call_proto, * where arg1_type is ARG_PTR_TO_CTX. */ insn = prog->insnsi; goto select_insn; out: CONT; } JMP_JA: insn += insn->off; CONT; JMP32_JA: insn += insn->imm; CONT; JMP_EXIT: return BPF_R0; /* JMP */ #define COND_JMP … COND_JMP(u, JEQ, ==) COND_JMP(u, JNE, !=) COND_JMP(u, JGT, >) COND_JMP(u, JLT, <) COND_JMP(u, JGE, >=) COND_JMP(u, JLE, <=) COND_JMP(u, JSET, &) COND_JMP(s, JSGT, >) COND_JMP(s, JSLT, <) COND_JMP(s, JSGE, >=) COND_JMP(s, JSLE, <=) #undef COND_JMP /* ST, STX and LDX*/ ST_NOSPEC: /* Speculation barrier for mitigating Speculative Store Bypass. * In case of arm64, we rely on the firmware mitigation as * controlled via the ssbd kernel parameter. Whenever the * mitigation is enabled, it works for all of the kernel code * with no need to provide any additional instructions here. * In case of x86, we use 'lfence' insn for mitigation. We * reuse preexisting logic from Spectre v1 mitigation that * happens to produce the required code on x86 for v4 as well. */ barrier_nospec(); CONT; #define LDST … LDST(B, u8) LDST(H, u16) LDST(W, u32) LDST(DW, u64) #undef LDST #define LDSX … LDSX(B, s8) LDSX(H, s16) LDSX(W, s32) #undef LDSX #define ATOMIC_ALU_OP … STX_ATOMIC_DW: STX_ATOMIC_W: switch (IMM) { ATOMIC_ALU_OP(BPF_ADD, add) ATOMIC_ALU_OP(BPF_AND, and) ATOMIC_ALU_OP(BPF_OR, or) ATOMIC_ALU_OP(BPF_XOR, xor) #undef ATOMIC_ALU_OP case BPF_XCHG: if (BPF_SIZE(insn->code) == BPF_W) SRC = (u32) atomic_xchg( (atomic_t *)(unsigned long) (DST + insn->off), (u32) SRC); else SRC = (u64) atomic64_xchg( (atomic64_t *)(unsigned long) (DST + insn->off), (u64) SRC); break; case BPF_CMPXCHG: if (BPF_SIZE(insn->code) == BPF_W) BPF_R0 = (u32) atomic_cmpxchg( (atomic_t *)(unsigned long) (DST + insn->off), (u32) BPF_R0, (u32) SRC); else BPF_R0 = (u64) atomic64_cmpxchg( (atomic64_t *)(unsigned long) (DST + insn->off), (u64) BPF_R0, (u64) SRC); break; default: goto default_label; } CONT; default_label: /* If we ever reach this, we have a bug somewhere. Die hard here * instead of just returning 0; we could be somewhere in a subprog, * so execution could continue otherwise which we do /not/ want. * * Note, verifier whitelists all opcodes in bpf_opcode_in_insntable(). */ pr_warn("BPF interpreter: unknown opcode %02x (imm: 0x%x)\n", insn->code, insn->imm); BUG_ON(1); return 0; } #define PROG_NAME … #define DEFINE_BPF_PROG_RUN … #define PROG_NAME_ARGS … #define DEFINE_BPF_PROG_RUN_ARGS … #define EVAL1 … #define EVAL2 … #define EVAL3 … #define EVAL4 … #define EVAL5 … #define EVAL6 … EVAL6(DEFINE_BPF_PROG_RUN, 32, 64, 96, 128, 160, 192); EVAL6(DEFINE_BPF_PROG_RUN, 224, 256, 288, 320, 352, 384); EVAL4(DEFINE_BPF_PROG_RUN, 416, 448, 480, 512); EVAL6(DEFINE_BPF_PROG_RUN_ARGS, 32, 64, 96, 128, 160, 192); EVAL6(DEFINE_BPF_PROG_RUN_ARGS, 224, 256, 288, 320, 352, 384); EVAL4(DEFINE_BPF_PROG_RUN_ARGS, 416, 448, 480, 512); #define PROG_NAME_LIST … static unsigned int (*interpreters[])(const void *ctx, const struct bpf_insn *insn) = { EVAL6(PROG_NAME_LIST, 32, 64, 96, 128, 160, 192) EVAL6(PROG_NAME_LIST, 224, 256, 288, 320, 352, 384) EVAL4(PROG_NAME_LIST, 416, 448, 480, 512) }; #undef PROG_NAME_LIST #define PROG_NAME_LIST … static __maybe_unused u64 (*interpreters_args[])(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5, const struct bpf_insn *insn) = { EVAL6(PROG_NAME_LIST, 32, 64, 96, 128, 160, 192) EVAL6(PROG_NAME_LIST, 224, 256, 288, 320, 352, 384) EVAL4(PROG_NAME_LIST, 416, 448, 480, 512) }; #undef PROG_NAME_LIST #ifdef CONFIG_BPF_SYSCALL void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth) { stack_depth = max_t(u32, stack_depth, 1); insn->off = (s16) insn->imm; insn->imm = interpreters_args[(round_up(stack_depth, 32) / 32) - 1] - __bpf_call_base_args; insn->code = BPF_JMP | BPF_CALL_ARGS; } #endif #else static unsigned int __bpf_prog_ret0_warn(const void *ctx, const struct bpf_insn *insn) { … } #endif bool bpf_prog_map_compatible(struct bpf_map *map, const struct bpf_prog *fp) { … } static int bpf_check_tail_call(const struct bpf_prog *fp) { … } static void bpf_prog_select_func(struct bpf_prog *fp) { … } /** * bpf_prog_select_runtime - select exec runtime for BPF program * @fp: bpf_prog populated with BPF program * @err: pointer to error variable * * Try to JIT eBPF program, if JIT is not available, use interpreter. * The BPF program will be executed via bpf_prog_run() function. * * Return: the &fp argument along with &err set to 0 for success or * a negative errno code on failure */ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err) { … } EXPORT_SYMBOL_GPL(…); static unsigned int __bpf_prog_ret1(const void *ctx, const struct bpf_insn *insn) { … } static struct bpf_prog_dummy { … } dummy_bpf_prog = …; struct bpf_empty_prog_array bpf_empty_prog_array = …; EXPORT_SYMBOL(…); struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags) { … } void bpf_prog_array_free(struct bpf_prog_array *progs) { … } static void __bpf_prog_array_free_sleepable_cb(struct rcu_head *rcu) { … } void bpf_prog_array_free_sleepable(struct bpf_prog_array *progs) { … } int bpf_prog_array_length(struct bpf_prog_array *array) { … } bool bpf_prog_array_is_empty(struct bpf_prog_array *array) { … } static bool bpf_prog_array_copy_core(struct bpf_prog_array *array, u32 *prog_ids, u32 request_cnt) { … } int bpf_prog_array_copy_to_user(struct bpf_prog_array *array, __u32 __user *prog_ids, u32 cnt) { … } void bpf_prog_array_delete_safe(struct bpf_prog_array *array, struct bpf_prog *old_prog) { … } /** * bpf_prog_array_delete_safe_at() - Replaces the program at the given * index into the program array with * a dummy no-op program. * @array: a bpf_prog_array * @index: the index of the program to replace * * Skips over dummy programs, by not counting them, when calculating * the position of the program to replace. * * Return: * * 0 - Success * * -EINVAL - Invalid index value. Must be a non-negative integer. * * -ENOENT - Index out of range */ int bpf_prog_array_delete_safe_at(struct bpf_prog_array *array, int index) { … } /** * bpf_prog_array_update_at() - Updates the program at the given index * into the program array. * @array: a bpf_prog_array * @index: the index of the program to update * @prog: the program to insert into the array * * Skips over dummy programs, by not counting them, when calculating * the position of the program to update. * * Return: * * 0 - Success * * -EINVAL - Invalid index value. Must be a non-negative integer. * * -ENOENT - Index out of range */ int bpf_prog_array_update_at(struct bpf_prog_array *array, int index, struct bpf_prog *prog) { … } int bpf_prog_array_copy(struct bpf_prog_array *old_array, struct bpf_prog *exclude_prog, struct bpf_prog *include_prog, u64 bpf_cookie, struct bpf_prog_array **new_array) { … } int bpf_prog_array_copy_info(struct bpf_prog_array *array, u32 *prog_ids, u32 request_cnt, u32 *prog_cnt) { … } void __bpf_free_used_maps(struct bpf_prog_aux *aux, struct bpf_map **used_maps, u32 len) { … } static void bpf_free_used_maps(struct bpf_prog_aux *aux) { … } void __bpf_free_used_btfs(struct btf_mod_pair *used_btfs, u32 len) { … } static void bpf_free_used_btfs(struct bpf_prog_aux *aux) { … } static void bpf_prog_free_deferred(struct work_struct *work) { … } void bpf_prog_free(struct bpf_prog *fp) { … } EXPORT_SYMBOL_GPL(…); /* RNG for unprivileged user space with separated state from prandom_u32(). */ static DEFINE_PER_CPU(struct rnd_state, bpf_user_rnd_state); void bpf_user_rnd_init_once(void) { … } BPF_CALL_0(bpf_user_rnd_u32) { … } BPF_CALL_0(bpf_get_raw_cpu_id) { … } /* Weak definitions of helper functions in case we don't have bpf syscall. */ const struct bpf_func_proto bpf_map_lookup_elem_proto __weak; const struct bpf_func_proto bpf_map_update_elem_proto __weak; const struct bpf_func_proto bpf_map_delete_elem_proto __weak; const struct bpf_func_proto bpf_map_push_elem_proto __weak; const struct bpf_func_proto bpf_map_pop_elem_proto __weak; const struct bpf_func_proto bpf_map_peek_elem_proto __weak; const struct bpf_func_proto bpf_map_lookup_percpu_elem_proto __weak; const struct bpf_func_proto bpf_spin_lock_proto __weak; const struct bpf_func_proto bpf_spin_unlock_proto __weak; const struct bpf_func_proto bpf_jiffies64_proto __weak; const struct bpf_func_proto bpf_get_prandom_u32_proto __weak; const struct bpf_func_proto bpf_get_smp_processor_id_proto __weak; const struct bpf_func_proto bpf_get_numa_node_id_proto __weak; const struct bpf_func_proto bpf_ktime_get_ns_proto __weak; const struct bpf_func_proto bpf_ktime_get_boot_ns_proto __weak; const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto __weak; const struct bpf_func_proto bpf_ktime_get_tai_ns_proto __weak; const struct bpf_func_proto bpf_get_current_pid_tgid_proto __weak; const struct bpf_func_proto bpf_get_current_uid_gid_proto __weak; const struct bpf_func_proto bpf_get_current_comm_proto __weak; const struct bpf_func_proto bpf_get_current_cgroup_id_proto __weak; const struct bpf_func_proto bpf_get_current_ancestor_cgroup_id_proto __weak; const struct bpf_func_proto bpf_get_local_storage_proto __weak; const struct bpf_func_proto bpf_get_ns_current_pid_tgid_proto __weak; const struct bpf_func_proto bpf_snprintf_btf_proto __weak; const struct bpf_func_proto bpf_seq_printf_btf_proto __weak; const struct bpf_func_proto bpf_set_retval_proto __weak; const struct bpf_func_proto bpf_get_retval_proto __weak; const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void) { … } const struct bpf_func_proto * __weak bpf_get_trace_vprintk_proto(void) { … } u64 __weak bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy) { … } EXPORT_SYMBOL_GPL(…); /* Always built-in helper functions. */ const struct bpf_func_proto bpf_tail_call_proto = …; /* Stub for JITs that only support cBPF. eBPF programs are interpreted. * It is encouraged to implement bpf_int_jit_compile() instead, so that * eBPF and implicitly also cBPF can get JITed! */ struct bpf_prog * __weak bpf_int_jit_compile(struct bpf_prog *prog) { … } /* Stub for JITs that support eBPF. All cBPF code gets transformed into * eBPF by the kernel and is later compiled by bpf_int_jit_compile(). */ void __weak bpf_jit_compile(struct bpf_prog *prog) { … } bool __weak bpf_helper_changes_pkt_data(void *func) { … } /* Return TRUE if the JIT backend wants verifier to enable sub-register usage * analysis code and wants explicit zero extension inserted by verifier. * Otherwise, return FALSE. * * The verifier inserts an explicit zero extension after BPF_CMPXCHGs even if * you don't override this. JITs that don't want these extra insns can detect * them using insn_is_zext. */ bool __weak bpf_jit_needs_zext(void) { … } /* Return true if the JIT inlines the call to the helper corresponding to * the imm. * * The verifier will not patch the insn->imm for the call to the helper if * this returns true. */ bool __weak bpf_jit_inlines_helper_call(s32 imm) { … } /* Return TRUE if the JIT backend supports mixing bpf2bpf and tailcalls. */ bool __weak bpf_jit_supports_subprog_tailcalls(void) { … } bool __weak bpf_jit_supports_percpu_insn(void) { … } bool __weak bpf_jit_supports_kfunc_call(void) { … } bool __weak bpf_jit_supports_far_kfunc_call(void) { … } bool __weak bpf_jit_supports_arena(void) { … } bool __weak bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena) { … } u64 __weak bpf_arch_uaddress_limit(void) { … } /* Return TRUE if the JIT backend satisfies the following two conditions: * 1) JIT backend supports atomic_xchg() on pointer-sized words. * 2) Under the specific arch, the implementation of xchg() is the same * as atomic_xchg() on pointer-sized words. */ bool __weak bpf_jit_supports_ptr_xchg(void) { … } /* To execute LD_ABS/LD_IND instructions __bpf_prog_run() may call * skb_copy_bits(), so provide a weak definition of it for NET-less config. */ int __weak skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len) { … } int __weak bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, void *addr1, void *addr2) { … } void * __weak bpf_arch_text_copy(void *dst, void *src, size_t len) { … } int __weak bpf_arch_text_invalidate(void *dst, size_t len) { … } bool __weak bpf_jit_supports_exceptions(void) { … } void __weak arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie) { … } /* for configs without MMU or 32-bit */ __weak const struct bpf_map_ops arena_map_ops; __weak u64 bpf_arena_get_user_vm_start(struct bpf_arena *arena) { … } __weak u64 bpf_arena_get_kern_vm_start(struct bpf_arena *arena) { … } #ifdef CONFIG_BPF_SYSCALL static int __init bpf_global_ma_init(void) { … } late_initcall(bpf_global_ma_init); #endif DEFINE_STATIC_KEY_FALSE(bpf_stats_enabled_key); EXPORT_SYMBOL(…); /* All definitions of tracepoints related to BPF. */ #define CREATE_TRACE_POINTS #include <linux/bpf_trace.h> EXPORT_TRACEPOINT_SYMBOL_GPL(…); EXPORT_TRACEPOINT_SYMBOL_GPL(…);
Codebase Browser
linux